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 commands/manhua-man/harness-coding-protocol/revise-ai-docsgit clone --depth 1 https://github.com/manhua-man/harness-coding-protocolWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/manhua-man/harness-coding-protocol/revise-ai-docs)<a href="https://agentmods.dev/commands/manhua-man/harness-coding-protocol/revise-ai-docs"><img src="https://agentmods.dev/badge/commands/manhua-man/harness-coding-protocol/revise-ai-docs.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00034 | $0.00675 |
| Opus 5 | $0.00017 | $0.00338 |
| Sonnet 5 | $0.00007 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
revise-ai-docs 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 5d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review this session for durable learnings about working with AI in the current target repository. Update the minimal set of files so future sessions load correct context.
Follow the layer model in ../skills/project-ai-docs-steward/SKILL.md.
事 = AGENTS.md (Facts) · 法 = CLAUDE.md (Protocol) — docs/ remains human background unless fixing a link from entry docs.
Step 1: Reflect
What would have changed a future decision? (commands, ports, test patterns, module boundaries, recurring tool behavior)
Before persisting a learning, require all three:
- Recurrence — evidence that the situation can recur, not merely that it happened once.
- Future decision value — a future agent would choose differently because this rule exists.
- Net simplicity — the rule removes more repeated discovery or error than the permanent documentation, state, and maintenance it adds.
Prefer deleting or simplifying a stale rule over adding another exception. One-off incidents, temporary workarounds, speculative governance, and rules with no current caller are not durable learnings.
Step 2: Find target files
| Kind | Path |
|---|---|
| Facts | ./AGENTS.md |
| Protocol | ./CLAUDE.md |
| Personal (gitignored) | ./.claude.local.md if appropriate |
| Scoped rules | steering/*.md or .kiro/steering/*.md |
One line per durable learning. Do not paste session logs.
Step 3: Route
- Commands / layout / ports →
AGENTS.md - Tool routing →
AGENTS.md§ AI Assistant Tool Index; separate repository-owned tools from recommended external/global tools - Collaboration norms →
CLAUDE.md - Narrow technical convention or optional reference rule → matching steering file; keep reference-only material clearly labelled and do not silently promote it into mandatory protocol
- Create a new
steering/*.mdreference only when the user explicitly asks for it or explicitly approves a proposed project-specific casebook. Adapt examples to real project paths and invariants; never copy a generic template verbatim. - Unsure → do not persist it. Keep uncertainty in the current response and gather evidence in a later session if it recurs.
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.
- 5d ago First seen · 55 lines · 34 tokens per session scan A a8fc1f61cff2
revise-ai-docs is a command published in the GitHub repository manhua-man/harness-coding-protocol (5 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 675 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 2026-08-31.
Other commands, from other repositories
constitution
根据交互输入或已提供原则创建或更新项目章程，并确保相关模板保持同步。.
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
security-audit
Comprehensive security audit of your project AND Claude Code configuration. Analyzes secrets exposure, injection surfaces, dependencies, hook security, and produces a scored security posture assessment.
audit-quiz-coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions.
diff-docs
Compare official Anthropic docs baseline vs current snapshot (no network — instant).