Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/grimoire-rs/grimoirenpx agentmods add skills/grimoire-rs/grimoire/docs-planWrote 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/grimoire-rs/grimoire/docs-plan)<a href="https://agentmods.dev/skills/grimoire-rs/grimoire/docs-plan"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/docs-plan/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/grimoire-rs/grimoire/docs-plan"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/docs-plan.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 | $0.00166 | $0.02805 |
| Opus 5.5 | $0.00066 | $0.01122 |
| Sonnet 5.5 | $0.00033 | $0.00561 |
| Haiku 4.5 | $0.00017 | $0.00281 |
Grade A, and why
docs-plan 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 1mo 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-plan
Discover what a project's documentation must cover, from the project's own evidence, and write the result to one durable artifact.
The artifact holds a ranked task list in three tiers and one user need per task. It also holds a typed inventory of every page, a coverage map, a delete list and an IA plan. Nothing here writes documentation prose.
Use this skill before writing or restructuring documentation. Use the
docs-quality rules while writing individual pages.
Stop condition
Stop when the artifact file exists on disk and all of the following hold.
- Every top-level subcommand or exported entry point appears either in the task list or in the explicit out-of-scope list.
- Every shortlisted task carries a user need, a tier, a ranking signal, a mapped
page or the literal
missing, and an action. - Every existing page carries a
doc_typevalue, proposed or already declared. - The delete list contains only pages that failed both delete signals.
Then stop. Do not write the pages. Do not apply the delete list without the maintainer saying so, because deleting documentation unattended is a different risk class from writing a page.
The evidence rule
Every claim in the artifact comes from the repository, its issue tracker, its logs, or a run you actually performed. Never from an existing docs page title, and never from a number you did not measure. Those two shortcuts are the way this procedure gets faked, and both have their own rule.
Procedure
Run the steps in order. Each names the output it must leave behind.
1. Declare the product shape
Read the docs config for one of cli, library, hosted-service or
framework. Look in the mkdocs.yml extra table, a pyproject.toml tool
table, or a docs.toml. If none is declared, infer one from the repository and
write it into the config as part of this run.
Output: one shape value, recorded in the artifact header. Every first-steps threshold later branches on it. See references/tiers-and-types.md.
What ships with it
5 files 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.
- 1mo ago First seen · 251 lines · 166 tokens per session scan A f24e1aa34961
docs-plan is a skill published in the GitHub repository grimoire-rs/grimoire (14 stars, last pushed today), licensed Apache-2.0. It adds 166 tokens to every session and 2,805 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-08.
Other skills, from other repositories
vuln-scanner
Audit trending repos for real security vulnerabilities and disclose responsibly - scan and route findings (PVR / dependency PR), re-submit queued advisories, and send armed email disclosures.
fork-fleet
Fork divergence monitor - tracks where the fleet's active forks diverge in CODE (unique commits, new/modified skills) and CONFIG (enable/var/model/schedule vs upstream), gated on real change.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
autoresearch
Evolve a skill by generating variations, evaluating them, and updating the best version.