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/update-docsgit clone --depth 1 https://github.com/manhua-man/harness-coding-protocolWhat 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 | $0.00001 | $0.01443 |
| Opus 5 | $0.00000 | $0.00722 |
| Sonnet 5 | $0.00000 | $0.00289 |
| Haiku 4.5 | $0.00000 | $0.00144 |
Grade A, and why
update-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 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Update
Sync human documentation with implementation reality: $ARGUMENTS
Two jobs:
- Discovery — By default, infer candidate markdown from recent git changes; when the user names a topic or paths, follow the user first.
- Writing — For each file in scope, apply document types, layout, and doc-governance rules below.
Not in scope: replacing AGENTS.md / CLAUDE.md (use /revise-ai-docs or /project-ai-docs-steward). No spec-kit phase percentages or specs/ trees unless the repo actually uses them.
Change discovery (default on)
Priority: user $ARGUMENTS (topic, paths, module names) over git inference below.
- Git signals — Recent commits touching
*.md; unstaged/stagedgit diff --name-onlyfor markdown and for code/config that may invalidate docs. - Direct hits — Any
.mdalready in the diff goes on the candidate list. - Path association — When code under a directory changed, check human docs that usually describe that area (nearby README, related
docs/pages, package-level readme). Do not blindfindof every markdown file. An optional local mapping table in the target repo (e.g.steering/docs-path-map.mdor a project copy of this command) may narrow this step — mapping tables stay in the app repo, not in this protocol command. - Keyword search (narrow) — From changed files, extract module names, endpoints, env vars, script names; search only
docs/**and mapped doc paths withrg/grep. Skip repo-wide sweeps when the user narrowed scope. - Fact check — Commands, ports, paths against
AGENTS.mdand the live tree; human docs do not override AI truth.
If the user named specific files or a topic, skip broadening search beyond that scope plus obvious cross-links.
Human docs/** and README.md are background; they do not override AGENTS.md / CLAUDE.md.
Doc layers (typical repo — skip missing paths)
| Layer | Common path | Role |
|---|---|---|
| AI truth · Facts | AGENTS.md |
Facts; one-line link only when adding a new entry point |
| AI truth · Protocol | CLAUDE.md |
Protocol; not bulk-edited here |
| Scoped overrides | steering/**, .kiro/steering/**, etc. |
When present |
| Human long-form | docs/** |
Architecture, modules, runbooks |
| Entry | README.md |
Navigation; no duplicating AGENTS.md tables |
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 · 94 lines · 0 tokens per session scan A 32e0f79ecf58
update-docs is a command published in the GitHub repository manhua-man/harness-coding-protocol (5 stars, last pushed 2d ago), licensed MIT. It adds 1 tokens to every session and 1,443 once invoked, about $0.0000 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。.
cross-research
Two-phase multi-model research. Phase A fans codex+gemini in parallel (benchmarks + citations angles); Phase B synthesises via fresh Claude session. Usage: /cross-research [--with | list | compare].
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
ijfw-execute
Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name].
ijfw-metrics
Show IJFW token / cost / session metrics over a time window. Reads .ijfw/metrics/sessions.jsonl via the ijfwmetrics MCP tool.