Borrowing it
Nothing to install: this file belongs to zernie/vigiles. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zernie/vigiles/main/.claude/skills/review-docs/SKILL.mdgit clone --depth 1 https://github.com/zernie/vigilesWrote 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/zernie/vigiles/review-docs)<a href="https://agentmods.dev/skills/zernie/vigiles/review-docs"><img src="https://agentmods.dev/badge/skills/zernie/vigiles/review-docs.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00113 | $0.01493 |
| Opus 5 | $0.00056 | $0.00746 |
| Sonnet 5 | $0.00023 | $0.00299 |
| Haiku 4.5 | $0.00011 | $0.00149 |
Grade A, and why
review-docs 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 7d 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.
Review a front-door doc (default README.md; honor a path the user names) the way
real readers would — not the way the author does. The author knows what every line
means; a first-time reader does not. The job is to surface where a specific audience
gets confused, under-served, or bounces, score it, and propose concrete fixes.
The method is fan-out: spawn one subagent PER PERSONA, all in parallel, each doing a cold read as that reader. Different readers catch different things; running them concurrently is faster and keeps each read uncontaminated by the others.
How to run it
1. Read the target doc yourself first
Read the doc in full and skim the docs it links to (so "promises depth the linked doc doesn't deliver" is checkable). You need this to judge the personas' findings and to apply fixes later.
2. Fan out one subagent per persona — in parallel
Spawn the personas below as subagents in a single message (multiple Agent/Task calls at once) so they run concurrently. Use a fast, cheap model (Sonnet or Haiku) — this is a reading/judgment task, not heavy synthesis — and say so in one line when you launch them.
Give EACH subagent the same rubric, only the persona changes:
You are <PERSONA>. Read
<path>(ignore any HTML comment block at the top — that's internal authoring notes, not user-facing copy). Do a COLD read as this reader: adopt their goals, vocabulary, and patience. Be a harsh grader — most READMEs are a 3; 5/5 means you'd genuinely act on it and it's crisp end to end. Return ONLY:
- SCORE: x/5
- 30-second test: after the first screen only, in one sentence, what do you think this tool does — and is that right/wrong/fuzzy?
- Top 3 concrete problems — each quotes the exact line/phrase and gives a specific suggested rewrite (confusing jargon, sentences carrying too many ideas, anything that doesn't sell, formatting that hurts scanning, hype that costs trust).
- Jargon check: every word you had to stop on (harness, spec, eval, subagent, rings, recall/precision…) — is it defined in context or left guessing?
- What works — keep these, so revisions don't lose them.
- The one change that would move the score most. Quote exact text. Be useful, not polite.
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.
- 7d ago First seen · 116 lines · 113 tokens per session scan A 26f81f436a34
review-docs is a skill published in the GitHub repository zernie/vigiles (15 stars, last pushed 3d ago), licensed MIT. It adds 113 tokens to every session and 1,493 once invoked, about $0.0006 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
link-check
Verify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix.
activity-log
Query and manage the unified .aiwg/activity.log chronological record of AIWG-managed workflow operations.
mention-conventions
Display @-mention naming conventions and placement rules.
validate-metadata
Validate AIWG extension definitions against the metadata schema and report errors with field names, line numbers, and remediation hints.
eval-agent
Run evaluation tests against an agent to assess quality and archetype resistance.
hook-enable
Enable the AIWG context hook in platform context files without re-deploying.