Files
claude-skills-reference/engineering-team/self-improving-agent/CLAUDE.md
Alireza Rezvani e09d202aa3 feat: add self-improving-agent plugin — auto-memory curation for Claude Code (#260)
New plugin: engineering-team/self-improving-agent/
- 5 skills: /si:review, /si:promote, /si:extract, /si:status, /si:remember
- 2 agents: memory-analyst, skill-extractor
- 1 hook: PostToolUse error capture (zero overhead on success)
- 3 reference docs: memory architecture, promotion rules, rules directory patterns
- 2 templates: rule template, skill template
- 20 files, 1,829 lines

Integrates natively with Claude Code's auto-memory (v2.1.32+).
Reads from ~/.claude/projects/<path>/memory/ — no duplicate storage.
Promotes proven patterns from MEMORY.md to CLAUDE.md or .claude/rules/.

Also:
- Added to marketplace.json (18 plugins total)
- Added to README (Skills Overview + install section)
- Updated badge count to 88+
- Regenerated .codex/skills-index.json + symlink

Co-authored-by: Leo <leo@openclaw.ai>
2026-03-05 17:16:53 +01:00

80 lines
2.5 KiB
Markdown

# Self-Improving Agent — Claude Code Instructions
This plugin helps you curate Claude Code's auto-memory into durable project knowledge.
## Commands
Use the `/si:` namespace for all commands:
- `/si:review` — Analyze auto-memory health and find promotion candidates
- `/si:promote <pattern>` — Graduate a learning to CLAUDE.md or `.claude/rules/`
- `/si:extract <pattern>` — Create a reusable skill from a proven pattern
- `/si:status` — Quick memory health dashboard
- `/si:remember <knowledge>` — Explicitly save something to auto-memory
## How auto-memory works
Claude Code maintains `~/.claude/projects/<project-path>/memory/MEMORY.md` automatically. The first 200 lines load into every session. When it grows too large, Claude moves details into topic files like `debugging.md` or `patterns.md`.
This plugin reads that directory — it never creates its own storage.
## When to use each command
### After completing a feature or debugging session
```
/si:review
```
Check if anything Claude learned should become a permanent rule.
### When a pattern keeps coming up
```
/si:promote "Always run migrations before tests in this project"
```
Moves it from MEMORY.md (background note) to CLAUDE.md (enforced rule).
### When you solved something non-obvious that could help other projects
```
/si:extract "Docker build fix for ARM64 platform mismatch"
```
Creates a standalone skill with SKILL.md, ready to install elsewhere.
### To check memory capacity
```
/si:status
```
Shows line counts, topic files, stale entries, and recommendations.
## Key principle
**Don't fight auto-memory — orchestrate it.**
- Auto-memory is great at capturing patterns. Let it do its job.
- This plugin adds judgment: what's worth keeping, what should be promoted, what's stale.
- Promoted rules in CLAUDE.md have higher priority than MEMORY.md entries.
- Removing promoted entries from MEMORY.md frees space for new learnings.
## Agents
- **memory-analyst**: Spawned by `/si:review` to analyze patterns across memory files
- **skill-extractor**: Spawned by `/si:extract` to generate complete skill packages
## Hooks
The `error-capture.sh` hook fires on `PostToolUse` (Bash only). It detects command failures and appends structured entries to auto-memory. Zero overhead on successful commands.
To enable:
```json
// .claude/settings.json
{
"hooks": {
"PostToolUse": [{
"matcher": "Bash",
"hooks": [{
"type": "command",
"command": "./skills/self-improving-agent/hooks/error-capture.sh"
}]
}]
}
}
```