Self Improving Agent

--- name: "self-improving-agent" description: "Curate an agent runtime's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to AI_RUNTIME_GUIDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what AI assistant has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity."

Internal Safety Override

• Status: local-only unless explicitly opted into external access.
• Before using network tools, account connectors, browser automation, or APIs, state the destination, data scope, and credential source.
• Do not transmit repository files, secrets, credentials, or private documents by default.
• Audit categories: network, secrets.

Self-Improving Agent

Auto-memory captures. This plugin curates.

an agent runtime's auto-memory (v2.1.32+) automatically records project patterns, debugging insights, and your preferences in MEMORY.md. This plugin adds the intelligence layer: it analyzes what AI assistant has learned, promotes proven patterns into project rules, and extracts recurring solutions into reusable skills.

Quick Reference

How It Fits Together

┌─────────────────────────────────────────────────────────┐
│                  an agent runtime Memory Stack                │
├─────────────┬──────────────────┬────────────────────────┤
│  AI_RUNTIME_GUIDE.md  │   Auto Memory    │   Session Memory       │
│  (you write)│   (AI assistant writes)│   (AI assistant writes)      │
│  Rules &    │   MEMORY.md      │   Conversation logs    │
│  standards  │   + topic files  │   + continuity         │
│  Full load  │   First 200 lines│   Contextual load      │
├─────────────┴──────────────────┴────────────────────────┤
│              ↑ /si:promote        ↑ /si:review          │
│         Self-Improving Agent (this plugin)               │
│              ↓ /si:extract    ↓ /si:remember            │
├─────────────────────────────────────────────────────────┤
│  .claude/rules/    │    New Skills    │   Error Logs     │
│  (scoped rules)    │    (extracted)   │   (auto-captured)│
└─────────────────────────────────────────────────────────┘

Installation

an agent runtime (Plugin)

/plugin marketplace add alirezarezvani/ai-ops-skills
/plugin install self-improving-agent@ai-ops-skills

OpenClaw

clawhub install self-improving-agent

an agent runtime

./scripts/codex-install.sh --skill self-improving-agent

Memory Architecture

Where things live

The promotion lifecycle

1. AI assistant discovers pattern → auto-memory (MEMORY.md)
2. Pattern recurs 2-3x → /si:review flags it as promotion candidate
3. You approve → /si:promote graduates it to AI_RUNTIME_GUIDE.md or rules/
4. Pattern becomes an enforced rule, not just a note
5. MEMORY.md entry removed → frees space for new learnings

Core Concepts

Auto-memory is capture, not curation

Auto-memory is excellent at recording what AI assistant learns. But it has no judgment about:

• Which learnings are temporary vs. permanent
• Which patterns should become enforced rules
• When the 200-line limit is wasting space on stale entries
• Which solutions are good enough to become reusable skills

That's what this plugin does.

Promotion = graduation

When you promote a learning, it moves from AI assistant's scratchpad (MEMORY.md) to your project's rule system (AI_RUNTIME_GUIDE.md or .claude/rules/). The difference matters:

• MEMORY.md: "I noticed this project uses pnpm" (background context)
• AI_RUNTIME_GUIDE.md: "Use pnpm, not npm" (enforced instruction)

Promoted rules have higher priority and load in full (not truncated at 200 lines).

Rules directory for scoped knowledge

Not everything belongs in AI_RUNTIME_GUIDE.md. Use .claude/rules/ for patterns that only apply to specific file types:

# .claude/rules/api-testing.md
---
paths:
  - "src/api/**/*.test.ts"
  - "tests/api/**/*"
---
- Use supertest for API endpoint testing
- Mock external services with msw
- Always test error responses, not just happy paths

This loads only when AI assistant works with API test files — zero overhead otherwise.

Agents

memory-analyst

Analyzes MEMORY.md and topic files to identify:

• Entries that recur across sessions (promotion candidates)
• Stale entries referencing deleted files or old patterns
• Related entries that should be consolidated
• Gaps between what MEMORY.md knows and what AI_RUNTIME_GUIDE.md enforces

skill-extractor

Takes a proven pattern and generates a complete skill:

• SKILL.md with proper frontmatter
• Reference documentation
• Examples and edge cases
• Ready for /plugin install or clawhub publish

Hooks

error-capture (PostToolUse → Bash)

Monitors command output for errors. When detected, appends a structured entry to auto-memory with:

• The command that failed
• Error output (truncated)
• Timestamp and context
• Suggested category

Token overhead: Zero on success. ~30 tokens only when an error is detected.

Platform Support

Related

• an agent runtime Memory Docs
• pskoett/self-improving-agent — inspiration
• playwright-pro — sister plugin in this repo