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.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00915 |
| Opus 5 | $0.00032 | $0.00458 |
| Sonnet 5 | $0.00013 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
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 7d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review APIs before they ship
Catch inconsistent conventions, missing versioning, and design smells before APIs are consumed by clients. Breaking changes are permanent costs — find them in review, not after release.
REST design principles
Resource naming:
- Collections: plural nouns (
/users,/orders) - Instances:
/{id}(singular, no verb) - Actions that don't fit:
POST /users/{id}/activate(notGET /activateUser)
HTTP method semantics:
GET— read; must be idempotent; no side effectsPOST— create or action; not idempotentPUT— replace the whole resource; idempotentPATCH— partial update; idempotentDELETE— remove; idempotent
Status codes — common wrong choices:
| Situation | Wrong | Right |
|---|---|---|
| Resource not found | 200 with {error} body |
404 |
| Validation failure | 500 | 400 with error detail |
| Auth failure | 404 (hiding resource) | 401 (unauthenticated) or 403 (unauthorised) |
| Created resource | 200 | 201 with Location header |
| Async accepted | 200 | 202 |
Breaking change detection
These changes break existing clients and require a version bump:
- Remove an endpoint
- Remove or rename a required field
- Change a field's type
- Add a required field to a request body
- Change a status code a client depends on
- Change pagination semantics
These are safe (backward-compatible):
- Add a new optional field to a response
- Add a new endpoint
- Add a new optional query parameter
Steps
- Read the OpenAPI spec or code diff. If no spec exists, note the missing spec as a CONCERN and continue reviewing the code that exists — don't block the review on a spec that isn't there.
- Check resource naming. Plural nouns, no verbs in paths (except for actions), consistent casing.
- Check HTTP method usage. Every
GETmust be safe and idempotent.POSTfor creates and non-idempotent actions only. - Check status codes. Map every response to the correct 2xx/4xx/5xx. 200 for errors is an automatic BLOCK.
- Check for breaking changes. Diff against the previous spec/version. List every breaking change and verify it's covered by a version bump.
- Check error format. Consistent envelope:
{ "error": { "code": "...", "message": "...", "details": [...] } }— not ad-hoc per endpoint. - Check versioning. Is the versioning strategy documented — a version prefix (
/v1/), header-based versioning, or a deliberate no-version choice? A documented no-version API is fine; only an undocumented or contradictory strategy is a finding. - Emit verdict. BLOCK / CONCERNS / CLEAN with file/line evidence for each finding.
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.
- 7d 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 7d ago), licensed Apache-2.0. It adds 63 tokens to every session and 915 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
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.