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-lifecycle-sweepnpx skills add stainless-code/codemap --skill docs-lifecycle-sweepgit 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 | $0.00164 | $0.01592 |
| Opus 5 | $0.00082 | $0.00796 |
| Sonnet 5 | $0.00033 | $0.00318 |
| Haiku 4.5 | $0.00016 | $0.00159 |
Grade A, and why
docs-lifecycle-sweep 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs lifecycle sweep — the doc janitor
docs-governance defines what every doc should be. This skill is the how — it walks any doc-bearing surface, applies the spec mechanically, and produces a per-file action plan the user approves before anything is touched.
The promise: at the end of a sweep, every remaining file passes the existence test, every closed plan is lifted, every closed audit is either kept-with-justification or deleted-with-knowledge-lifted, every cross-reference still resolves, and there is no dead weight.
Procedure: WORKFLOW.md — enumerate → existence test → classify → report → execute on approval.
When to fire
User intent (any phrase is enough):
- "clean up stale docs" / "doc janitor" / "doc sweep"
- "audit docs lifecycle" / "compact audits" / "compact plans"
- "are these audits still earning their keep"
- "what's gone stale in
docs/" - "delete tombstones" / "no tombstones, please"
- "promote / lift / retire
<doc>" - "is this audit closed properly"
- "post-merge docs cleanup on PR #N"
Also fire proactively when:
- Closing a Plan, Audit, or Research file via
audit-pr-architecture, or any normal commit that ships a tracked roadmap item. - A repo-wide refactor changes paths or symbol names cited from docs (cross-reference rot risk).
Scope
The two surface tiers codemap has today:
| Tier | Substrate | Sweep scope |
|---|---|---|
| B — repo-wide | docs/ |
All 5 lifecycle types: architecture.md, roadmap.md, glossary.md, agents.md, etc. + plans/, research/, future audits/ |
| 0 — per-tooling-area | .agents/, .cursor/, scripts/, templates/agents/ |
Each rule + skill — apply existence test; check Tier 1 always-on cost still earns its keep |
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 · 72 lines · 164 tokens per session scan A 7c5696b7ac76
docs-lifecycle-sweep is a skill published in the GitHub repository stainless-code/codemap (8 stars, last pushed 6d ago), licensed MIT. It adds 164 tokens to every session and 1,592 once invoked, about $0.0008 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.