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 willdady/platypus --skill docs-auditgit clone --depth 1 https://github.com/willdady/platypusWrote 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/willdady/platypus/docs-audit)<a href="https://agentmods.dev/skills/willdady/platypus/docs-audit"><img src="https://agentmods.dev/badge/skills/willdady/platypus/docs-audit/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/willdady/platypus/docs-audit"><img src="https://agentmods.dev/badge/skills/willdady/platypus/docs-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00032 | $0.01105 |
| Opus 5.5 | $0.00013 | $0.00442 |
| Sonnet 5.5 | $0.00006 | $0.00221 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
docs-audit 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit one section of apps/docs/content against the source, and report every
claim that no longer holds.
apps/docs/content/docs-contract.test.ts already pins the claims with exactly
one authoritative source — env tables, webhook events, core Plugin names, field
limits, internal links, heading anchors. Assume those are green and do not
re-check them. Your job is everything that needs judgement, above all the ~150
bolded UI labels across building-with-platypus/, which nothing can see.
Never answer from memory. Every verdict cites a file and a line in the code. A claim you did not open the source for is a claim you did not check.
Step 1 — Pick the section and build the suspect pool
Audit one section per run — one top-level directory of the docs content. List what is actually there rather than working from a remembered set, so a section added since cannot be the one you never audit. Ask the user which if they did not say.
Find when the section was last touched, then list what changed in the code since:
git log -1 --format=%H -- apps/docs/content/<section>
git log <that-sha>..HEAD --oneline -- apps/backend apps/frontend packages/schemas
Drift concentrates where code moved and docs did not, so read that commit list before you read the pages — it tells you which claims to distrust.
Done when: you have the section, the last-touch SHA, and the commit list.
Step 2 — List every claim
Read each page in the section in full. Then write out every falsifiable
claim it makes, each with its file:line.
A claim is anything a reader could act on and find wrong: a UI label, a field name, a menu path, a default, a limit, an ordering, a behaviour, a "this requires that", a "you cannot do X".
List every claim, not a sample. Coverage has to be a property of the procedure, because it will not be a property of your attention. A page with sixty claims produces sixty rows.
Done when: every page in the section has been read end to end and every claim is on the list with a line number.
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.
- 10d ago Changed 13aeca52a707
- 1mo ago First seen · 108 lines · 32 tokens per session scan A 9e8c3255bddf
docs-audit is a skill published in the GitHub repository willdady/platypus (120 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,105 once invoked, about $0.0001 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 2026-09-01.
Other skills, from other repositories
community-research-insight
Extract structured insight briefs from community research transcripts or notes. Produces pain points, stakeholder needs, opportunity maps, risks, and follow-up questions. Requires human review before publication.
openclaw-github-dedupe
Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.
openclaw-pr-batch-sweep
Select, review, repair, validate, and land batches of up to 20 low-risk OpenClaw contributor pull requests using Vincent's maintainer preferences and bounded sub-agent lanes. Use for "next 20", broad contributor PR sweeps, merge-candidate mining, or continued PR-batch work where drafts, maintainer work, trivial…
semantic-slicing
Build local semantic review slices by combining clawpatch feature maps, deepsec threat candidates, visual review maps, and optional gitcrawl/discrawl evidence for repos such as openclaw/openclaw.
github-code-review
Review code changes by analyzing git diffs, leaving inline comments on PRs, and performing thorough pre-push review. Works with gh CLI or falls back to git + GitHub REST API via curl.
gh-address-comments
This skill should be used when addressing GitHub pull request review comments systematically with mandatory resolution tracking. Use when user says "address PR comments", "fix review feedback", "handle PR review", "resolve PR threads", or needs to ensure all review comments are addressed before merging. Fetches…