diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
index 1cf92e1..8840b74 100644
--- a/.claude-plugin/marketplace.json
+++ b/.claude-plugin/marketplace.json
@@ -693,10 +693,10 @@
     },
     {
       "name": "deep-research",
-      "description": "Generate format-controlled research reports with evidence tracking, citations, and iterative review. Use when users request research reports, literature reviews, market or industry analysis, competitive landscapes, policy or technical briefs, or strict report templates and section formatting",
+      "description": "Generate format-controlled research reports with evidence tracking, source governance, and multi-pass synthesis. V6.1 adds: source accessibility (circular verification forbidden, exclusive advantage encouraged). Enterprise Research Mode: six-dimension data collection, SWOT/barrier/risk frameworks, and three-level quality control for company research",
       "source": "./",
       "strict": false,
-      "version": "1.0.0",
+      "version": "2.4.0",
       "category": "documentation",
       "keywords": [
         "research",
@@ -706,7 +706,10 @@
         "market-research",
         "citations",
         "evidence",
-        "deepresearch"
+        "deepresearch",
+        "enterprise",
+        "company-research",
+        "due-diligence"
       ],
       "skills": [
         "./deep-research"
diff --git a/deep-research/SKILL.md b/deep-research/SKILL.md
index f15212e..135e891 100644
--- a/deep-research/SKILL.md
+++ b/deep-research/SKILL.md
@@ -1,183 +1,479 @@
 ---
 name: deep-research
 description: |
-  Generate format-controlled research reports with evidence tracking, citations, and iterative review. This skill should be used when users request a research report, literature review, market or industry analysis, competitive landscape, policy or technical brief, or require a strict report template and section formatting that a single deepresearch pass cannot reliably enforce.
+  Generate format-controlled research reports with evidence tracking, citations, source governance, and multi-pass synthesis.
+  This skill should be used when users request a research report, literature review, market or industry analysis,
+  competitive landscape, policy or technical brief. Triggers: "帮我调研一下", "深度研究", "综述报告", "深入分析",
+  "research this topic", "write a report on", "survey the literature on", "competitive analysis of",
+  "技术选型分析", "竞品研究", "政策分析", "行业报告".
+  V6 adds: source-type governance, AS_OF freshness checks, mandatory counter-review, and citation registry. V6.1 adds: source accessibility (circular verification forbidden, exclusive advantage encouraged).
 ---
 
 # Deep Research
 
-Create high-fidelity research reports with strict format control, evidence mapping, and multi-pass synthesis.
+Create high-fidelity research reports with strict format control, evidence mapping, source governance, and multi-pass synthesis.
 
-## Quick Start
-
-1. Clarify the report spec and format contract
-2. Build a research plan and query set
-3. Collect evidence with the deepresearch tool (multi-pass if needed)
-4. Triage sources and build an evidence table
-5. Draft the full report in multiple complete passes (parallel subagents)
-6. UNION merge, enforce format compliance, verify citations
-7. Present draft for human review and iterate
-
-## Core Workflow
-
-Copy this checklist and track progress:
+## Architecture: Lead Agent + Subagents
 
 ```
-Deep Research Progress:
-- [ ] Step 1: Intake and format contract
-- [ ] Step 2: Research plan and query set
-- [ ] Step 3: Evidence collection (deepresearch tool)
-- [ ] Step 4: Source triage and evidence table
-- [ ] Step 5: Outline and section map
-- [ ] Step 6: Multi-pass full drafting (parallel subagents)
-- [ ] Step 7: UNION merge and format compliance
-- [ ] Step 8: Evidence and citation verification
-- [ ] Step 9: Present draft for human review and iterate
+Lead Agent (coordinator — minimizes raw search context)
+  |
+  P0: Environment + source policy setup
+  |
+  P1: Research Task Board (roles, queries, parallel groups)
+  |
+  Dispatch ──→ Subagent A ──→ writes task-a.md ──┐
+           ──→ Subagent B ──→ writes task-b.md ──┤ (parallel)
+           ──→ Subagent C ──→ writes task-c.md ──┘
+  |                                               |
+  |     research-notes/  <────────────────────────┘
+  |
+  P2: Build citation registry with source_type + as_of + authority
+  P3: Evidence-mapped outline with counter-claim flags
+  P4: Draft from notes (never from raw search results)
+  P5: Counter-review (claims, confidence, alternatives)
+  P6: Verify (every [n] in registry, traceability check)
+  P7: Polish → final report with confidence markers
 ```
 
-### Step 1: Intake and Format Contract
+**Context efficiency:** Subagents' raw search results stay in their context and are discarded. Lead agent sees only distilled notes (~60-70% context reduction).
 
-Establish the report requirements before any research:
+## Mode Selection
 
-- Confirm audience, purpose, scope, time range, and geography
-- Lock output format: Markdown, DOCX, slides, or user-provided template
-- Capture required sections and exact formatting rules
-- Confirm citation style (footnotes, inline, numbered, APA, etc.)
-- Confirm length targets per section
-- Ask for any existing style guide or sample report
+Determine the research mode before starting:
 
-Create a concise report spec file:
+| Dimension | Options |
+|-----------|---------|
+| **Topic Mode** | Enterprise Research (company/corporation) OR General Research (industry/policy/tech) |
+| **Depth Mode** | Standard (5-6 tasks, 3000-8000 words) OR Lightweight (3-4 tasks, 2000-4000 words) |
+
+- **Enterprise Research Mode**: Six-dimension data collection with structured analysis frameworks (SWOT, risk matrix, competitive barrier quantification)
+- **General Research Mode**: Standard P0-P7 research pipeline with source governance
+- **Depth Selection**: Lightweight for single entity/concept < 30 words; Standard for multi-entity comparison or "深入"/"comprehensive" requests
+
+## Source Governance (V6)
+
+### Source Accessibility Classification
+
+**CRITICAL RULE**: Every source must be classified by accessibility:
+
+| Accessibility | Definition | Examples | Usage Rule |
+|--------------|------------|----------|------------|
+| `public` | Available to any external researcher without authentication | Public websites, news articles, WHOIS (without privacy), academic papers | ✅ Always allowed |
+| `semi-public` | Requires registration or limited access | LinkedIn profiles, Crunchbase basic, industry reports (free tier) | ✅ Allowed with disclosure |
+| `exclusive-user-provided` | User's paid subscriptions, private APIs, proprietary databases | Crunchbase Pro, PitchBook, private data feeds, internal databases | ✅ **ALLOWED** for third-party research |
+| `private-user-owned` | User's own accounts when researching themselves | User's registrar for user's own company, user's bank for user's own finances | ❌ **FORBIDDEN** - circular verification |
+
+**⚠️ CIRCULAR VERIFICATION BAN**: You must NOT:
+- Use user's private data to "discover" what they already know about themselves
+- Research user's own company by accessing user's private accounts
+- Present user's private knowledge as "research findings"
+
+**✅ EXCLUSIVE INFORMATION ADVANTAGE**: You SHOULD:
+- Use user's Crunchbase Pro to research competitors
+- Use user's proprietary databases for market research
+- Use user's private APIs for investment analysis
+- Leverage any exclusive source user provides for third-party research
+
+### Source Type Labels
+
+Every source MUST also be tagged with:
+
+| Label | Definition | Examples |
+|-------|------------|----------|
+| `official` | Primary source, official documentation | Company SEC filings, government reports, official blog |
+| `academic` | Peer-reviewed research | Journal articles, conference papers, dissertations |
+| `secondary-industry` | Professional analysis | Industry reports, analyst coverage, trade publications |
+| `journalism` | News reporting | Reputable media outlets, investigative journalism |
+| `community` | User-generated content | Forums, reviews, social media, Q&A sites |
+| `other` | Uncategorized or mixed | Aggregators, unverified sources |
+
+**Quality Gates:**
+- Standard mode: ≥30% official sources in final approved set
+- Lightweight mode: ≥20% official sources
+- Maximum single-source share: ≤25% (Standard), ≤30% (Lightweight)
+- Minimum unique domains: 5 (Standard), 3 (Lightweight)
+
+## AS_OF Date Policy
+
+Set `AS_OF` date explicitly at P0. For all time-sensitive claims:
+- Include source publication date with every citation
+- Downgrade confidence if source is older than relevant horizon
+- Flag stale sources in registry (studies >3 years, news >6 months for fast-moving topics)
+
+## P0: Environment & Policy Setup
+
+Check capabilities before starting:
+
+| Check | Requirement | Impact if Missing |
+|-------|-------------|-------------------|
+| web_search available | Required | Stop - cannot proceed |
+| web_fetch available | Required for DEEP tasks | SCAN-only mode |
+| Subagent dispatch | Preferred | Degrade to sequential |
+| Filesystem writable | Required | In-memory notes only |
+
+Set policy variables:
+- `AS_OF`: Today's date (YYYY-MM-DD) - mandatory for timed topics
+- `MODE`: Standard (default) or Lightweight
+- `SOURCE_TYPE_POLICY`: Enforce official/academic/secondary/journalism/community/other labels
+- `COUNTER_REVIEW_PLAN`: What opposing interpretation to test
+
+Report: `[P0 complete] Subagent: {yes/no}. Mode: {standard/lightweight}. AS_OF: {YYYY-MM-DD}.`
+
+When researching a specific company/enterprise, follow this specialized workflow that ensures six-dimension coverage, quantified analysis frameworks, and three-level quality control.
+
+### Enterprise Workflow Overview
 
 ```
-Report Spec:
-- Audience:
-- Purpose:
-- Scope:
-- Time Range:
-- Geography:
-- Required Sections:
-- Section Formatting Rules:
-- Citation Style:
-- Output Format:
-- Length Targets:
-- Tone:
-- Must-Include Sources:
-- Must-Exclude Topics:
+Enterprise Research Progress:
+- [ ] E1: Intake — confirm company entity, research depth, format contract
+- [ ] E2: Six-dimension data collection (parallel where possible)
+  - [ ] D1: Company fundamentals (entity, founding, funding, ownership)
+  - [ ] D2: Business & products (segments, products, revenue structure)
+  - [ ] D3: Competitive position (industry rank, competitors, barriers)
+  - [ ] D4: Financial & operations (3-year financials, efficiency metrics)
+  - [ ] D5: Recent developments (6-month events, strategic signals)
+  - [ ] D6: Internal/proprietary sources (or note limitation)
+- [ ] E3: Structured analysis frameworks
+  - [ ] SWOT analysis (evidence-backed, 4 quadrants × 3-5 entries)
+  - [ ] Competitive barrier quantification (7 dimensions, weighted score)
+  - [ ] Risk matrix (8 categories, probability × impact)
+  - [ ] Comprehensive scorecard (6 dimensions, weighted total)
+- [ ] E4: L1/L2/L3 quality checks at each stage transition
+- [ ] E5: Draft report using 7-chapter enterprise template
+- [ ] E6: Multi-pass drafting + UNION merge (same as general Step 6-7)
+- [ ] E7: Present draft for human review and iterate
 ```
 
-If a user provides a template or an example report, treat it as a hard constraint and mirror the structure.
+## P1: Research Task Board
 
-### Step 2: Research Plan and Query Set
+Decompose the research question into 4-6 investigation tasks (Standard) or 3-4 tasks (Lightweight).
 
-Define the research strategy before calling tools:
+Each task assignment includes:
+- **Expert Role**: Specialist persona (e.g., "Policy Historian", "Ecosystem Mapper")
+- **Objective**: One-sentence investigation goal
+- **Queries**: 2-3 pre-planned search queries
+- **Depth**: DEEP (fetch 2-3 full articles) or SCAN (snippets sufficient)
+- **Output**: Path to research notes file
+- **Parallel Group**: Group A (independent) or Group B (depends on Group A)
 
-- Break the main question into 3-7 subquestions
-- Define key entities, keywords, and synonyms
-- Identify primary sources vs secondary sources
-- Define disqualifiers (outdated, low quality, opinion-only)
-- Assemble a query set per section
+### Task Decomposition Rules
 
-Use [references/research_plan_checklist.md](references/research_plan_checklist.md) for guidance.
+1. Each task covers one coherent sub-topic a specialist would own
+2. Group A tasks must be independent and source-diverse
+3. Max 3 tasks per parallel group (concurrency limit)
+4. Every task must flag time-sensitive claims and expected citation aging risk
 
-### Step 3: Evidence Collection (Deepresearch Tool)
+### Enterprise Research Integration
 
-Use the deepresearch tool to collect evidence and citations.
+When in Enterprise Research Mode, task board maps to six dimensions:
+- Task A: Company fundamentals (entity, founding, funding, ownership)
+- Task B: Business & products (segments, products, revenue structure)
+- Task C: Competitive position (industry rank, competitors, barriers)
+- Task D: Financial & operations (3-year financials, efficiency metrics)
+- Task E: Recent developments (6-month events, strategic signals)
+- Task F: Internal/proprietary sources (or document limitation)
 
-- Run multiple complete passes if coverage is uncertain
-- Vary query phrasing to reduce blind spots
-- Preserve raw tool output in files for traceability
+Report: `[P1 complete] {N} tasks in {M} groups. Dispatching Group A.`
+
+---
+
+## Enterprise Research Mode (Specialized Pipeline)
+
+When researching a specific company/enterprise, follow this specialized workflow that ensures six-dimension coverage, quantified analysis frameworks, and three-level quality control.
+
+### E1: Intake
+
+Same as P0/P1 above, plus:
+- Confirm the exact legal entity being researched (parent vs subsidiary)
+- Select research depth: Quick scan (3-5 pages) / Standard (10-20 pages) / Deep (20-40 pages)
+- Identify any specific comparison targets (benchmark companies)
+
+## P2: Dispatch + Investigate
+
+Subagents execute tasks using [references/subagent_prompt.md](references/subagent_prompt.md) and output to [references/research_notes_format.md](references/research_notes_format.md).
+
+### With Subagents (Claude Code / Cowork / DeerFlow)
+
+1. Dispatch Group A tasks in parallel (max 3 concurrent)
+2. Each subagent searches, fetches, and tags source types
+3. Every source line includes `Source-Type` and `As Of`
+4. Wait for Group A completion
+5. Dispatch Group B (can read Group A notes)
+
+### Subagent Output Requirements
+
+Each task-{id}.md must contain:
+- **Sources section**: URLs from actual search results with Source-Type, As Of, Authority (1-10)
+- **Findings section**: Max 10 one-sentence facts with source numbers
+- **Deep Read Notes** (DEEP tasks): 2-3 sources read in full with key data/insights
+- **Gaps section**: What was searched but NOT found, alternative interpretations
+
+### Without Subagents (Degraded Mode)
+
+Lead agent executes tasks sequentially, acting as each specialist. Raw search results are discarded after writing notes.
+
+### Enterprise Research: Six-Dimension Collection
+
+Follow [references/enterprise_research_methodology.md](references/enterprise_research_methodology.md) for:
+- Detailed collection workflow per dimension (query strategies, data fields, validation)
+- Data source priority matrix (P0-P3 ranking)
+- Cross-validation rules (min sources, max deviation thresholds)
+
+**Key principles**:
+- Evidence-driven: every conclusion must trace to a citable source
+- Multi-source validation: key data requires ≥2 independent sources
+- Restrained judgment: mark speculation explicitly, avoid unsubstantiated claims
+- Structured presentation: complex information via tables, lists, hierarchies
+
+Run L1 quality check after completing each dimension (see enterprise_quality_checklist.md).
+
+Status per task: `[P2 task-{id} complete] {N} sources, {M} findings.`
+Status all: `[P2 complete] {N} tasks done, {M} total sources. Building registry.`
+
+### E3: Structured Analysis Frameworks
+
+Apply frameworks from [references/enterprise_analysis_frameworks.md](references/enterprise_analysis_frameworks.md) in order:
+1. **SWOT analysis** — each entry with evidence + source + impact assessment
+2. **Competitive barrier quantification** — 7 dimensions with weighted scoring → A+/A/B+/B/C+/C rating
+3. **Risk matrix** — 8 mandatory categories, probability × impact → Red/Yellow/Green
+4. **Comprehensive scorecard** — 6-dimension weighted total → X/10
+
+Run L2 quality check after analysis is complete.
+
+### E4: Quality Control
+
+Three-level checks from [references/enterprise_quality_checklist.md](references/enterprise_quality_checklist.md):
+- **L1 (Data)**: Source count, attribution, cross-validation, timeliness
+- **L2 (Analysis)**: SWOT completeness, risk coverage, barrier scoring, conclusion support
+- **L3 (Document)**: Structure compliance, format consistency, readability, appendices
+
+### E5: Draft Using Enterprise Template
+
+Use the 7-chapter enterprise report template from enterprise_quality_checklist.md:
+1. Company Overview
+2. Business & Product Structure
+3. Market & Competitive Position
+4. Financial & Operations Analysis
+5. Risks & Concerns
+6. Recent Developments
+7. Comprehensive Assessment & Conclusion
+
+Plus appendices: Data Source Index, Glossary, Disclaimer.
+
+### E3-E7: Enterprise Analysis, Drafting, and Review
+
+- **E3: Structured Analysis** — Apply frameworks from [references/enterprise_analysis_frameworks.md](references/enterprise_analysis_frameworks.md)
+- **E4: Quality Control** — Run L1/L2/L3 checks per [references/enterprise_quality_checklist.md](references/enterprise_quality_checklist.md)
+- **E5: Draft** — Use 7-chapter enterprise template
+- **E6-E7: Multi-Pass Drafting and Review** — Same as P4-P7 below
+
+---
+
+## P3: Citation Registry + Source Governance
+
+Lead agent reads all task notes and builds unified registry.
+
+### Registry Process
+
+1. Read every task file's `## Sources` section
+2. Merge all sources, deduplicate by URL
+3. Assign sequential [n] numbers by first appearance
+4. Tag: source_type, as_of date, authority score (1-10), task id
+5. **Apply quality gates:**
+   - Standard: ≥12 approved sources, ≥5 unique domains, ≥30% official
+   - Lightweight: ≥6 approved sources, ≥3 unique domains, ≥20% official
+   - Max single-source share: ≤25% (Standard), ≤30% (Lightweight)
+6. **Drop sources** below threshold and list them explicitly
+
+### Registry Output Format
 
-**File structure (recommended):**
 ```
-<output_dir>/research/<topic-name>/
-  deepresearch_pass1.md
-  deepresearch_pass2.md
-  deepresearch_pass3.md
+CITATION REGISTRY
+
+Approved:
+[1] Author/Org — Title | URL | Source-Type: official | Accessibility: public | Date: 2026-03-01 | Auth: 8 | task-a
+[2] ...
+
+Dropped:
+x Source | URL | Source-Type: community | Accessibility: privileged | Auth: 3 | Reason: PRIVILEGED SOURCE - NOT ALLOWED
+
+Stats: {approved}/{total}, {N} domains, official_share {xx}%
+Privileged sources rejected: {N}
 ```
 
-If deepresearch is unavailable, rely on user-provided sources only and state limitations explicitly.
+**Critical rule:** These [n] are FINAL. P5 may only cite from Approved list. Dropped sources never reappear.
 
-### Step 4: Source Triage and Evidence Table
+**Circular verification handling**: When researching the user's own company/assets, if you discover data in user's private accounts (e.g., user's domain registrar showing they own domains), you MUST:
+1. Reject it from the registry (user already knows this)
+2. Note it as "CIRCULAR - USER ALREADY KNOWS" in Dropped
+3. Search for equivalent PUBLIC sources (e.g., public WHOIS, news articles)
+4. Report from external investigator perspective only
 
-Normalize and score sources before drafting:
+**Exclusive source handling**: When user EXPLICITLY PROVIDES their paid subscriptions or private APIs for third-party research (e.g., "Use my Crunchbase Pro to research competitors"), you SHOULD:
+1. Accept it as "exclusive-user-provided" accessibility
+2. Use it as competitive advantage
+3. Cite it properly in registry
+4. If no public equivalent exists, mark as [unverified] or omit the claim
 
-- De-duplicate sources across passes
-- Score sources using [references/source_quality_rubric.md](references/source_quality_rubric.md)
-- Build an evidence table mapping claims to sources
+Report: `[P3 complete] {approved}/{total} sources. {N} domains. Official share: {xx}%. Privileged rejected: {N}.`
 
-Evidence table minimum columns:
+### Handling Information Black Box
 
-- Source ID
-- Title
-- Publisher
-- Date
-- URL or reference
-- Quality tier (A/B/C)
-- Notes
+When researching entities with no public footprint (like the "深度推理" example):
 
-### Step 5: Outline and Section Map
+**What an external researcher would find:**
+- WHOIS: Privacy protected → No owner info
+- Web search: No news, no press releases
+- Social media: No company pages
+- Business registries: No public API or requires local access
+- Result: **Complete information black box**
 
-Create an outline that enforces the format contract:
-
-- Use the template in [references/research_report_template.md](references/research_report_template.md)
-- Produce a section map with required elements per section
-- Confirm ordering and headings match the report spec
-
-### Step 6: Multi-Pass Full Drafting (Parallel Subagents)
-
-Avoid single-pass drafting; generate multiple complete reports, then merge.
-
-#### Preferred Strategy: Parallel Subagents (Complete Draft Each)
-
-Use the Task tool to spawn parallel subagents with isolated context. Each subagent must:
-
-- Load the report spec, outline, and evidence table
-- Draft the FULL report (all sections)
-- Enforce formatting rules and citation style
-
-**Implementation pattern:**
+**Correct response:**
 ```
-Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version1.md
-Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version2.md
-Task(subagent_type="general-purpose", prompt="Draft complete report ...", run_in_background=false) -> version3.md
+Findings: NO PUBLIC INFORMATION AVAILABLE
+
+Sources checked:
+- WHOIS (public): Privacy protected [failed]
+- Company registry (public): Access denied/No API [failed]
+- News media: No coverage [failed]
+- Corporate website: Placeholder only [minimal]
+
+Verdict: UNABLE TO VERIFY COMPANY EXISTENCE from external perspective
+Sources found: 0 (or minimal, e.g., only WHOIS showing domain exists)
+Confidence: N/A - Insufficient evidence
 ```
 
-**Write drafts to files, not conversation context:**
+**DO NOT:**
+- ❌ Use user's own credentials to "fill in the gaps"
+- ❌ Assume the company exists based on domain registration alone
+- ❌ Fill missing data with speculation
+- ❌ Claim to have "verified" information you accessed through privileged means
+
+**DO:**
+- ✅ Clearly state what an external researcher can/cannot verify
+- ✅ Document all failed search attempts
+- ✅ Mark claims as [unverified] or omit entirely
+- ✅ Downgrade mode to Lightweight or stop if insufficient public sources
+- ✅ Recommend direct contact for due diligence
+
+---
+
+## P4: Evidence-Mapped Outline
+
+Lead agent reads notes + registry to build outline.
+
+1. Identify cross-task patterns
+2. Design sections topic-first, not task-order-first
+3. Map each section to specific findings with source numbers
+4. Flag sections needing counter-review
+5. Mark recency-sensitive claims with AS_OF checks
+
+Outline format:
 ```
-<output_dir>/intermediate/<topic-name>/version1.md
-<output_dir>/intermediate/<topic-name>/version2.md
-<output_dir>/intermediate/<topic-name>/version3.md
+## N. {Section Title}
+Sources: [1][3][7] from tasks a, b
+Claims: {claim from task-a finding 3}, {claim from task-b finding 1}
+Counter-claim candidates: {alternative explanations}
+Recency checks: {source dates + AS_OF}
+Gaps: {limited official evidence}
 ```
 
-### Step 7: UNION Merge and Format Compliance
+---
 
-Merge using UNION, never remove content without evidence-based justification:
+## P5: Draft from Notes
 
-- Keep all unique findings from all versions
-- Consolidate duplicates while preserving the most detailed phrasing
-- Ensure every claim in the merged draft has a cited source
-- Enforce the exact section order, headings, and formatting
-- Re-run formatting rules from [references/formatting_rules.md](references/formatting_rules.md)
+Write section by section using [references/report_template_v6.md](references/report_template_v6.md).
 
-### Step 8: Evidence and Citation Verification
+**Rules:**
+- Every factual claim needs citation [n]
+- Numbers/percentages must have source
+- Add **confidence marker** per section: High/Medium/Low with rationale
+- Add **counter-claim sentence** when evidence conflicts
+- No new sources may be introduced
+- Use [unverified] for unsupported statements
 
-Verify traceability:
+**Anti-hallucination:**
+- Lead agent never invents URLs — only from subagent notes
+- Lead agent never fabricates data — mark [unverified] if number not in notes
 
-- Every numeric claim has at least one source
-- Every recommendation references supporting evidence
-- No orphan claims without citations
-- Dates and time ranges are consistent
-- Conflicts are explicitly called out with both sources
+Status: `[P5 in progress] {N}/{M} sections, ~{words} words.`
 
-Use [references/completeness_review_checklist.md](references/completeness_review_checklist.md).
+---
 
-### Step 9: Present Draft for Human Review and Iterate
+## P6: Counter-Review (Mandatory)
 
-Present the draft as a reviewable version:
+For each major conclusion, perform opposite-view checks:
 
-- Emphasize that format compliance and factual accuracy need human review
-- Accept edits to format, structure, and scope
-- If the user provides another AI output, cross-compare and UNION merge
+1. **Could the conclusion be wrong?**
+2. **Which high-impact claims depend on a single source?**
+3. **Which claims lack official/academic support?**
+4. **Are stale sources used for time-sensitive claims?**
+5. **Find ≥3 issues** (re-examine if 0 found)
+
+### Using Counter-Review Team (Recommended)
+
+For comprehensive parallel review, use the Counter-Review Team:
+
+```bash
+# 1. Prepare inputs
+counter-review-inputs/
+  ├── draft_report.md
+  ├── citation_registry.md
+  ├── task-notes/
+  └── p0_config.md
+
+# 2. Dispatch to 4 specialist agents in parallel
+SendMessage to: claim-validator
+SendMessage to: source-diversity-checker
+SendMessage to: recency-validator
+SendMessage to: contradiction-finder
+
+# 3. Wait for all specialists to complete
+
+# 4. Send to coordinator for synthesis
+SendMessage to: counter-review-coordinator
+  inputs: [4 specialist reports]
+
+# 5. Receive final P6 Counter-Review Report
+```
+
+See [references/counter_review_team_guide.md](references/counter_review_team_guide.md) for detailed usage.
+
+### Manual Counter-Review (Fallback)
+
+If Counter-Review Team is unavailable, perform manual checks:
+- Verify every high-confidence claim has ≥2 sources
+- Check official/academic backing for key claims
+- Verify AS_OF dates on time-sensitive claims
+- Document opposing interpretations
+
+### Output
+
+Include in final report:
+```
+## 核心争议 / Key Controversies
+- **争议 1:** [主张 A 与反向证据 B 对比] [n][m]
+- **争议 2:** ...
+```
+
+Report: `[P6 complete] {N} issues found: {critical} critical, {high} high, {medium} medium.`
+
+---
+
+## P7: Verify
+
+Cross-check before finalization:
+
+1. **Registry cross-check:** List every [n] in report vs approved registry
+2. **Spot-check 5+ claims:** Trace to task notes
+3. **Remove/fix non-traceable claims**
+4. **Validate no dropped source resurrected**
+5. **Check source concentration** for key claims
+
+Report: `[P7 complete] {N} spot-checks, {M} violations fixed.`
+
+---
 
 ## Output Requirements
 
@@ -188,6 +484,18 @@ Present the draft as a reviewable version:
 
 ## Reference Files
 
+### Core V6 Pipeline References
+
+| File | When to Load |
+| --- | --- |
+| [source_accessibility_policy.md](references/source_accessibility_policy.md) | **P0 (CRITICAL)**: Source classification rules - read first |
+| [subagent_prompt.md](references/subagent_prompt.md) | P2: Task dispatch to subagents |
+| [research_notes_format.md](references/research_notes_format.md) | P2: Subagent output format |
+| [report_template_v6.md](references/report_template_v6.md) | P5: Draft with confidence markers and counter-review |
+| [quality_gates.md](references/quality_gates.md) | All phases: Quality thresholds and anti-hallucination checks |
+
+### General Research References
+
 | File | When to Load |
 | --- | --- |
 | [research_report_template.md](references/research_report_template.md) | Build outline and draft structure |
@@ -196,6 +504,14 @@ Present the draft as a reviewable version:
 | [research_plan_checklist.md](references/research_plan_checklist.md) | Build research plan and query set |
 | [completeness_review_checklist.md](references/completeness_review_checklist.md) | Review for coverage, citations, and compliance |
 
+### Enterprise Research References (load when in Enterprise Research Mode)
+
+| File | When to Load |
+| --- | --- |
+| [enterprise_research_methodology.md](references/enterprise_research_methodology.md) | Six-dimension data collection workflow, source priority, cross-validation rules |
+| [enterprise_analysis_frameworks.md](references/enterprise_analysis_frameworks.md) | SWOT template, competitive barrier quantification, risk matrix, comprehensive scoring |
+| [enterprise_quality_checklist.md](references/enterprise_quality_checklist.md) | L1/L2/L3 quality checks, per-dimension checklists, 7-chapter report template |
+
 ## Anti-Patterns
 
 - Single-pass drafting without parallel complete passes
@@ -205,3 +521,10 @@ Present the draft as a reviewable version:
 - Mixing conflicting dates without calling out discrepancies
 - Copying external AI output without verification
 - Deleting intermediate drafts or raw research outputs
+- **Lead agent reading raw search results** — only read subagent notes
+- **Inventing URLs** — only use URLs from actual search results
+- **Resurrecting dropped sources** — dropped in P3 never reappear
+- **Missing AS_OF for time-sensitive claims** — always include source date
+- **Skipping counter-review** — mandatory P6 must find ≥3 issues
+- **CIRCULAR VERIFICATION** — never use user's private data to "discover" what they already know about themselves
+- **IGNORING EXCLUSIVE SOURCES** — when user provides Crunchbase Pro etc. for competitor research, USE IT
diff --git a/deep-research/references/V6_1_improvements.md b/deep-research/references/V6_1_improvements.md
new file mode 100644
index 0000000..e9758b6
--- /dev/null
+++ b/deep-research/references/V6_1_improvements.md
@@ -0,0 +1,112 @@
+# Deep Research Skill V6.1 Improvements
+
+**Date**: 2026-04-03  
+**Version**: 2.3.0 → 2.4.0  
+**Based on**: User feedback and "深度推理" case study
+
+---
+
+## Summary of Changes
+
+### 1. Source Accessibility Policy - Critical Correction
+
+**Problem Identified**:  
+Previously, we incorrectly banned all "privileged" sources. This was wrong because it prevented users from leveraging their competitive information advantages.
+
+**The Real Issue**:  
+The problem is not using user's private information—it's **circular verification**: using user's data to "discover" what they already know about themselves.
+
+**Example of the Error**:
+```
+User: "Research my company 深度推理"
+❌ WRONG: Access user's Spaceship → "You own 25 domains"
+   → This is circular: user already knows they own these domains
+
+✅ RIGHT: Check public WHOIS → "Privacy protected, ownership not visible"
+   → This is external research perspective
+```
+
+**Correct Classification**:
+
+| Accessibility | For Self-Research | For Third-Party Research |
+|--------------|-------------------|-------------------------|
+| `public` | ✅ Use | ✅ Use |
+| `semi-public` | ✅ Use | ✅ Use |
+| `exclusive-user-provided` | ⚠️ Careful* | ✅ **ENCOURAGED** |
+| `private-user-owned` | ❌ **FORBIDDEN** | N/A |
+
+\* When user provides exclusive sources for their own company, evaluate if it's circular
+
+### 2. Counter-Review Team V2
+
+**Created**: 5-agent parallel review team
+- 🔵 claim-validator: Claim validation
+- 🟢 source-diversity-checker: Source diversity analysis
+- 🟡 recency-validator: Recency/freshness checks
+- 🟣 contradiction-finder: Contradiction and bias detection
+- 🟠 counter-review-coordinator: Synthesis and reporting
+
+**Usage**:
+```bash
+# 1. Dispatch to 4 specialists in parallel
+SendMessage to: claim-validator
+SendMessage to: source-diversity-checker
+SendMessage to: recency-validator
+SendMessage to: contradiction-finder
+
+# 2. Send to coordinator for synthesis
+SendMessage to: counter-review-coordinator
+```
+
+### 3. Methodology Clarifications
+
+#### When Researching User's Own Company
+- **Approach**: External investigator perspective
+- **Use**: Public sources only
+- **Do NOT use**: User's private accounts (creates circular verification)
+- **Report**: "From public perspective: X, Y, Z gaps"
+
+#### When User Provides Exclusive Sources for Third-Party Research
+- **Approach**: Leverage competitive advantage
+- **Use**: User's paid subscriptions, private APIs, proprietary databases
+- **Cite**: Mark as `exclusive-user-provided`
+- **Report**: "Per user's exclusive source [Crunchbase Pro], competitor X raised $Y"
+
+### 4. Registry Format Update
+
+**Added fields**:
+- `Accessibility`: public / semi-public / exclusive-user-provided / private-user-owned
+- `Circular rejection tracking`: Note when sources are rejected for circular verification
+
+**Updated anti-patterns**:
+- ❌ **CIRCULAR VERIFICATION**: Never use user's private data to "discover" what they already know
+- ✅ **USE EXCLUSIVE SOURCES**: When user provides Crunchbase Pro etc. for competitor research, USE IT
+
+### 5. Documentation Updates
+
+**New/Updated Files**:
+- `source_accessibility_policy.md`: Complete rewrite explaining circular vs. competitive advantage distinction
+- `counter_review_team_guide.md`: Usage guide for the 5-agent team
+- `SKILL.md`: Updated Source Governance section with correct classification
+- `marketplace.json`: Updated description
+
+---
+
+## Key Principles Summary
+
+1. **Circular Verification is Bad**: Don't use user's data to tell them what they already know
+2. **Exclusive Information Advantage is Good**: Use user's paid tools to research competitors
+3. **External Perspective for Self-Research**: When researching user's own company, act like an external investigator
+4. **Leverage Everything for Third-Party**: When researching others, use every advantage user provides
+
+---
+
+## Version History
+
+| Version | Changes |
+|---------|---------|
+| 2.0.0 | Initial Enterprise Research Mode |
+| 2.1.0 | V6 features: source governance, AS_OF, counter-review |
+| 2.2.0 | Counter-Review Team |
+| 2.3.0 | Source accessibility (initial, incorrect ban on privileged) |
+| **2.4.0** | **Corrected: circular vs. exclusive advantage distinction** |
diff --git a/deep-research/references/counter_review_team_guide.md b/deep-research/references/counter_review_team_guide.md
new file mode 100644
index 0000000..3b85627
--- /dev/null
+++ b/deep-research/references/counter_review_team_guide.md
@@ -0,0 +1,181 @@
+# Counter-Review Team 使用指南
+
+Deep Research V6 P6 阶段的专用 Agent Team，并行执行多维度审查。
+
+## Team 架构
+
+```
+counter-review-coordinator (协调者)
+    ├── claim-validator (声明验证器)
+    ├── source-diversity-checker (来源多样性检查器)
+    ├── recency-validator (时效性验证器)
+    └── contradiction-finder (矛盾发现器)
+```
+
+## Agent 职责
+
+| Agent | 职责 | 输出 |
+|-------|------|------|
+| **claim-validator** | 验证声明准确性，识别无证据/弱证据声明 | Claim Validation Report |
+| **source-diversity-checker** | 检查单一来源依赖，source-type 分布 | Source Diversity Report |
+| **recency-validator** | 验证时敏声明的新鲜度，AS_OF 合规 | Recency Validation Report |
+| **contradiction-finder** | 发现内部矛盾，缺失的反向观点 | Contradiction and Bias Report |
+| **counter-review-coordinator** | 整合所有报告，生成最终 P6 报告 | P6 Counter-Review Report |
+
+## 使用流程
+
+### 1. 准备输入材料
+
+在 P5 (Draft) 完成后，收集以下材料：
+
+```
+inputs/
+├── draft_report.md          # P5 起草的报告
+├── citation_registry.md     # P3 的引用注册表
+├── task-notes/
+│   ├── task-a.md           # 子代理研究笔记
+│   ├── task-b.md
+│   └── ...
+└── p0_config.md            # P0 配置 (AS_OF 日期, Mode 等)
+```
+
+### 2. 并行分发任务
+
+向 4 个 specialist agent 同时发送任务：
+
+```bash
+# 向 claim-validator 发送
+SendMessage to: claim-validator
+  输入: draft_report.md + citation_registry.md + task-notes/
+  指令: 验证所有声明的证据支持
+
+# 向 source-diversity-checker 发送
+SendMessage to: source-diversity-checker
+  输入: draft_report.md + citation_registry.md
+  指令: 检查来源多样性和单一来源依赖
+
+# 向 recency-validator 发送
+SendMessage to: recency-validator
+  输入: draft_report.md + citation_registry.md + p0_config.md
+  指令: 验证时敏声明的新鲜度
+
+# 向 contradiction-finder 发送
+SendMessage to: contradiction-finder
+  输入: draft_report.md + task-notes/ + citation_registry.md
+  指令: 发现矛盾和缺失的反向观点
+```
+
+### 3. 协调汇总
+
+等待 4 个 specialist 完成后，发送给 coordinator：
+
+```bash
+SendMessage to: counter-review-coordinator
+  输入:
+    - Claim Validation Report
+    - Source Diversity Report
+    - Recency Validation Report
+    - Contradiction and Bias Report
+  指令: 整合所有报告，生成最终 P6 Counter-Review Report
+```
+
+### 4. 获取最终输出
+
+Coordinator 输出包含：
+- 问题汇总（必须 ≥3 个）
+- 关键争议部分（可直接复制到最终报告）
+- 强制修复清单
+- 质量门状态
+
+## 质量门要求
+
+| 检查项 | 标准模式 | 轻量模式 | 失败处理 |
+|--------|---------|---------|---------|
+| 发现问题数 | ≥3 | ≥3 | 重新审查 |
+| 关键声明单来源 | 0 | 0 | 补充来源或降级 |
+| 官方来源占比 | ≥30% | ≥20% | 补充官方来源 |
+| AS_OF 日期完整 | 100% | 100% | 补充日期 |
+| 核心争议文档化 | 必填 | 必填 | 补充争议部分 |
+
+## 输出示例
+
+### Coordinator 最终报告结构
+
+```markdown
+# P6 Counter-Review Report
+
+## Executive Summary
+- Total issues found: 7 (critical: 2, high: 3, medium: 2)
+- Must-fix before publish: 2
+- Recommended improvements: 5
+
+## Critical Issues (Block Publish)
+| # | Issue | Location | Source | Fix Required |
+|---|-------|----------|--------|--------------|
+| 1 | 市场份额声明无来源 | 3.2节 | 无 | 补充来源或删除 |
+| 2 | 单一社区来源支持收入数据 | 4.1节 | [12] community | 找官方来源替代 |
+
+## 核心争议 / Key Controversies
+
+- **争议 1:** 公司声称增长 50% vs 分析师报告增长 30%
+  - 证据强度: official(公司财报) vs academic(第三方研究)
+  - 建议: 并列呈现两种数据，说明差异原因
+
+## Mandatory Fixes Checklist
+- [ ] 补充 3.2 节市场份额来源
+- [ ] 替换 4.1 节收入数据来源
+- [ ] 添加 AS_OF: 2026-04-03 到所有时敏声明
+
+## Quality Gates Status
+| Gate | Status | Notes |
+|------|--------|-------|
+| P6 ≥3 issues found | ✅ | 发现 7 个问题 |
+| No critical claim single-sourced | ❌ | 2 个问题待修复 |
+| AS_OF dates present | ❌ | 3 处缺失 |
+| Counter-claims documented | ✅ | 已添加 |
+```
+
+## 集成到 SKILL.md 工作流
+
+在 SKILL.md 的 P6 阶段，添加以下指令：
+
+```markdown
+## P6: Counter-Review (Mandatory)
+
+**使用 Counter-Review Team 执行并行审查：**
+
+1. **准备材料**: draft_report.md, citation_registry.md, task-notes/, p0_config.md
+2. **并行分发**: 同时发送给 4 个 specialist agent
+3. **等待完成**: 收集 4 份 specialist 报告
+4. **协调汇总**: 发送给 coordinator 生成最终 P6 报告
+5. **强制执行**: 所有 Critical 问题必须在 P7 前修复
+6. **输出**: 将"核心争议"部分复制到最终报告
+
+**Report**: `[P6 complete] {N} issues found: {critical} critical, {high} high, {medium} medium.`
+```
+
+## 团队管理
+
+### 查看团队状态
+```bash
+cat ~/.claude/teams/counter-review-team/config.json
+```
+
+### 向 Agent 发送消息
+```bash
+SendMessage to: claim-validator
+message: 开始审查任务，输入文件在 ./review-inputs/
+```
+
+### 关闭团队
+```bash
+SendMessage to: "*"
+message: {"type": "shutdown_request", "reason": "任务完成"}
+```
+
+## 注意事项
+
+1. **必须发现 ≥3 个问题** - 如果 coordinator 报告 <3 个问题，需要重新审查
+2. **Critical 问题必须修复** - 才能进入 P7
+3. **保留所有审查记录** - 作为研究方法论的一部分
+4. **中文输入中文输出** - 所有 agent 支持中英文双语
diff --git a/deep-research/references/enterprise_analysis_frameworks.md b/deep-research/references/enterprise_analysis_frameworks.md
new file mode 100644
index 0000000..209c03a
--- /dev/null
+++ b/deep-research/references/enterprise_analysis_frameworks.md
@@ -0,0 +1,135 @@
+# Enterprise Analysis Frameworks
+
+Apply these frameworks after completing the six-dimension data collection. Execute in order: SWOT → Competitive Barriers → Risk Matrix → Comprehensive Scoring.
+
+## SWOT Analysis Template
+
+Each SWOT entry MUST include evidence and source attribution.
+
+```
+|              | Positive Factors                  | Negative Factors                  |
+|--------------|-----------------------------------|-----------------------------------|
+| **Internal** | **S (Strengths)**                 | **W (Weaknesses)**                |
+|              | 1. {description}                  | 1. {description}                  |
+|              |    • Evidence: {data/fact}        |    • Evidence: {data/fact}        |
+|              |    • Source: {citation}           |    • Source: {citation}           |
+|              |    • Impact: {assessment}         |    • Impact: {assessment}         |
+|              |                                   |                                   |
+| **External** | **O (Opportunities)**             | **T (Threats)**                   |
+|              | 1. {description}                  | 1. {description}                  |
+|              |    • Evidence: {trend/policy}     |    • Evidence: {pressure/risk}    |
+|              |    • Source: {citation}           |    • Source: {citation}           |
+|              |    • Probability: {assessment}    |    • Probability: {assessment}    |
+|              |    • Impact: {assessment}         |    • Impact: {assessment}         |
+```
+
+**Requirements**:
+- Each quadrant: 3-5 entries minimum
+- Every entry must have evidence with source
+- S/W must be data-backed (not opinions)
+- O/T must include probability and impact estimates
+
+**Strategic Implications Matrix** (generate after SWOT):
+- **SO Strategy** (leverage strengths to capture opportunities): 1-2 specific recommendations
+- **WO Strategy** (overcome weaknesses to seize opportunities): 1-2 specific recommendations
+- **ST Strategy** (use strengths to counter threats): 1-2 specific recommendations
+- **WT Strategy** (mitigate weaknesses to avoid threats): 1-2 specific recommendations
+
+## Competitive Barrier Quantification Framework
+
+7 barrier dimensions with weighted scoring:
+
+| Dimension | Weight | Strong | Moderate | Weak |
+|-----------|--------|--------|----------|------|
+| **Network Effects** | 20% | 4.5 — Clear network effects (social platforms, marketplaces) | 3.0 — Exists but replaceable | 1.5 — Minimal network effects |
+| **Scale Economies** | 15% | 4.0 — Unit cost drops 30%+ with scale | 2.5 — Cost drops 10-30% | 1.0 — Cost drops <10% |
+| **Brand Value** | 15% | 4.0 — Category leader, high pricing power | 2.5 — Known brand, competitive | 1.0 — Commodity brand, price-sensitive |
+| **Technology/Patents** | 15% | 4.0 — Core patents, hard to circumvent | 2.5 — Some patent protection | 1.0 — Peripheral patents only |
+| **Switching Costs** | 15% | 4.0 — High lock-in (data, ecosystem) | 2.5 — Moderate switching friction | 1.0 — Low switching cost |
+| **Regulatory Licenses** | 10% | 3.5 — Heavy regulation, hard to obtain | 2.0 — Standard regulatory requirements | 0.5 — Light regulation |
+| **Data Assets** | 10% | 3.5 — Massive proprietary high-quality data | 2.0 — Some data accumulation | 0.5 — Limited or public data |
+
+**Scoring**: Total = Σ(dimension score × weight)
+
+**Rating Scale**:
+| Score | Rating | Interpretation |
+|-------|--------|---------------|
+| ≥3.5 | A+ | Exceptional moat |
+| ≥2.8 | A | Strong moat |
+| ≥2.0 | B+ | Good moat |
+| ≥1.5 | B | Moderate moat |
+| ≥1.0 | C+ | Limited moat |
+| <1.0 | C | Weak moat |
+
+**Output format**: Present a scorecard table with each dimension's strength rating, raw score, justification (with evidence), and the weighted total with final rating.
+
+## Risk Matrix Framework
+
+Assess 8 mandatory risk categories:
+
+### Risk Assessment Scales
+
+**Probability**:
+| Level | Range | Score |
+|-------|-------|-------|
+| High | >70% | 0.7-1.0 |
+| Medium | 30-70% | 0.3-0.7 |
+| Low | <30% | 0.0-0.3 |
+
+**Impact**:
+| Level | Description | Score |
+|-------|-------------|-------|
+| High | >30% revenue impact | 3 |
+| Medium | 10-30% revenue impact | 2 |
+| Low | <10% revenue impact | 1 |
+
+**Risk Level**: Risk Value = Probability Score × Impact Score
+| Color | Level | Threshold |
+|-------|-------|-----------|
+| Red | High risk | ≥2.5 |
+| Yellow | Medium risk | 1.0 – 2.5 |
+| Green | Low risk | <1.0 |
+
+### 8 Mandatory Risk Categories
+
+| # | Category | Typical Triggers |
+|---|----------|-----------------|
+| 1 | Market risk | Industry slowdown, demand shifts |
+| 2 | Competitive risk | New entrants, incumbents pivoting |
+| 3 | Technology risk | Tech obsolescence, disruption |
+| 4 | Regulatory risk | Policy tightening, compliance cost |
+| 5 | Financial risk | Cash flow stress, debt levels |
+| 6 | Operational risk | Key talent loss, supply chain |
+| 7 | Talent risk | Brain drain, recruiting difficulty |
+| 8 | Geopolitical risk | Trade friction, data localization |
+
+### Risk Table Format
+
+| Category | Specific Risk | Probability | Impact | Risk Value | Level | Evidence/Triggers | Current Mitigations | Recommended Actions |
+|----------|--------------|-------------|--------|------------|-------|-------------------|--------------------|--------------------|
+
+**Requirements**:
+- All 8 categories must be assessed (no skipping)
+- Each risk entry must cite specific evidence or triggers
+- Provide current mitigations AND recommended actions
+- High risks: require immediate action plans
+- Medium risks: require monitoring plans
+- Low risks: require periodic review schedule
+
+## Comprehensive Scoring (Final Section)
+
+After completing SWOT, barriers, and risk matrix, generate a comprehensive scorecard:
+
+```
+| Dimension | Score | Weight | Weighted | Key Evidence |
+|-----------|-------|--------|----------|-------------|
+| Business Quality | X/10 | 25% | | |
+| Competitive Position | X/10 | 20% | | |
+| Financial Health | X/10 | 20% | | |
+| Growth Potential | X/10 | 15% | | |
+| Risk Profile | X/10 | 10% | | |
+| Management Quality | X/10 | 10% | | |
+| **Total** | | 100% | **X/10** | |
+```
+
+Every score must reference specific evidence from the six-dimension data collection.
diff --git a/deep-research/references/enterprise_quality_checklist.md b/deep-research/references/enterprise_quality_checklist.md
new file mode 100644
index 0000000..b09d925
--- /dev/null
+++ b/deep-research/references/enterprise_quality_checklist.md
@@ -0,0 +1,160 @@
+# Enterprise Research Quality Checklist
+
+Three-level quality control executed at each stage transition.
+
+## L1: Data Collection Quality (after each dimension)
+
+### Per-Dimension Checks
+
+| Check Item | Standard | Method | Pass Condition |
+|-----------|----------|--------|---------------|
+| Source count | Key data points ≥2 sources | Count source annotations | ≥90% compliance |
+| Source attribution | All data has source marked | Check citations in draft | ≥95% completeness |
+| Cross-validation pass rate | Data deviation ≤10% | Compare multi-source data | ≥95% validation pass |
+| Timeliness | Financial: ≤2 years; News: ≤6 months | Check timestamps | 100% compliance |
+
+**Result handling**: All pass → proceed. Partial fail → supplement sources. Critical fail → re-collect dimension.
+
+### Dimension-Specific Checklists
+
+**D1 Company Fundamentals** (target: 11/11):
+- [ ] Legal entity boundaries clarified
+- [ ] Founding date with month/year
+- [ ] Headquarters city identified
+- [ ] Founder/CEO confirmed (≥2 sources)
+- [ ] Employee count with year
+- [ ] Listing status (exchange, ticker)
+- [ ] Latest valuation/market cap with date
+- [ ] Core business one-liner
+- [ ] Funding history ≥3 rounds
+- [ ] ≥5 milestone events in timeline
+- [ ] Ownership structure: controller identified
+
+**D2 Business & Products** (target: 7/7):
+- [ ] ≥3 business segments identified
+- [ ] Revenue share per segment
+- [ ] ≥3 core products analyzed
+- [ ] User metrics (DAU/MAU) with numbers
+- [ ] Monetization model per product
+- [ ] Revenue breakdown (segment/geography/customer)
+- [ ] Growth/decline trend per segment
+
+**D3 Competitive Position** (target: 7/7):
+- [ ] Industry clearly defined
+- [ ] Market size quantified
+- [ ] Company rank established
+- [ ] Market share with number
+- [ ] ≥3 competitors identified
+- [ ] Multi-dimension comparison table complete
+- [ ] ≥5 barrier dimensions assessed with scores
+
+**D4 Financial & Operations** (target: 9/9):
+- [ ] Revenue: 3-year data
+- [ ] Net income: 3-year data
+- [ ] Gross margin: 3-year data
+- [ ] Net margin: 3-year data
+- [ ] Operating cash flow: 3-year data
+- [ ] R&D expense: 3-year data
+- [ ] Key financial data cross-validated (≥2 sources)
+- [ ] Metric definitions consistent across years
+- [ ] ≥3 efficiency metrics (ROE/ROA/etc.)
+
+**D5 Recent Developments** (target: 5/5):
+- [ ] ≥5 recent events (within 6 months)
+- [ ] Events span ≥3 event types
+- [ ] Each event has impact assessment
+- [ ] ≥2 strategic direction signals identified
+- [ ] Most recent event within 1 month
+
+**D6 Internal/Proprietary** (target: 2/2):
+- [ ] Internal knowledge base queried (or limitation noted)
+- [ ] Internal document search executed (or limitation noted)
+
+## L2: Analysis Quality (after analysis frameworks applied)
+
+| Check Item | Standard | Method | Pass Condition |
+|-----------|----------|--------|---------------|
+| SWOT completeness | Each quadrant ≥3 entries | Entry count | Full coverage |
+| SWOT evidence | Every entry has data backing | Check "Evidence" fields | 100% evidenced |
+| Risk matrix coverage | All 8 categories assessed | Category checklist | 100% covered |
+| Barrier quantification | All 7 dimensions scored | Check scorecard completeness | 100% scored |
+| Conclusion support | All conclusions trace to evidence | Trace each conclusion | 100% supported |
+
+**Result handling**: All pass → proceed to writing. Partial fail → supplement analysis evidence. Critical fail → re-execute analysis framework.
+
+## L3: Document Quality (after report drafted)
+
+| Check Item | Standard | Method | Pass Condition |
+|-----------|----------|--------|---------------|
+| Structure compliance | Follows 7-chapter template | Compare against template | ≥95% compliance |
+| Table format consistency | All tables uniformly formatted | Visual inspection | 100% uniform |
+| Readability | Paragraphs ≤450 chars; ≥3 parallel items use lists | Paragraph length check | ≥95% compliance |
+| Data annotation | All data has source + year | Citation audit | 100% complete |
+| Appendix completeness | Includes source index + glossary | Content check | 100% complete |
+
+**Result handling**: All pass → deliver. Partial fail → format optimization. Critical fail → regenerate document.
+
+## Enterprise Report Structure (7 Chapters)
+
+```
+# {Company Name} Research Report
+
+> Executive Summary: {1-2 sentence core conclusion}
+
+---
+
+## 1. Company Overview
+### 1.1 Basic Information (table)
+### 1.2 Development Timeline
+### 1.3 Funding History (table)
+### 1.4 Ownership Structure & Control
+### 1.5 Core Management Team (table)
+
+## 2. Business & Product Structure
+### 2.1 Business Landscape Overview
+### 2.2 Core Product Matrix (table)
+### 2.3 Revenue Structure Analysis
+### 2.4 Business Development Trends
+
+## 3. Market & Competitive Position
+### 3.1 Industry Position Analysis
+### 3.2 Competitive Comparison (table)
+### 3.3 Competitive Barrier Assessment (scorecard)
+
+## 4. Financial & Operations Analysis
+### 4.1 Key Financial Metrics (3-year comparison table)
+### 4.2 Operating Efficiency Assessment
+### 4.3 Financial Health Summary
+
+## 5. Risks & Concerns
+### 5.1 Risk Matrix Analysis (8-category table)
+### 5.2 Key Risk Deep-Dives
+### 5.3 Risk Mitigation Recommendations
+
+## 6. Recent Developments
+### 6.1 Major Recent Events (table)
+### 6.2 Strategic Signal Interpretation
+
+## 7. Comprehensive Assessment & Conclusion
+### 7.1 SWOT Summary
+### 7.2 Comprehensive Scorecard
+### 7.3 Core Conclusions & Outlook
+
+---
+
+## Appendices
+### A. Data Source Index
+### B. Glossary
+### C. Disclaimer
+```
+
+## Quality Control Four Dimensions
+
+Apply throughout all stages:
+
+| Dimension | Focus | Key Checks |
+|-----------|-------|------------|
+| **Accuracy** | Data correctness | Source attribution, fact verification, cross-validation, error tolerance |
+| **Completeness** | Information coverage | Dimension coverage, key element presence, conclusion support, risk coverage |
+| **Timeliness** | Data currency | Data freshness, trend capture, signal detection, dynamic updates |
+| **Consistency** | Uniform standards | Metric definitions aligned, format unified, style consistent, terminology standardized |
diff --git a/deep-research/references/enterprise_research_methodology.md b/deep-research/references/enterprise_research_methodology.md
new file mode 100644
index 0000000..be8680e
--- /dev/null
+++ b/deep-research/references/enterprise_research_methodology.md
@@ -0,0 +1,164 @@
+# Enterprise Research Methodology
+
+## Six-Dimension Data Collection
+
+Enterprise research requires parallel collection across six dimensions. Execute all six in order, writing findings to a structured draft after each dimension.
+
+### Dimension 1: Company Fundamentals
+
+```
+Step 1.1: Confirm legal entity
+├── Clarify parent/subsidiary/affiliate boundaries
+├── Query: "{company} legal entity corporate structure"
+├── Output: Entity scope statement
+└── Verify: Map operating entities to brands
+
+Step 1.2: Basic information
+├── Query round 1: "{company} founding date headquarters founder"
+├── Query round 2: "{company} company overview profile"
+├── Query round 3: "{company} CEO management team executives"
+├── Source priority: Official site > Regulatory filings > Authoritative media
+└── Output: Basic info table (name, founded, HQ, CEO, employees, listing status)
+
+Step 1.3: Funding history
+├── Query: "{company} funding rounds valuation IPO"
+├── Key fields: round, amount, investors, post-money valuation, date
+└── Output: Funding timeline table
+
+Step 1.4: Ownership structure
+├── Query: "{company} ownership structure beneficial owner"
+├── Key fields: controller identity, economic interest %, voting rights %, control mechanisms (dual-class etc.)
+└── Output: Ownership summary
+```
+
+### Dimension 2: Business & Products
+
+```
+Step 2.1: Business landscape scan
+├── Query round 1: "{company} product lines business segments"
+├── Query round 2: "{company} revenue breakdown by segment"
+├── Query round 3: "{company} business model monetization"
+├── Key fields: segment name, positioning, revenue share, YoY growth, synergies
+└── Output: Business landscape table
+
+Step 2.2: Core product analysis
+├── Query: "{company} core products DAU MAU user base"
+├── Per product: positioning, target users, scale (DAU/MAU), market share, monetization, competitive advantage, trends
+└── Output: Product matrix table
+
+Step 2.3: Revenue structure analysis
+├── Source: Financial reports (deep extraction)
+├── Breakdown by: segment, geography, customer type, pricing model
+└── Output: Revenue structure summary
+```
+
+### Dimension 3: Competitive Position
+
+```
+Step 3.1: Industry position
+├── Query: "{company} industry ranking market share"
+├── Key fields: industry definition, TAM/SAM/SOM, company rank, share, concentration (CR3/CR5)
+└── Output: Industry position analysis
+
+Step 3.2: Competitor identification & comparison
+├── Query round 1: "{company} competitors"
+├── Query round 2: "{company} vs {competitor A} comparison"
+├── Query round 3: "{company} vs {competitor B} differences"
+├── Comparison dimensions: founding, revenue, market share, core products, user scale, valuation/market cap, strengths, weaknesses
+├── Minimum: ≥3 competitors identified
+└── Output: Competitive comparison table
+
+Step 3.3: Competitive barriers assessment
+├── Use quantified barrier framework (see enterprise_analysis_frameworks.md)
+├── 7 dimensions: network effects, scale economies, brand, technology/patents, switching costs, regulatory licenses, data assets
+└── Output: Barrier scorecard with rating
+```
+
+### Dimension 4: Financial & Operations
+
+```
+Step 4.1: Financial data collection
+├── Query: "{company} financial results {year} revenue profit"
+├── Core metrics (3-year minimum): revenue, revenue growth, net income, gross margin, net margin, operating cash flow, R&D expense, R&D ratio
+└── Output: Financial metrics table (3+ years)
+
+Step 4.2: Operating efficiency analysis
+├── Query: "{company} ROE ROA efficiency per-employee"
+├── Efficiency metrics: ROE, ROA, revenue per employee, accounts receivable days, debt-to-equity
+└── Output: Operating efficiency table
+
+Step 4.3: Cross-validation
+├── Require ≥2 independent sources for key financial data
+├── Sources: company filings (primary), regulatory filings, authoritative financial data providers
+├── Deviation rules:
+│   ├── ≤10%: Pass
+│   ├── 10-20%: Flag with explanation
+│   └── >20%: Require third-party verification
+└── Output: Validation record
+```
+
+### Dimension 5: Recent Developments
+
+```
+Step 5.1: Recent news scan (past 6 months)
+├── Query round 1: "{company} latest news {current year}"
+├── Query round 2: "{company} strategy pivot latest developments"
+├── Query round 3: "{company} executive changes leadership"
+├── Query round 4: "{company} partnership acquisition latest"
+├── Query round 5: "{company} product launch new release"
+├── Event types: product launches, fundraising/capital, strategy shifts, executive changes, M&A/partnerships, regulatory/compliance
+├── Minimum: ≥5 events identified
+└── Output: Major events table
+
+Step 5.2: Strategic signal interpretation
+├── Dimensions: expansion signals, contraction signals, transformation signals, risk signals
+└── Output: Strategic signal analysis
+```
+
+### Dimension 6: Internal/Proprietary Sources
+
+```
+Step 6.1: Internal knowledge base query (if available)
+├── Query 1: "our company's relationship with {target company}"
+├── Query 2: "internal assessment of {target company}"
+├── Query 3: "{target company} competitive analysis"
+├── Query 4: "{target company} industry research"
+└── Output: Internal perspective supplementary info
+
+Step 6.2: If no internal sources available
+├── State explicitly: "No internal/proprietary sources available for this research"
+├── Compensate with additional public source depth
+└── Note limitation in final report
+```
+
+## Data Source Priority Matrix
+
+| Priority | Source Type | Reliability | Timeliness | Use Case |
+|----------|-----------|-------------|------------|----------|
+| **P0** | Official filings / annual reports | 10/10 | High | Core financial data |
+| **P0** | Company website / announcements | 10/10 | High | Basic info, updates |
+| **P1** | Regulatory filings | 9/10 | High | Ownership, licenses |
+| **P1** | Authoritative industry reports | 9/10 | Medium | Market position, trends |
+| **P2** | Mainstream financial media | 8/10 | High | News, analysis |
+| **P2** | Professional research institutions | 8/10 | Medium | Deep analysis, forecasts |
+| **P3** | Social media / forums | 5/10 | High | Sentiment signals only |
+
+**Rule**: P0 + P1 are primary sources. P2 for validation. P3 for reference only, never as sole source.
+
+## Cross-Validation Rules
+
+| Data Type | Min Sources | Max Deviation | Primary Source | Fallback Sources |
+|-----------|------------|---------------|----------------|-----------------|
+| Financial data | 2 | 10% | Official financial reports | Regulatory filings, analyst reports |
+| Market share | 2 | 15% | Industry reports | Company disclosures, third-party analysis |
+| Management info | 1 | N/A | Company official sources | Regulatory filings, reputable media |
+| User metrics | 2 | 20% | Company disclosures | Third-party analytics, industry reports |
+
+## Search Strategy Best Practices
+
+1. **Multi-angle queries**: 3 different query angles per topic
+2. **Time filtering**: Prioritize data within last 12 months for operational data, last 3 years for financial trends
+3. **Site restriction**: Use `site:` for authoritative domains when possible
+4. **Language diversity**: Query in both English and the company's primary language
+5. **Exclude noise**: Use `-` to exclude irrelevant results
+6. **Progressive depth**: Start broad, then narrow based on gaps identified
diff --git a/deep-research/references/quality_gates.md b/deep-research/references/quality_gates.md
new file mode 100644
index 0000000..b92488a
--- /dev/null
+++ b/deep-research/references/quality_gates.md
@@ -0,0 +1,77 @@
+# Quality Gates V6
+
+## Gate 1: Task Notes Quality (after P2)
+
+| Check | Standard | Lightweight | Fix |
+|-------|----------|-------------|-----|
+| All tasks completed | 100% | 100% | Re-dispatch failed tasks |
+| Sources per task | >= 2 | >= 1 | Run additional searches |
+| Findings per task | >= 3 | >= 2 | Deepen search or fetch more |
+| DEEP tasks have Deep Read Notes | 100% | 100% | Fetch and read top source |
+| All source URLs from actual search | 100% | 100% | Remove any invented URL |
+
+## Gate 2: Citation Registry (after P3)
+
+| Check | Standard | Lightweight | Fix |
+|-------|----------|-------------|-----|
+| Total approved sources | >= 12 | >= 6 | Flag thin areas for P6 |
+| Unique domains | >= 5 | >= 3 | Diversify in re-search |
+| Max single-source share | <= 25% | <= 30% | Find alternatives |
+| Official source coverage | >= 30% for standard | >= 20% for lightweight | Add official sources |
+| Source-type balance | official + academic + secondary at least 2 types | same | Fill missing type
+| Dropped sources listed | All | All | Must be explicit |
+| No duplicate URLs | 0 duplicates | 0 | Merge during P3 |
+
+## Gate 3: Draft Quality (after P5)
+
+| Check | Standard | Lightweight | Fix |
+|-------|----------|-------------|-----|
+| Every [n] in registry | 100% | 100% | Remove or fix |
+| No dropped source cited | 0 violations | 0 | Remove immediately |
+| Citation density | >= 1 per 200 words | >= 1 per 300 words | Add citations |
+| Every section has confidence marker | 100% | 100% | Add missing |
+| High-confidence claims backed by official source | 100% | 100% | Downgrade or re-source |
+| Counter-claim recorded for major sections | 100% | 70% | Add opposing interpretation |
+| Total word count | 3000-8000 | 2000-4000 | Adjust scope |
+
+## Gate 4: Notes Traceability (after P6)
+
+| Check | Threshold | Fix |
+|-------|-----------|-----|
+| Every specific claim traceable to a task note finding | 100% | 100% | Remove or mark [unverified] |
+| Every statistic/number appears in some task note | 100% | 100% | Remove or verify |
+| No claim contradicts a task note | 0 contradictions | 0 | Rewrite to match notes |
+| Claims with recency sensitivity include source date and AS_OF | 100% | 100% | Add date metadata |
+| P6 found >= 3 issues | Must | Re-examine harder if 0 found |
+
+## Gate 5: Verification (after P7)
+
+| Check | Threshold | Fix |
+|-------|-----------|-----|
+| Registry cross-check: all [n] valid | 100% | 100% | Remove invalid [n] |
+| Spot-check: 5+ claims traced to notes | >= 4/5 pass | Fix failing claims |
+| No dropped source resurrected | 0 | Remove immediately |
+| Source concentration check for key claims | None > 25% | diversify |
+
+## Anti-Hallucination Patterns
+
+| Pattern | Where to detect | Fix |
+|---------|----------------|-----|
+| URL not from any subagent search | P7 registry check | Remove citation |
+| Claim not in any task note | P6 traceability check | Remove or mark [unverified] |
+| Number more precise than source | P6 ("73.2%" when note says "about 70%") | Use note's precision |
+| Source authority inflated | P3 registry building | Re-score from notes |
+| Source type mismatched to claim | P3 + P6 | Reclassify or replace source |
+| "Studies show..." without naming study | P6 | Name specific source or remove |
+| Dropped source reappears | P7 cross-check | Remove immediately |
+| Subagent invented a URL | Gate 1 (lead verifies subagent notes) | Remove from notes before P3 |
+
+## Chinese-Specific Patterns
+
+| Pattern | Fix |
+|---------|-----|
+| Fake CNKI URL format | Remove, note gap |
+| "某专家表示" without name/institution | Name or remove |
+| "据统计" without data source | Add source or qualitative language |
+| Fabricated institution report | Verify existence or remove |
+| 旧模型信息未标注 AS_OF | 降级置信度并重搜 |
diff --git a/deep-research/references/report_template_v6.md b/deep-research/references/report_template_v6.md
new file mode 100644
index 0000000..ab4c3f9
--- /dev/null
+++ b/deep-research/references/report_template_v6.md
@@ -0,0 +1,82 @@
+# {{TITLE}}
+
+> 研究日期: {{DATE}} | 来源数量: {{SOURCE_COUNT}} | 字数: ~{{WORD_COUNT}} | 模式: {{MODE}} | AS_OF: {{AS_OF}} | 官方源占比: {{OFFICIAL_SHARE}}
+
+## 摘要 / Executive Summary
+
+{{200-400 words summarizing key findings, methodology, conclusions, and risks.}}
+
+---
+
+## 目录
+
+{{Auto-generate from actual section headers below.}}
+
+---
+
+{{BODY SECTIONS —  Adapt to topic type and include opposing interpretation per section.}}
+
+For each section:
+
+## N. [Topic-Specific Section Title]
+
+{{Section content with inline citations [1][2].
+Standard mode: 500-1000 words per section.
+Lightweight mode: 300-600 words per section.
+
+Rules:
+- 每个事实性论点都需要引用 [n]
+- 数字/百分比必须有来源
+- 出现不同证据时要成对给出支持与反驳
+}}
+
+**置信度:** High/Medium/Low
+
+**依据:** {{Why this confidence level — source agreement, evidence quality, data availability}}
+
+**反方解释:** {{One explicit opposing interpretation with supporting citations if any, or [unverified] if insufficient.}}
+
+---
+
+{{COUNTER-REVIEW SUMMARY}}
+
+- **核心争议 1:** [主张 A 与反向证据 B 对比] [n][m]
+- **核心争议 2:** ...
+
+## 关键发现 / Key Findings
+
+{{3-5 findings in Standard mode, 2-3 in Lightweight. Each finding should:}}
+- 具体结论
+- 对应引文
+- 信心说明
+
+Example:
+- **发现 1:** [Most important discovery] [3][7]
+- **发现 2:** [Second most important] [1][4]
+
+---
+
+## 局限性与未来方向 / Limitations & Future Directions
+
+### 本研究局限
+{{Be explicit:
+- What topics/angles couldn't be covered and why
+- Methodological limits (web-accessible sources, paywall, language, timing)
+- Source coverage gaps and counter-claim evidence gaps
+}}
+
+### 未来方向
+{{Concrete suggestions for follow-up research with priority and responsible evidence type.}}
+
+---
+
+## 参考文献 / References
+
+[1] Author/Org. "Title". Source-Type: official/academic/secondary-industry/journalism/community/other. As Of: YYYY-MM-DD. URL.
+[2] Author/Org. "Title". Source-Type: ... As Of: YYYY-MM-DD. URL.
+
+Rules:
+- Every [n] in body MUST have matching entry here
+- Every entry here MUST be cited at least once
+- Source-Type and As Of fields are mandatory
+- All URLs MUST come from actual search results (P2 source pool)
diff --git a/deep-research/references/research_notes_format.md b/deep-research/references/research_notes_format.md
new file mode 100644
index 0000000..49d1196
--- /dev/null
+++ b/deep-research/references/research_notes_format.md
@@ -0,0 +1,147 @@
+# Research Notes Format Specification
+
+The research notes are the ONLY communication channel between subagents and
+the lead agent. Every fact in the final report must be traceable to a line in
+these notes. No exceptions.
+
+## File Structure
+
+```
+workspace/research-notes/
+  task-a.md       Subagent A writes (history expert)
+  task-b.md       Subagent B writes (transport historian)
+  task-c.md       Subagent C writes (telecom analyst)
+  task-d.md       Subagent D writes (comparative analyst)
+  registry.md     Lead agent builds from task-*.md (P3)
+```
+
+## Per-Task Notes Format
+
+Each `task-{id}.md` file follows this exact structure:
+
+```markdown
+---
+task_id: a
+role: Economic Historian
+status: complete
+sources_found: 4
+---
+
+## Sources
+
+[1] Before AI skeptics, Luddites raged against the machine | https://www.nationalgeographic.com/... | Source-Type: secondary-industry | As Of: 2025-08 | Authority: 8/10
+[2] Rage against the machine | https://www.cam.ac.uk/research/news/rage-against-the-machine | Source-Type: academic | As Of: 2024-04 | Authority: 8/10
+[3] Luddite | https://en.wikipedia.org/wiki/Luddite | Source-Type: community | As Of: 2026-03 | Authority: 7/10
+[4] Learning from the Luddites | https://forum.effectivealtruism.org/... | Source-Type: community | As Of: 2025-10 | Authority: 6/10
+
+## Findings
+
+- Luddite movement began March 11, 1811 in Arnold, Nottinghamshire. [3]
+- Luddites were skilled craftspeople, not anti-technology extremists. [1][2]
+- In the 100M-person textile industry, Luddites never exceeded a few thousand. [2]
+- Government crushed movement: 12 executed at York Assizes, Jan 1813. [3]
+- Movement collapsed by 1817 under military repression. [1]
+- Full textile mechanization transition took 50-90 years (1760s-1850s). [4]
+- Textile workers' real wages dropped ~70% during transition. [4]
+- Key lesson for AI: Luddites organized AFTER displacement began, losing leverage. [4]
+
+## Deep Read Notes
+
+### Source [1]: National Geographic — Luddites and AI
+Key data: destroyed up to 10,000 pounds of frames in first year alone.
+  Movement spread from Nottinghamshire to Yorkshire and Lancashire in 1812.
+  Children made up 2/3 of workforce at Cromford factory.
+Key insight: Luddites attacked the SYSTEM of exploitation, not machines per se.
+  They protested manufacturers circumventing standard labor practices.
+Useful for: framing section on historical displacement, correcting "anti-tech" myth
+
+### Source [2]: Cambridge University
+Key data: Luddites were "elite craftspeople" not working class broadly.
+  Yorkshire croppers had 7-year apprenticeships. Movement was localized, never exceeded a few thousand.
+Key insight: The movement was smaller and more elite than popular history suggests.
+Useful for: nuancing the scale of historical resistance
+
+## Gaps
+
+- Could not find quantitative data on how many specific jobs were lost to textile machines
+- No Chinese-language academic sources on Luddite movement found
+- Alternative explanation: displacement narrative may be partly confounded by wartime demand shocks
+```
+
+## Source Line Format
+
+Each source line in the `## Sources` section must contain exactly:
+```
+[n] Title | URL | Source-Type: one-of{official|academic|secondary-industry|journalism|community|other} | As Of: YYYY-MM(or YYYY) | Authority: score/10
+```
+
+Rules:
+- [n] numbers are LOCAL to this task file (start at [1])
+- Lead agent will reassign GLOBAL [n] numbers in registry.md
+- URL must be from an actual search result (subagent MUST NOT invent URLs)
+- `Authority` score follows guide in quality-gates.md
+- `As Of` must be provided; use `undated` if unknown
+- High-confidence claims in final report must use `official` or `academic` sources
+
+## Findings Line Format
+
+Each finding must be:
+- One sentence of specific, factual information
+- End with source number(s) in brackets: [1] or [1][2]
+- Max 10 findings per task (forces prioritization)
+- No vague claims like "research shows..." — name what specifically
+
+Good: `Full textile mechanization transition took 50-90 years (1760s-1850s). [4]`
+Bad: `The transition took a long time. [4]`
+Bad: `Studies suggest that it was a lengthy process.` (no source, vague)
+
+## Deep Read Notes Format
+
+For each source that was web_fetched (full article read):
+- Key data: specific, numeric evidence from article
+- Key insight: the one thing this source says that others don't
+- Useful for: which final section this supports
+
+Max 4 lines per source. This is a research notebook, not a summary.
+
+## Gaps Section
+
+List what the subagent searched for but could NOT find, and possible counter-readings.
+This signals where evidence is thin and confidence should be lowered.
+
+## Registry Format (built by lead agent in P3)
+
+The `registry.md` file merges all task sources into a global registry and adds source-type / as-of fields.
+
+```markdown
+# Citation Registry
+Built from: task-a.md, task-b.md, task-c.md, task-d.md
+
+## Approved Sources
+
+[1] National Geographic — Luddites | https://www.nationalgeographic.com/... | Source-Type: secondary-industry | As Of: 2026-03 | Auth: 8 | From: task-a
+[2] Cambridge — Rage against machine | https://www.cam.ac.uk/... | Source-Type: academic | As Of: 2012-04 | Auth: 8 | From: task-a
+[3] OpenAI — Day Horse Lost Job | https://blogs.microsoft.com/... | Source-Type: official | As Of: 2026-01 | Auth: 8 | From: task-b
+...
+[N] Last source
+
+## Dropped
+
+x Quora answer | https://www.quora.com/... | Source-Type: community | As Of: 2024-10 | Auth: 3 | Reason: below threshold
+x Study.com | https://study.com/... | Source-Type: secondary-industry | As Of: undated | Auth: 4 | Reason: better sources available
+
+## Stats
+
+Total evaluated: 22
+Approved: 16
+Dropped: 6
+Unique domains: 12
+Source-type: official 4 / academic 3 / secondary-industry 5 / journalism 2 / community 2
+Max single-source share: 3/16 = 19% (pass)
+```
+
+Rules for registry:
+- [n] numbers here are FINAL — they appear unchanged in the report
+- Every [n] in the report must exist in the Approved list
+- Every Dropped source must NEVER appear in the report
+- If two tasks found the same URL, keep it once with the higher authority score
diff --git a/deep-research/references/source_accessibility_policy.md b/deep-research/references/source_accessibility_policy.md
new file mode 100644
index 0000000..844189d
--- /dev/null
+++ b/deep-research/references/source_accessibility_policy.md
@@ -0,0 +1,179 @@
+# Source Accessibility Policy
+
+**Version**: V6.1  
+**Purpose**: Distinguish between legitimate exclusive information advantages and circular verification traps
+
+---
+
+## The Problem
+
+In the "深度推理" case study, we made a **methodology error**:
+
+**What happened**:
+1. User asked to research **their own company**: "深度推理（上海）科技有限公司"
+2. We accessed user's **own Spaceship account** (their private registrar)
+3. Found 25 domains **the user already owned**
+4. Reported back: "The company owns these 25 domains"
+
+**Why this is wrong**:
+- This is **circular reasoning**, not research
+- User asked us to *discover* information about their company
+- We instead *queried* their private data and presented it as findings
+- It's like looking in someone's wallet to tell them how much money they have
+
+**The real question**: Can an external investigator confirm this company exists?
+**Answer**: No (WHOIS privacy, no public records)
+
+---
+
+## Core Principle: No Circular Verification
+
+### ❌ FORBIDDEN: Self-Verification
+
+When researching **the user's own assets/company/identity**:
+
+| Scenario | WRONG | RIGHT |
+|----------|-------|-------|
+| User's company | "I found in YOUR registrar that YOU own these domains" | "Public WHOIS shows privacy protection - ownership not externally verifiable" |
+| User's identity | "I checked YOUR email and found YOUR address" | "Please provide address if relevant to the research" |
+| User's property | "I accessed YOUR bank to see YOUR balance" | Not applicable to research |
+
+**Rule**: Cannot use user's private data to "discover" what user already knows about themselves.
+
+---
+
+### ✅ ALLOWED: Exclusive Information Advantage
+
+When researching **third parties** (competitors, markets, investments):
+
+| Source Type | Example | Usage |
+|-------------|---------|-------|
+| **User's paid subscriptions** | Crunchbase Pro, PitchBook, Wind | ✅ Use to research competitors |
+| **User's proprietary databases** | Internal CRM, industry databases | ✅ Use to research market |
+| **User's private APIs** | Trading APIs, data feeds | ✅ Use for investment research |
+| **User's internal documents** | Prior research, memos | ✅ Use as background for new research |
+
+**Rule**: User's exclusive information sources are competitive advantages - USE THEM for third-party research.
+
+---
+
+## The Distinction
+
+```
+Research Target: 深度推理（上海）科技有限公司
+├─ Is this the user's own company? → YES
+├─ Can we use user's private data about it? → NO (circular)
+└─ Must rely on: Public sources only
+
+Research Target: 竞争对手公司 X
+├─ Is this the user's own company? → NO
+├─ Can we use user's Crunchbase Pro? → YES (competitive advantage)
+└─ Can use: Public + User's exclusive sources
+```
+
+---
+
+## Corrected Methodology
+
+### When Researching User's Own Company
+
+**Approach**: External investigator perspective
+
+```
+User: "Research my company 深度推理"
+
+CORRECT RESPONSE:
+1. Search public sources (WHOIS, web, news)
+2. Find: Website placeholder, privacy-protected WHOIS, no news
+3. Report: "From public perspective: minimal footprint, cannot verify ownership"
+4. Gap: "Internal data not accessible to external investigators"
+
+INCORRECT RESPONSE:
+1. Access user's Spaceship account
+2. Find: 25 domains user already knows they own
+3. Report: "The company owns 25 domains" (user already knows this!)
+```
+
+### When User Provides Exclusive Sources
+
+**Approach**: Leverage competitive advantage
+
+```
+User: "Research competitor X, I have Crunchbase Pro"
+User: "Here's my API key: xxx"
+
+CORRECT RESPONSE:
+1. Use provided Crunchbase Pro API
+2. Find: Funding history, team info not in public sources
+3. Report: "Per Crunchbase Pro [exclusive source], X raised $Y in Series Z"
+4. Cite: Accessibility: exclusive (user-provided)
+```
+
+---
+
+## Source Classification
+
+### public ✅
+- Available to any external researcher
+- Examples: Public websites, news, SEC filings
+
+### exclusive-user-provided ✅ (FOR THIRD-PARTY RESEARCH)
+- User's paid subscriptions, private APIs, internal databases
+- **USE for**: Researching competitors, markets, investments
+- **DO NOT USE for**: Verifying user's own assets/identity
+
+### private-user-owned ❌ (FOR SELF-RESEARCH)
+- User's own accounts, emails, personal data
+- **DO NOT USE**: Creates circular verification
+
+---
+
+## Information Black Box Protocol
+
+When an entity (including user's own company) has no public footprint:
+
+1. **Document what external researcher would find**:
+   - WHOIS: Privacy protected
+   - Web search: No results  
+   - News: No coverage
+
+2. **Report honestly**:
+   ```
+   Public sources found: 0
+   External visibility: None
+   Verdict: Cannot verify from public perspective
+   Note: User may have private information not available to external investigators
+   ```
+
+3. **Do NOT**:
+   - Use user's private data to "fill gaps"
+   - Present user's private knowledge as "discovered evidence"
+
+---
+
+## Checklist
+
+When starting research, determine:
+
+1. **Who is the research target?**
+   - User's own company/asset? → Public sources ONLY
+   - Third party? → Can use user's exclusive sources
+
+2. **Am I discovering or querying?**
+   - Discovering new info? → Research
+   - Querying user's own data? → Circular, not allowed
+
+3. **Would this finding surprise the user?**
+   - Yes → Legitimate research
+   - No (they already know) → Probably circular verification
+
+---
+
+## Summary
+
+| Situation | Can Use User's Private Data? | Why? |
+|-----------|------------------------------|------|
+| Research user's own company | ❌ NO | Circular verification |
+| Research competitor using user's Crunchbase | ✅ YES | Competitive advantage |
+| Research market using user's database | ✅ YES | Exclusive information |
+| "Discover" user's own domain ownership | ❌ NO | User already knows this |
diff --git a/deep-research/references/subagent_prompt.md b/deep-research/references/subagent_prompt.md
new file mode 100644
index 0000000..1b3b97f
--- /dev/null
+++ b/deep-research/references/subagent_prompt.md
@@ -0,0 +1,116 @@
+# Subagent Prompt Template
+
+This file defines the prompt structure sent to each research subagent.
+The lead agent fills in the `{variables}` and dispatches.
+
+## Prompt
+
+```
+You are a research specialist with the role: {role}.
+
+## Your Task
+
+{objective}
+
+## Search Queries (start with these, adjust as needed)
+
+1. {query_1}
+2. {query_2}
+3. {query_3} (optional)
+
+## Instructions
+
+1. Run 2-4 web searches using the queries above (and variations).
+2. For the best 2-3 results, use web_fetch to read the full article.
+3. For each discovered source, assign:
+   - Source-Type: official|academic|secondary-industry|journalism|community|other
+   - As Of: YYYY-MM or YYYY (publication date or last verified)
+4. Assess each source's authority (1-10 scale).
+5. Write ALL findings to the file: {output_path}
+6. Record at least one explicit counter-claim candidate in `Gaps`.
+7. Use EXACTLY the format below. Do not deviate.
+
+## Output Format (write this to {output_path})
+
+---
+task_id: {task_id}
+role: {role}
+status: complete
+sources_found: {N}
+---
+
+## Sources
+
+[1] {Title} | {URL} | Source-Type: {Type} | As Of: {YYYY-MM-or-YYYY} | Authority: {score}/10
+[2] {Title} | {URL} | Source-Type: {Type} | As Of: {YYYY-MM-or-YYYY} | Authority: {score}/10
+...
+
+## Findings
+
+- {Specific fact, with source number}. [1]
+- {Specific fact, with source number and confidence}. [2]
+- {Another fact}. [1]
+... (max 10 findings, each one sentence, each with source number)
+
+## Deep Read Notes
+
+### Source [1]: {Title}
+Key data: {specific numbers, dates, percentages extracted from full text}
+Key insight: {the one thing this source contributes that others don't}
+Useful for: {which aspect of the broader research question}
+
+### Source [2]: {Title}
+Key data: ...
+Key insight: ...
+Useful for: ...
+
+## Gaps
+
+- {What you searched for but could NOT find}
+- {Alternative interpretation or methodological limitation}
+
+## END
+
+Do not include any content after the Gaps section.
+Do not summarize your process. Write the findings file and stop.
+```
+
+## Depth Levels
+
+**DEEP** — web_fetch 2-3 full articles and write detailed Deep Read Notes.
+Use for: core tasks where specific data points and expert analysis are critical.
+
+**SCAN** — rely mainly on search snippets, fetches at most 1 article.
+Use for: supplementary tasks like source mapping.
+
+## Environment-Specific Dispatch
+
+### Claude Code
+```bash
+# Single task
+claude -p "$(cat workspace/prompts/task-a.md)" \
+  --allowedTools web_search,web_fetch,write \
+  > workspace/research-notes/task-a.md
+
+# Parallel dispatch
+for task in a b c; do
+  claude -p "$(cat workspace/prompts/task-${task}.md)" \
+    --allowedTools web_search,web_fetch,write \
+    > workspace/research-notes/task-${task}.md &
+done
+wait
+```
+
+### Cowork
+Spawn subagent tasks via the subagent dispatch mechanism.
+
+### DeerFlow / OpenClaw
+Use the `task` tool:
+
+```python
+task(
+  prompt=task_a_prompt,
+  tools=["web_search", "web_fetch", "write_file"],
+  output_path="workspace/research-notes/task-a.md"
+)
+```