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 paultyng/skill-issue --skill review-documentationgit clone --depth 1 https://github.com/paultyng/skill-issueWrote 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/paultyng/skill-issue/review-documentation)<a href="https://agentmods.dev/skills/paultyng/skill-issue/review-documentation"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/review-documentation/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/paultyng/skill-issue/review-documentation"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/review-documentation.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 | $0.00083 | $0.02491 |
| Opus 5.5 | $0.00033 | $0.00996 |
| Sonnet 5.5 | $0.00017 | $0.00498 |
| Haiku 4.5 | $0.00008 | $0.00249 |
Grade A, and why
review-documentation scanned grade A with 1 finding 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 8d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Findings must cite probed evidence (`path:line`, grep output, command result), not pattern-matched suspicion. Per `~/.claude/rules/probe-not-assume.md`. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Review
Structured documentation review producing actionable, prioritized findings with code-level references. Checks that documentation exists, is accurate, and stays in sync with the implementation.
Workflow
1. Scope and explore
- Confirm scope with the user: full codebase, specific packages/directories, changed files only (PR or branch diff), or specific concern.
- Resolve scope to a file/package list. Based on what the user requested:
- Changed files (PR or branch): Run
git diff --name-only --diff-filter=d <base>...HEADto get changed files (default<base>ismain). If the user references a PR number, usegh pr diff <number> --name-onlyinstead. Filter to relevant file types (.go,.proto,.md, OpenAPI specs). Derive affected Go packages from the file paths (unique parent directories containing.gofiles). - Explicit paths/packages: The user may specify directories (e.g.
internal/auth/), Go package patterns (e.g../internal/auth/...), or individual files. When given a directory or package pattern, include all files under it. Derive Go package paths forgo docinvocations. - Full codebase: No filtering; explore everything (default).
- Changed files (PR or branch): Run
- Pass the resolved scope (file list and derived package paths) to all exploration and investigation subagents so findings stay scoped to those files. Reading is not scoped: follow callees, callers, and third-party source wherever a finding depends on their behavior. Report bugs in code the scope touches or calls even when they predate the diff, prefixed
pre-existing:. - Detect which documentation surfaces exist within the resolved scope:
.gofiles →go docanalysis,doc.gofiles,Example*tests.protofiles → service/method/message/field commentsopenapi.yml/openapi.yaml/swagger.*→ API descriptions*.mdfiles → README, guides, changelogs
2. Launch investigation subagents in parallel
Launch up to 3 investigation subagents concurrently using the Task tool (model: sonnet per subagent-model-routing — documentation analysis requires cross-referencing signatures and prose). Each receives the list of in-scope files as context. Only launch subagents whose preconditions are met.
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.
- 8d ago Changed · +28 tokens per session 0cef07c4c153
- 1mo ago First seen · 182 lines · 55 tokens per session scan A 21b98c25ec97
review-documentation is a skill published in the GitHub repository paultyng/skill-issue (8 stars, last pushed 4d ago), licensed MIT. It adds 83 tokens to every session and 2,491 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
deep-review
Evidence-based deep code review rubric — severity + confidence findings across maintainability, correctness, security, performance, and testing. Push for ambitious structural simplification (code judo), not just local cleanup. Escalate hands-on triage to the code-reviewer agent.
gh-address-comments
Triage and address open GitHub PR review and conversation comments using the gh CLI. Use when the user wants to "address PR comments", "resolve review threads", or "respond to reviewers" on the current branch's pull request.
pr-alignment-loop
Iterate a PR to its final form by running two opposing reviewer droids (reviewer-robustness and reviewer-minimalist) in a bounded back-and-forth loop. The main orchestrator synthesizes their feedback, makes edits, runs tests, and stops when both approve, on stagnation, or after 3 rounds. Use when the user asks to…
deslop
Remove AI-generated code slop and clean up code style.
blind-spot-pass
Run a pre-build blind spot pass before the agent builds anything. Treat the user's prompt as the map and the real project as the territory: classify gaps across known knowns, known unknowns, unknown knowns, and unknown unknowns (with deps, edge cases, and blast radius under unknown unknowns); ask 5 to 10 high-leverage…
merge-open-prs
Review, verify (Docker by default), and auto-merge open PRs when CI, reviews, and local verification pass. Batch up to 10 PRs per run. Use when the user wants to merge all open PRs, clear the PR queue, or run /merge-open-prs.