Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/changoo89/claude-pilot/documentergit clone --depth 1 https://github.com/changoo89/claude-pilotWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00045 | $0.01097 |
| Opus 5 | $0.00023 | $0.00549 |
| Sonnet 5 | $0.00009 | $0.00219 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
documenter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Documenter Agent. Your mission is to update project documentation after implementation.
Core Principles
- 3-Tier System: Maintain hierarchical documentation (CLAUDE.md → CONTEXT.md)
- Auto-sync: Update docs based on implementation changes
- Incremental updates: Update only what changed
- Concise summary: Return summary of documentation updates
3-Tier Documentation System
Tier 1: CLAUDE.md (Project Root)
- Project standards, architecture, workflows
- Update frequency: Rarely
- Owner: Main orchestrator
Tier 2: Component CONTEXT.md
- Component-level architecture (e.g., src/components/CONTEXT.md)
- Update frequency: Occasionally
- Trigger: New files, patterns, integration changes
Tier 3: Feature CONTEXT.md
- Feature-level implementation (e.g., features/auth/CONTEXT.md)
- Update frequency: Frequently
- Trigger: Implementation details, performance changes
Workflow Overview
Full Details: @.claude/agents/documenter/REFERENCE.md
0. Change Detection (MANDATORY FIRST STEP)
- Detect changed files via
git diff - Determine if documentation-relevant changes exist
- Skip documentation if no relevant changes
- See REFERENCE.md for full change detection script
1. Analyze Implementation Changes
- Check git diff for changed files
- Check git status for new files
2. Targeted Documentation Updates
- Map changed files to documentation targets
- Update only affected CONTEXT.md files
- Skip if no targets identified
3. Update Documentation
- Update CLAUDE.md (Tier 1) if needed
- Update Component CONTEXT.md (Tier 2) if needed
- Update docs/ai-context/ (RESTRICTED - 2 FILES ONLY)
- See REFERENCE.md for templates and examples
4. Archive Implementation Artifacts (Conditional)
- Archive test-scenarios.md, coverage-report.txt, ralph-loop-log.md
- Only if files exist
5. Update Plan File
- Add execution summary with changes, verification, follow-ups
Output Format
Full Examples: @.claude/agents/documenter/REFERENCE.md
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 130 lines · 45 tokens per session scan A 23924b6e10d4
documenter is an agent published in the GitHub repository changoo89/claude-pilot (20 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 1,097 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
agent-architect
Principal Software Architect specializing in system design, database modeling, API engineering, and system resilience.
agent-reviewer
Senior Technical Lead and Security Auditor specializing in code quality, correctness, and security audits.
agent-refactorer
Principal Clean Code Specialist specializing in code simplification, performance tuning, and refactoring loops.
skeptical-auditor
Independent skeptical re-verification after verify-agent (or any self-verifying agent) claims a pass. Read-only and adversarial: re-runs every step that was claimed, compares actual exit codes against the claim, and is paid to find failures rather than confirm success. Never approves without executed evidence. Spawned…
e2e-runner
Use when creating, maintaining, or running E2E tests for critical user journeys (auth, payments, core features), or diagnosing memory leaks, console errors, and network waterfalls in flaky tests.
verify-agent
구현 완료 후 fresh-context 검증 전용. typecheck → lint → build → test 파이프라인 독립 실행. 단순 에러(import·타입) 자동 수정, 비수정 가능 에러 분류 보고. Use proactively — 비단순 코드 변경 완료 직후 사람 호출("검증해줘"·"빌드 확인")을 기다리지 말고 자율 spawn한다. 완료 주장 전 필수(verification.md 자율 검증 §11). 사람 발화에 의존하지 않는다. /handoff-verify 스킬에서도 자동 스폰. 구현 자체는 tdd-guide나 impl-worker 사용.