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 tmj-90/gaffer --skill api-design-reviewergit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/api-design-reviewer)<a href="https://agentmods.dev/skills/tmj-90/gaffer/api-design-reviewer"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/api-design-reviewer/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/tmj-90/gaffer/api-design-reviewer"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/api-design-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00090 | $0.01453 |
| Opus 5.5 | $0.00036 | $0.00581 |
| Sonnet 5.5 | $0.00018 | $0.00291 |
| Haiku 4.5 | $0.00009 | $0.00145 |
Grade A, and why
api-design-reviewer 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 22d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review APIs before they ship
An API is a contract other code depends on; a breaking change costs every client and cannot be recalled after release. Review new and changed endpoints against HTTP semantics (RFC 9110), the error format (RFC 9457), and the compatibility rules of the Google API Improvement Proposals (AIP-180) and the Microsoft REST API Guidelines. When used as a review lens, a finding blocks only when it is a concrete defect: a broken existing contract, wrong semantics a client will act on, or an AC not met. Consistency wishes on new endpoints are notes.
Steps
- Find the contract. Read the OpenAPI/proto spec diff if one exists, else the route
and handler diff. Call
search_lorefor the repo's API conventions (error envelope, pagination style, versioning, casing). A missing spec is a note, not a blocker. - List every changed operation as
METHOD path → statuses, request shape, response shape, and mark each new, changed or removed. - Check compatibility of every changed or removed operation against the breaking list below. For each break, is there a new version, a deprecation path, or an AC that explicitly asks for it? If not, it is blocking.
- Check semantics — methods, status codes, errors, pagination, idempotency and concurrency — against the checklist, for new and changed operations.
- Check tests reach the contract. Each AC about an endpoint has a test that calls it
over its real interface and asserts status and body, including the error case the AC
names (the
contract-testskill when a spec exists). - Rate and record. Blocking: an unversioned breaking change; a success status on a
failure (a client will treat an error as success); a side-effecting
GET; a documented behaviour the diff contradicts. Should-fix: wrong status on a new endpoint that clients will branch on; an error body that departs from the envelope the repo's clients already parse. Note: naming, style and other consistency wishes. As a lens, record each finding withrecord_ac_evidence(evidence_type: manual_note: operation, rule, fix) and letreview-ticketcarry the verdict; outside a Gaffer review, emit BLOCK / CONCERNS / CLEAN with file and line.
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.
- 22d ago Changed · +18 lines · +27 tokens per session 4f89fc72a51b
- 1mo ago First seen · 78 lines · 63 tokens per session scan A 8f94a72c3bef
api-design-reviewer is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 23d ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,453 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
code-review
Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
spec-drift-check
Audits a WP brief for drift against current code — extracts claims, verifies each, emits PROCEED/STOP verdict. Use when starting a new WP, before consuming a spec as binding, or when a doc references paths/lines/functions.
besimple-broccoli-blind
Non-interactive wrapper: plan-sketch -> auto-pick recommended options -> plan-write -> plan-critique-loop -> implement-from-plan -> claude-simplify-wrapper -> dedup -> code-review-loop. No PR creation and no Linear comments.
code-review-loop
Iterative review+fix loop for BASESHA..HEAD: generate findings, apply accepted fixes, run checks, commit, and re-review up to 3 iterations or until clean.
dedup
Dedupe-only pass for BASESHA..HEAD: remove duplicate code introduced by the diff or reuse existing shared utils; applies changes + commits.