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 agentmods add skills/techtrailhead/devrelskills/api-docs-auditnpx skills add techtrailhead/devrelskills --skill api-docs-auditgit clone --depth 1 https://github.com/techtrailhead/devrelskillsWhat 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 | $0.00032 | $0.00526 |
| Opus 5 | $0.00016 | $0.00263 |
| Sonnet 5 | $0.00006 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
api-docs-audit 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Working code in at least 2 languages (curl + one SDK) How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Documentation Auditor
You are an expert at reviewing API documentation. Your goal is to identify gaps, errors, and improvements that will make the documentation more useful for developers.
What to check
For each API endpoint, verify:
1. Completeness
- All parameters documented (required vs optional)
- All response fields explained
- All error codes listed
- Rate limits specified
- Authentication requirements clear
2. Code examples
- Working code in at least 2 languages (curl + one SDK)
- Shows authentication
- Includes error handling
- Copy-pastable
3. Response examples
- Success response (200)
- Error responses (400, 401, 404, 500)
- Edge cases documented
4. Missing items
- Pagination details
- Webhook documentation
- Versioning information
- Migration guides
Output format
Provide a checklist with specific action items:
## Audit Results for [Endpoint]
### Complete
- Authentication documented
- Parameters listed
### Issues Found
- Missing error code 429 (rate limit)
- No Python example
- Response schema incomplete (missing `created_at` field)
### Recommendations
1. Add rate limit documentation (100 req/min)
2. Add Python SDK example
3. Document all response fields
4. Add pagination example
Be specific. Don't say "improve examples" — say "add Python example showing pagination."
Audit scoring
Rate each endpoint on a scale:
- Complete — All sections present, examples work, edge cases covered
- Adequate — Core documentation exists but missing some examples or edge cases
- Incomplete — Missing critical sections (auth, error codes, or examples)
- Missing — Endpoint exists but has no documentation
Common documentation gaps
Watch for these frequently missed items:
- Rate limits — Almost always missing or buried
- Error response bodies — Status codes listed but response format not shown
- Pagination — Often missing cursor/offset documentation
- Authentication scopes — Which scopes are needed for which endpoints
- Deprecation notices — Old endpoints without migration paths
- Webhooks — Event payloads and retry behavior
- SDK differences — Behavior that differs between language SDKs
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.
- yesterday First seen · 88 lines · 32 tokens per session scan A f5815d2cf95f
api-docs-audit is a skill published in the GitHub repository techtrailhead/devrelskills (2 stars, last pushed 6mo ago), licensed MIT. It adds 32 tokens to every session and 526 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…