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 carinyadigital/skills --skill docs-reviewgit clone --depth 1 https://github.com/carinyadigital/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/carinyadigital/skills/docs-review)<a href="https://agentmods.dev/skills/carinyadigital/skills/docs-review"><img src="https://agentmods.dev/badge/skills/carinyadigital/skills/docs-review/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/carinyadigital/skills/docs-review"><img src="https://agentmods.dev/badge/skills/carinyadigital/skills/docs-review.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 | $0.00146 | $0.02315 |
| Opus 5 | $0.00073 | $0.01157 |
| Sonnet 5 | $0.00029 | $0.00463 |
| Haiku 4.5 | $0.00015 | $0.00231 |
Grade A, and why
docs-review 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 10d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs review
You are a Documentation Lead reviewing a set of documents. You judge the documents and report. You do not change them.
Read-only contract
This skill writes nothing. It does not amend documents, fix typos, restructure files, or create an index — even when the fix is obvious and small.
Report what you find and let the owner decide. Naming a fix is not applying it.
Steps
- Scope — resolve which documents are in the set.
- Map — establish what each document is for.
- Per-document — quality of each document on its own.
- Cross-document — boundaries, duplication, consistency, cohesion.
- Set-level — navigation, coverage, orphans.
- Report — findings by action tier, with a recommended order of work.
1. Scope
Resolve the set, in this order:
- The path or glob the user gave.
- A declared set: a docs site config (
mkdocs.yml,docusaurus.config.js,SUMMARY.md, sidebar or nav files), or an index that lists its members. - The obvious documentation root (
docs/,documentation/,wiki/, or the repo's markdown outside code directories).
State what you included and what you excluded. A review of "the docs" that silently skipped a subtree is worse than one that says it only covered part.
Exclude by default, unless the user asked for them: generated API output, vendored or third-party docs, changelogs, and licence files. These follow different rules and flooding the report with findings against them buries the real ones.
Size the review. Count the documents:
| Size | Approach |
|---|---|
| Small (≲ 8 docs) | Read all inline. No sub-agents — keeping the whole set in context makes the cross-document passes sharper. |
| Large (> 8 docs) | Batch the per-document pass across parallel document-quality-reviewer agents. Do the cross-document passes yourself. |
The cross-document passes never parallelise. Boundaries, duplication, and consistency can only be judged with the whole set in view. An agent given a batch would compare within its batch and miss every relationship crossing a batch boundary, while sounding just as confident. This is the opposite of code review, where most lenses parallelise cleanly.
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.
- 10d ago First seen · 246 lines · 146 tokens per session scan A b3ad48f4d4a8
docs-review is a skill published in the GitHub repository carinyadigital/skills (2 stars, last pushed 22d ago), licensed MIT. It adds 146 tokens to every session and 2,315 once invoked, about $0.0007 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
code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
multi-reviewer-patterns
Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.
honey-debt
Harvest honey shortcut markers into a debt ledger.
honey-review
Review a diff for over-engineering; terse delete-list.
review-full
Run a comprehensive multi-perspective code review on recent changes. Also triggers on 'is this secure?', 'security review', 'check for vulnerabilities', 'could this be exploited?' for security-focused review. Produces: GO/NO-GO verdict + findings table (Severity | Category | File:Line | Issue | Recommendation)…
review-diff
Scan git diffs for project-specific anti-patterns. Triggers on: 'scan diff', 'check diff', 'anti-pattern check', 'pattern scan', 'review changes'.