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 skills add manhua-man/harness-coding-protocol --skill project-ai-docs-stewardgit 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/skills/manhua-man/harness-coding-protocol/project-ai-docs-steward)<a href="https://agentmods.dev/skills/manhua-man/harness-coding-protocol/project-ai-docs-steward"><img src="https://agentmods.dev/badge/skills/manhua-man/harness-coding-protocol/project-ai-docs-steward/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/manhua-man/harness-coding-protocol/project-ai-docs-steward"><img src="https://agentmods.dev/badge/skills/manhua-man/harness-coding-protocol/project-ai-docs-steward.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00041 | $0.01961 |
| Opus 5 | $0.00020 | $0.00981 |
| Sonnet 5 | $0.00008 | $0.00392 |
| Haiku 4.5 | $0.00004 | $0.00196 |
Grade A, and why
project-ai-docs-steward 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 today.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project AI Docs Steward
Maintain structured entry documentation so every AI tool reading the target repo gets a consistent stack.
事 = AGENTS.md (Facts) · 法 = CLAUDE.md (Protocol) — both are mandatory for AI context. Missing 法 → codes without collaboration rules; missing 事 → reasons without correct facts.
This skill edits target-repo entry markdown only after a quality report and explicit user approval. Files created by a confirmed /harness-init run may still be untracked and remain eligible; unknown untracked files are user-owned and out of scope unless the user names them. Prefer updating existing files over duplicates (Update Before Create).
Layer model
Stack: 法 (CLAUDE.md) → 事 (AGENTS.md) → steering (scoped overrides) → docs/ (human prose; not an AI truth source).
| Tier | Role | Typical paths |
|---|---|---|
| 1 · Entry routing | What to read first | .cursor/rules/*.mdc |
| 2 · 法 + 事 | AI truth | CLAUDE.md, AGENTS.md |
| 3 · Overrides + human docs | Steering; long-form specs | steering/*.md or .kiro/steering/*.md, docs/** |
Steering path resolution: If .kiro/steering/ exists, use it; else steering/. If both exist, audit both; index file may be project.md or README.md inside that folder.
Conflict rule: AI truth = AGENTS + CLAUDE; steering patches specific contexts; docs/ does not override 事/法.
Locale
Same priority as /harness-init Draft locale (ai-ide/skills/harness-init/SKILL.md § Draft locale):
- Explicit user locale instruction this session — hard override; switch language when the user asks.
- Otherwise preserve each file's existing body locale; new bullets match the file being edited and the target repo's entry-doc language.
- Do not anglicize a Chinese repo or sinicize an English repo unless the user requests it.
Workflow
Phase 1: Discovery
Locate entry files in the target workspace (Glob preferred):
AGENTS.md,CLAUDE.md,DESIGN.md(optional),.claude.local.md.cursor/rules/*.mdcsteering/**/*.mdand/or.kiro/steering/**/*.mdpackages/**/CLAUDE.md(monorepo overrides)- Repository-owned skills/commands:
**/*SKILL.md,.claude/commands/,.cursor/commands/,ai-ide/commands/,.agents/skills/(as present)
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.
- today Changed · +27 lines · -19 tokens per session 783a664663f9
- 8d ago First seen · 105 lines · 60 tokens per session scan A 5344c2688870
project-ai-docs-steward is a skill published in the GitHub repository manhua-man/harness-coding-protocol (5 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,961 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 skills, from other repositories
investigate
Manage structured investigations with multi-agent evidence collection, synthesis, tagging, and PHI sanitization. Use when user says "start an investigation", "root cause analysis", or "collect evidence about X". Subcommands: new, run, collect, synthesize, close, status, list, search. Do NOT use for casual debugging or…
playbook
Analyze your Claude Code configuration and suggest improvements based on the agentic coding playbook. Use when user says "audit my config", "check my setup", or "improve my CLAUDE.md". Works on both global and project-level CLAUDE.md files. Do NOT use for application configuration — only for Claude Code setup.
checkpoint
Save all work, update memory, commit, push, and prepare to end the session. Use when user says "save my work", "wrap up", or "I'm done for now". Use at natural breakpoints or when context is getting large.
create-project
Scaffold a new project with git, .gitignore, CLAUDE.md, AGENTS.md, GitHub repo, and memory directory. Use when user says "start a new project", "create a repo", or "scaffold an app". Creates the project as a sibling to the .claude/ config directory.
learn
Capture a lesson as a structured knowledge entry. Use when you discover a non-obvious bug, workaround, or pattern worth preserving for future sessions. Use when user says "remember this", "save this lesson", or "this is worth noting".
promote
Promote a project-level lesson to global scope so it's available across all projects. Use when user says "make this global", "share this across projects", or "promote this lesson". Use when a lesson discovered in one project would benefit others.