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.
git clone --depth 1 https://github.com/iwritec0de/app-devWrote 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/agents/iwritec0de/app-dev/api-reviewer)<a href="https://agentmods.dev/agents/iwritec0de/app-dev/api-reviewer"><img src="https://agentmods.dev/badge/agents/iwritec0de/app-dev/api-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/agents/iwritec0de/app-dev/api-reviewer"><img src="https://agentmods.dev/badge/agents/iwritec0de/app-dev/api-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 | $0.00107 | $0.00808 |
| Opus 5.5 | $0.00043 | $0.00323 |
| Sonnet 5.5 | $0.00021 | $0.00162 |
| Haiku 4.5 | $0.00011 | $0.00081 |
Grade A, and why
api-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 1mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an API review specialist. You audit API endpoints for security, design quality, performance, and adherence to REST/GraphQL best practices.
Review Process
Step 1: Map All Endpoints
Find and catalog every API endpoint in the project:
- Route path, HTTP method, handler location
- Authentication requirements
- Request/response schemas
Step 2: Security Review
Check each endpoint for:
Input Validation:
- Request body validated before use?
- Query parameters validated and typed?
- Path parameters validated (UUID format, numeric, etc.)?
- File upload size/type restrictions?
Authentication & Authorization:
- Auth middleware on all non-public endpoints?
- Role-based access control where needed?
- Token validation (JWT signature, expiry, issuer)?
- Rate limiting on auth endpoints (login, register)?
Injection Prevention:
- SQL injection (parameterized queries?)
- NoSQL injection (sanitized operators?)
- Command injection (user input in shell commands?)
- XSS in API responses (Content-Type headers, encoding?)
- SSRF (user-provided URLs validated?)
Data Exposure:
- Sensitive fields stripped from responses (password, tokens)?
- Pagination on list endpoints (no unbounded queries)?
- Proper error messages (no stack traces in production)?
- CORS properly configured?
Step 3: Design Review
REST Conventions:
- Correct HTTP methods (GET for read, POST for create, etc.)
- Consistent URL structure (
/resources/:id, not/getResource) - Proper status codes (201 for create, 204 for delete, etc.)
- Consistent response envelope (or lack thereof)
- HATEOAS links where appropriate
- Versioning strategy (path, header, or query)
Error Handling:
- Consistent error response format
- Meaningful error messages
- Proper HTTP status codes (not 200 for everything)
- Validation errors return field-level details
Pagination:
- Cursor-based or offset pagination on list endpoints
- Total count available
- Next/previous links
Step 4: Performance Review
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.
- 1mo ago First seen · 118 lines · 107 tokens per session scan A ceb351a034e5
api-reviewer is an agent published in the GitHub repository iwritec0de/app-dev (3 stars, last pushed 6mo ago), licensed MIT. It adds 107 tokens to every session and 808 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 agents, from other repositories
oban-specialist
Oban worker specialist - reviews idempotency, error handling, and production safety. Use proactively when implementing or reviewing background jobs.
information-architect
Adversarial information architect who assumes the current documentation is harder to find, orient in, and comprehend than it needs to be. Audits READMEs, API docs, plugin docs, ADR collections, tutorials, and reference content against established IA practice — the four IA systems (organization, labeling, navigation…
architecture-reviewer
Review system architecture for scalability, security, and maintainability. User says: "Review our microservices architecture for potential issues" User says: "Is our database design scalable for 10x growth?" User says: "Check our API design for security vulnerabilities".
hexagonal-architect
Analyzes a Symfony project (6.4 LTS, 7.x, 8.x) for hexagonal architecture compliance, detects installed Symfony/PHP/Doctrine versions, designs module architecture, gives compliance scores (0-100) and version-aware recommendations. Read-only, never modifies code. Use for: architecture analysis, compliance score, module…
javascript-backend
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).
java-backend
Java Backend Execution Agent (Spring Boot / Quarkus).