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 bestagentkits/agency-skills --skill api-design-reviewergit clone --depth 1 https://github.com/bestagentkits/agency-skillsWrote 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/bestagentkits/agency-skills/api-design-reviewer)<a href="https://agentmods.dev/skills/bestagentkits/agency-skills/api-design-reviewer"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/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/bestagentkits/agency-skills/api-design-reviewer"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/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 | $0.00070 | $0.03069 |
| Opus 5 | $0.00035 | $0.01535 |
| Sonnet 5 | $0.00014 | $0.00614 |
| Haiku 4.5 | $0.00007 | $0.00307 |
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 12d 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.
This is a copy
89% identical to api-design-reviewer — 41 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Design Reviewer
Tier: POWERFUL
Category: Engineering / Architecture
Maintainer: Claude Skills Team
Overview
The API Design Reviewer skill provides comprehensive analysis and review of API designs, focusing on REST conventions, best practices, and industry standards. This skill helps engineering teams build consistent, maintainable, and well-designed APIs through automated linting, breaking change detection, and design scorecards.
Quick Start — run the tools first
# 1. Lint an OpenAPI/Swagger spec for convention violations
python3 scripts/api_linter.py openapi.json --format json -o lint.json
# 2. Detect breaking changes between two spec versions (gate: exits non-zero with --exit-on-breaking)
python3 scripts/breaking_change_detector.py openapi-v1.json openapi-v2.json --format json --exit-on-breaking -o breaking.json
# 3. Score overall design quality (gate: --min-grade fails below threshold)
python3 scripts/api_scorecard.py openapi.json --format json --min-grade B -o scorecard.json
Review flow: run all three, report linter findings + breaking changes + grade to the user, fix, then re-run until the linter is clean, --exit-on-breaking passes (or breaking changes are version-bumped), and the scorecard meets the agreed --min-grade. Never sign off an API review on prose alone — attach the tool outputs.
Core Capabilities
1. API Linting and Convention Analysis
- Resource Naming Conventions: Enforces kebab-case for resources, camelCase for fields
- HTTP Method Usage: Validates proper use of GET, POST, PUT, PATCH, DELETE
- URL Structure: Analyzes endpoint patterns for consistency and RESTful design
- Status Code Compliance: Ensures appropriate HTTP status codes are used
- Error Response Formats: Validates consistent error response structures
- Documentation Coverage: Checks for missing descriptions and documentation gaps
2. Breaking Change Detection
- Endpoint Removal: Detects removed or deprecated endpoints
- Response Shape Changes: Identifies modifications to response structures
- Field Removal: Tracks removed or renamed fields in API responses
- Type Changes: Catches field type modifications that could break clients
- Required Field Additions: Flags new required fields that could break existing integrations
- Status Code Changes: Detects changes to expected status codes
What ships with it
6 files 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.
- 12d ago First seen · 433 lines · 70 tokens per session scan A 660bbf3c4a59
api-design-reviewer is a skill published in the GitHub repository bestagentkits/agency-skills (11 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 3,069 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to api-design-reviewer, differing in 41 lines, and is treated as a copy.
Other skills, from other repositories
nestjs-code-review
Provides comprehensive code review capability for NestJS applications, analyzing controllers, services, modules, guards, interceptors, pipes, dependency injection, and database integration patterns. Use when reviewing NestJS code changes, before merging pull requests, after implementing new features, or for…
vanity-engineering-review
Reviews codebases, architectures, PRs, and technical plans for vanity engineering — code and systems built for the developer's ego, resume, or intellectual pleasure rather than delivering user or business value. Triggers on: "review this code", "is this over-engineered", "code review", "architecture review"…
argumentation
Construct well-structured arguments using the hypothesis-argument-example triad. Covers formulating falsifiable hypotheses, building logical arguments (deductive, inductive, analogical, evidential), providing concrete examples, and steelmanning counterarguments. Use when writing or reviewing PR descriptions that…
cross-review-project
Conduct a structured cross-project code review between two Claude Code instances via the cross-review-mcp broker. Each agent reads its own codebase, reviews the peer's code, and engages in evidence-backed dialogue — with QSG scaling laws enforcing review quality through minimum bandwidth constraints and phase-gated…
design-serialization-schema
Design serialization schemas using JSON Schema, Protocol Buffer definitions, or Apache Avro. Covers schema versioning, backwards compatibility, validation rules, and evolution strategies for long-lived data formats. Use when defining a new API contract or data interchange format, adding fields to an existing schema…
build-custom-mcp-server
Build a custom MCP (Model Context Protocol) server that exposes domain-specific tools to AI assistants. Covers server implementation in Node.js or R, tool definitions, transport configuration, and testing with Claude Code. Use when you need to expose custom functionality beyond what mcptools provides, when building…