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 levnikolaevich/claude-code-skills --skill ln-21-documentation-auditorgit clone --depth 1 https://github.com/levnikolaevich/claude-code-skillsWrote 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/levnikolaevich/claude-code-skills/ln-21-documentation-auditor)<a href="https://agentmods.dev/skills/levnikolaevich/claude-code-skills/ln-21-documentation-auditor"><img src="https://agentmods.dev/badge/skills/levnikolaevich/claude-code-skills/ln-21-documentation-auditor/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/levnikolaevich/claude-code-skills/ln-21-documentation-auditor"><img src="https://agentmods.dev/badge/skills/levnikolaevich/claude-code-skills/ln-21-documentation-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 83 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00034 | $0.02529 |
| Opus 5 | $0.00017 | $0.01264 |
| Sonnet 5 | $0.00007 | $0.00506 |
| Haiku 4.5 | $0.00003 | $0.00253 |
Grade A, and why
ln-21-documentation-auditor 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 4d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Auditor
Goal: Audit documentation as a read-only evidence system: can a new contributor, operator, user, or coding agent find the right source, trust its claims, and act without hidden context? Review both standalone documents and code comments where they carry public or operational knowledge.
Execution contract: The ordered checkboxes are the Definition of Done. Track every item internally as PENDING, PROVEN with concrete evidence, CLEARED with evidence that its condition is absent, or UNPROVEN with a gap; reading, delegation, or tool failure is not proof. Reconcile items after each section. Before returning, resolve all PENDING and count only PROVEN and CLEARED; apply the skill's verdict and approval rules to every gap.
Preserve user intent, scope, and existing authorization. Continue authorized work; ask only for consequential unresolved choices or required external approval. Scale depth to material risk without silently skipping checks. Preserve dependency and safety ordering; otherwise choose the verification method appropriate to each obligation.
Tool Routing
| Need | Preferred tool | Use it when | Fallback |
|---|---|---|---|
| Document inventory and hierarchy | Native file listing with narrow patterns | Establishing documentation surfaces, generated areas, and navigation structure | Repository tree and known entry documents |
| Links, repeated terms, claims, and contradictions | Native text search, then focused reads | Finding references, stale names, duplicated guidance, paths, commands, and configuration keys | Manual cross-document comparison |
| Code and configuration truth | Native code search, manifests, schemas, and direct file reads | A document claims that a path, option, endpoint, behavior, or default exists | Execute a safe inspection command when text is insufficient |
| Freshness and ownership | Git log, blame, and diff | Determining when a claim changed, whether a document tracks active code, or who owns a convention | Current code and explicit ownership files |
| Commands and examples | Shell in non-mutating or dry-run mode | Verifying help text, command existence, config parsing, generated output, or example syntax | Inspect command registration and tests; mark runtime proof unavailable |
| External facts | Official documentation, specifications, and release notes | A current external API, version, standard, or platform behavior affects correctness | Primary-source web research; otherwise mark UNVERIFIED |
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.
- 4d ago Changed · -23 lines · -8 tokens per session 5adfa79f2cbe
- 11d ago First seen · 139 lines · 42 tokens per session scan A 52b8028a7fcc
ln-21-documentation-auditor is a skill published in the GitHub repository levnikolaevich/claude-code-skills (559 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 2,529 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
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.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
sr-reviewer
Reviewer role for the specrails implement pipeline. Validates the entire implementation: the OpenSpec change package (proposal/design/tasks/specs) is well-formed, the developer's code matches the design's public API and invariants, every tasks.md box is ticked, the tests cover every spec scenario, and the project's…
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
dev-full-auto
Hand over a spec and walk away — plans, builds, tests and audits on its own, stopping only at a real blocker.