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 grimoire-rs/grimoire --skill docs-instrumentgit clone --depth 1 https://github.com/grimoire-rs/grimoireWrote 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-instrument)<a href="https://agentmods.dev/skills/grimoire-rs/grimoire/docs-instrument"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/docs-instrument/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-instrument"><img src="https://agentmods.dev/badge/skills/grimoire-rs/grimoire/docs-instrument.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 | $0.00177 | $0.04409 |
| Opus 5.5 | $0.00071 | $0.01764 |
| Sonnet 5.5 | $0.00035 | $0.00882 |
| Haiku 4.5 | $0.00018 | $0.00441 |
Grade A, and why
docs-instrument 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-instrument
A repository has adopted the docs-quality rule set. Most of its rules carry a
runnable verification, and none of those verifications runs yet. This skill
turns that rule set into a gate that actually fails.
Work in cost order. The declaration retrofit is first because eight other families read the declaration, and none of their checks can classify a page until it lands.
Stop condition
Stop when all five hold. Do not keep going, and do not add rules.
- Every
checks/script the repo wires up exits 0 with--self-test. - Every wired check has been seen red once, on a planted violation you reverted.
- Every file path named in a runner target, a lint config or a rule row resolves on disk.
- The signal manifest names every signal, including the deferred ones and their preconditions.
- The whole-tree warning counts are recorded as the ratchet baseline.
A check that cannot go red is not coverage. A path that does not resolve is not a check. Both are the failure this whole gate exists to prevent.
Before you start
- Read
rules/docs-quality/checks.md. It carries one row per script: what it checks, how to run it, its exit codes and its fixtures. Every flag beyond the common four lives there. Never invent a script name or a flag. - Every Python check shares one interface:
python3 checks/<name>.py [--root DIR] [PATH ...] [--format text|json] [--self-test]. Exit 0 is clean, 1 is findings, 2 is a usage error or missing input. Findings print aspath:line: DOC-XXX-nn: message. - Find the generator config:
mkdocs.yml,book.toml,.vitepress/config.*,docusaurus.config.*,astro.config.*,docs/conf.py. The answer decides most of the wiring. See references/wiring-by-generator.md. - Do not rewrite prose in this skill's work. Retrofits and configs only. A content fix belongs in its own change.
The procedure
Step 1. Build the published-file list
Every check reads this list. Getting it wrong is how a prose lint ends up reporting on research notes and agent config (DOC-PLAIN-23).
What ships with it
4 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 · 334 lines · 177 tokens per session scan A a7514e8c3a95
docs-instrument is a skill published in the GitHub repository grimoire-rs/grimoire (14 stars, last pushed today), licensed Apache-2.0. It adds 177 tokens to every session and 4,409 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
create-prove
Run a changed Aeon skill for real and attach SHA-bound behavioral evidence to its PR.
verification-engine
Use when verifying build/test/lint before commit, PR, or completion claims. Runs verification pipeline in fresh subagent context with auto-repair. Triggers on /handoff-verify, pre-commit check, build verification, test validation.
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
agent-e2e-test-specialist
Specialist subagent: Playwright, Cypress, and visual regression testing specialist. Use only when the user explicitly asks for E2E tests, browser test automation, or visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.
agent-test-generator
Specialist subagent: Generates comprehensive test suites using TDD patterns. Use only when the user explicitly asks for tests, improved coverage, or test-first development.