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/adobedocs/ff-services-docs/api-evalnpx skills add AdobeDocs/ff-services-docs --skill api-evalgit clone --depth 1 https://github.com/AdobeDocs/ff-services-docsWhat 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 | $0.00055 | $0.00681 |
| Opus 5 | $0.00028 | $0.00341 |
| Sonnet 5 | $0.00011 | $0.00136 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
api-eval 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 2d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/api-eval — Audit OpenAPI spec
When to run
- User invokes
/api-eval, "evaluate API spec", or "audit OpenAPI". - Do not edit files. Findings only.
Steps
-
Resolve target spec — Follow _shared/resolve-api-spec.md. Print
**Target spec:** \path`` in the output header. -
Layer 1 — Redocly lint — Run:
npm run lint:openapi -- <resolved-path>List every error/warning with path/line. Tag each as
api-fix-eligible(→ fix with /api-fix). -
Layer 2 — Structure — Load api-ref-structure.mdc. Flag section order, missing license, broken
$ref, duplicate schema names. Tag asapi-fix-eligible. -
Layer 3 — OpenAPI version — Read
openapifield. Audit 3.0 vs 3.1 rules per api-ref-schema.mdc ($ref, type arrays, anyOf/null). Flag issues lint may miss. -
Layer 4 — FFS style guide — Load api-ref-ffs-styleguide.mdc and ffs-styleguide-checklist.md. Flag significant contract inconsistencies only.
-
Layer 5 — Documentation — Load
api-ref-copy,api-ref-examples,api-ref-tags-errors. Check descriptions, examples, tags, public-facing text (no Jira/FFENT/codenames). -
Output format
- Summary — counts by layer and severity
- Redocly lint — numbered list (
api-fix-eligible) - Structure — numbered list (
api-fix-eligible) - OpenAPI version — findings
- FFS style guide — findings (wiki section if helpful)
- Documentation / copy — findings; suggest
/api-reviewfor full catalog - Reminder:
/api-fix= lint +api-ref-structure; copy/style =/api-revieworupdate refs N,M,…
Severity
- error — lint / invalid OpenAPI
- high — style guide or public-facing text violation
- medium — doc/copy inconsistency
- low — suggestion
Review completion checklist
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.
- 2d ago First seen · 55 lines · 55 tokens per session scan A ae25b1c650b6
api-eval is a skill published in the GitHub repository AdobeDocs/ff-services-docs (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 681 once invoked, about $0.0003 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
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…