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 skills/stainless-code/codemap/docs-governancenpx skills add stainless-code/codemap --skill docs-governancegit clone --depth 1 https://github.com/stainless-code/codemapWhat 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 | $0.00235 | $0.01012 |
| Opus 5 | $0.00118 | $0.00506 |
| Sonnet 5 | $0.00047 | $0.00202 |
| Haiku 4.5 | $0.00023 | $0.00101 |
Grade A, and why
docs-governance 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 yesterday.
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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs governance
Repo-wide docs framework for codemap. Every doc in this repo lives in one of two surface tiers (codemap is small enough that the per-feature and per-shared-component tiers used in larger codebases don't apply here — yet). Full blueprint: LIFECYCLE.md.
The repo-root docs/README.md is the single canonical surface for the cited Rules — every other doc points at it; never restate the Rules. Consumer-surface policy: .agents/rules/consumer-surfaces.md (Rule 10 sub-bullet).
Quick rules
- Five lifecycle types — Reference (
architecture.md,glossary.md,agents.md, …), Roadmap (roadmap.md), Plan (plans/<feature-name>.md), Audit (audit.mdoraudits/<topic>.md), Research (research/<tool-name>.mdorresearch/<topic>-YYYY-MM.md). New content folds into one of these; no new top-level types. - Existence test — a doc earns its place if source cites it, it carries durable policy unavailable elsewhere, it tracks open work, or inbound cites require a slim stub. Otherwise fold + delete.
- Plans are deleted + lifted when work ships — durable bits move to
architecture.md/glossary.md/roadmap.md/ a rule or skill; the plan file dies. No "slim & keep in plans/" state. .gitkeepin each potentially-empty lifecycle folder (plans/,research/, andaudits/when it exists) so it stays discoverable when empty.- Anti-bloat — don't add a rule until there's content that needs it. Same for ownership-table rows in
docs/README.md. - Repo-level vs in-source — codemap-wide tool evaluations + adoption (oxlint, future plugins) live in
.agents/rules/+.agents/skills/, not as permanentdocs/research/files. Per-tool tracker notes are an anti-pattern — positioning lives indocs/why-codemap.md. - Cross-reference preservation — grep before slim; preserve cited rule numbers and section anchors. See LIFECYCLE.md § 7.
- Provenance —
docs/README.mdRules 1–10 are cited from acrossdocs/and.agents/. Don't renumber without a coordinated re-grep + edit pass.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 31 lines · 235 tokens per session scan A 210bd4c09ee5
docs-governance is a skill published in the GitHub repository stainless-code/codemap (8 stars, last pushed 6d ago), licensed MIT. It adds 235 tokens to every session and 1,012 once invoked, about $0.0012 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
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
analyze-usage
Use when asked to analyze codescout tool usage, check for error patterns, audit tool health, generate a usage report, spot anti-patterns, or clear usage statistics to start fresh.
m1nd-first
Use when investigating a repository, searching for implementation, reviewing changes, working from specs/docs, or preparing a risky code change in an environment where m1nd is available. This doctrine makes m1nd the first investigative layer before grep, glob, or manual file reads, except when the task is pure…
mcp-headless-test
Run live tests of the Ariadne MCP server using Claude Code in headless mode. Tests tool discovery, invocation, and filtering. Use when validating MCP server changes or checking integration with Claude Code.
mcp-analytics
Check Ariadne MCP tool usage analytics — session counts, tool call stats, durations, and error rates.
release
Prepare a new release of Ariadne packages. Creates changesets, verifies build/tests, and drafts the PR to main.