api-design-reviewer

api-design-reviewer is a skill for Claude Code, Codex from tmj-90/gaffer. It costs 63 tokens per session (915 once invoked), scanned A, original, Apache-2.0.

A review process for web APIs, the interfaces through which software exchanges requests and responses. It checks resource names, HTTP methods, status codes, versioning, and changes that could break clients.

In plain words
What is it for?
Use it to review REST endpoints, check an API before a version-two migration, assess OpenAPI documentation, or identify breaking changes.
Why use it?
It finds inconsistent design and compatibility problems before other applications depend on them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review REST endpoints, check an API before a version-two migration, assess OpenAPI documentation, or identify breaking changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tmj-90/gaffer/api-design-reviewer
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.

Any agent
npx skills add tmj-90/gaffer --skill api-design-reviewer
Clone the repo
git clone --depth 1 https://github.com/tmj-90/gaffer

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for api-design-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/tmj-90/gaffer/api-design-reviewer.svg)](https://agentmods.dev/skills/tmj-90/gaffer/api-design-reviewer)
Your own site
<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>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 915 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00063 $0.00915
Opus 5 $0.00032 $0.00458
Sonnet 5 $0.00013 $0.00183
Haiku 4.5 $0.00006 $0.00092

Measured 7d ago against content hash 8f94a72c3bef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

runner/skills/api-design-reviewer/SKILL.md · 78 lines

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 (not GET /activateUser)

HTTP method semantics:

  • GET — read; must be idempotent; no side effects
  • POST — create or action; not idempotent
  • PUT — replace the whole resource; idempotent
  • PATCH — partial update; idempotent
  • DELETE — 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

  1. 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.
  2. Check resource naming. Plural nouns, no verbs in paths (except for actions), consistent casing.
  3. Check HTTP method usage. Every GET must be safe and idempotent. POST for creates and non-idempotent actions only.
  4. Check status codes. Map every response to the correct 2xx/4xx/5xx. 200 for errors is an automatic BLOCK.
  5. Check for breaking changes. Diff against the previous spec/version. List every breaking change and verify it's covered by a version bump.
  6. Check error format. Consistent envelope: { "error": { "code": "...", "message": "...", "details": [...] } } — not ad-hoc per endpoint.
  7. 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.
  8. Emit verdict. BLOCK / CONCERNS / CLEAN with file/line evidence for each finding.

Read the full file on GitHub · 78 lines

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. 7d ago First seen · 78 lines · 63 tokens per session scan A 8f94a72c3bef

Subscribe to this mod's changes

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.

Related

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.

QBall-Inc/the-bulwark · 61 tokens

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.

QBall-Inc/the-bulwark · 0 tokens

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.

QBall-Inc/the-bulwark · 54 tokens

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.

besimple-oss/broccoli · 58 tokens

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.

besimple-oss/broccoli · 40 tokens

dedup

Dedupe-only pass for BASESHA..HEAD: remove duplicate code introduced by the diff or reuse existing shared utils; applies changes + commits.

besimple-oss/broccoli · 32 tokens