api-ref-skills

A set of coding-agent instructions for checking and repairing OpenAPI JSON files, which describe how a web API works. It provides separate checks for evaluation, review, and fixes.

In plain words
What is it for?
Use it to audit, review, lint, and repair OpenAPI files stored under `static/`, including checking their version, structure, descriptions, and examples.
Why use it?
It gives API documentation work a consistent process and helps catch structural and style problems. It also makes clear which tasks only report findings and which can edit files.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/adobedocs/ff-services-docs/api-ref-skills
Clone the repo
git clone --depth 1 https://github.com/AdobeDocs/ff-services-docs

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00326
Opus 5 $0.00000 $0.00163
Sonnet 5 $0.00000 $0.00065
Haiku 4.5 $0.00000 $0.00033

Measured 2d ago against content hash 1cecfe6fc1d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-ref-skills 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.

.cursor/rules/api-ref-skills.mdc · 22 lines

What it actually says

API spec skills (/api-eval, /api-review, /api-fix)

Agent skills for OpenAPI JSON under static/. Resolve the spec path with _shared/resolve-api-spec.mdno petstore.json default.

Command Skill Edits?
/api-eval api-eval/SKILL.md No — audit findings
/api-review api-review/SKILL.md No — description catalog tables
/api-fix api-fix/SKILL.md Yes — Redocly lint + structure fixes

Agent: api-spec-reviewer.md — runs lint + api-fix after OpenAPI edits.

Lint: npm run lint:openapi -- static/your-spec.json · npm run lint:openapi:all

FFS style guide wiki: Firefly Services API Style Guide

Changes

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.

  1. 2d ago First seen · 22 lines · 0 tokens per session scan A 1cecfe6fc1d6

Subscribe to this mod's changes

api-ref-skills is a cursor rule published in the GitHub repository AdobeDocs/ff-services-docs (4 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 326 tokens. 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.