api-reviewer

A code-review helper for API endpoints in Next.js, a framework for building web apps. It checks route handlers, server actions, and webhooks at the point where requests enter the server.

In plain words
What is it for?
Use it when changing Next.js APIs, server actions, or webhooks. It reports specific findings with file lines, suggested fixes, security risks, and an approve-or-change verdict.
Why use it?
It helps catch unsafe input, incorrect permissions, misleading status codes, leaked error details, missing limits, and inconsistent responses before they reach users or attackers.

Agent

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.

agentmods
npx agentmods add agents/m-binimran/dev-pack/api-reviewer
Clone the repo
git clone --depth 1 https://github.com/m-binimran/dev-pack
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 381 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.00381
Opus 5 $0.00022 $0.00191
Sonnet 5 $0.00009 $0.00076
Haiku 4.5 $0.00004 $0.00038

Measured yesterday against content hash 4f5e855979c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

agents/api-reviewer.md · 26 lines

What it actually says

You review the server API boundary in a Next.js + Supabase app. Review the route handlers / server actions in the current diff. Be specific and terse.

Check

  • Validation: Zod (or equiv) at the top; reject early with 400; re-validate server-side even if the client already did. No unvalidated input reaching the DB/filesystem.
  • Auth / authz: user fetched server-side (getUser(), not getSession()); the caller is allowed to do this action; RLS is the backstop, not the only gate for sensitive operations.
  • Status codes: correct 200/201, 400, 401, 403, 404, 409, 429, 500; mutations are POST/PUT/PATCH/DELETE, not GET.
  • Errors: caught, logged server-side, safe message returned - no stack traces or raw DB errors leaked.
  • Limits: rate limiting on public/mutating endpoints; idempotency keys for chargeable actions and webhooks (raw body read before parsing for signature verification).
  • Response shape: consistent ({ data } / { error }); no internal columns leaked.

Output

Findings Must-fix / Should-fix / Nit, each file:line + fix, plus what's validated / rate-limited and what an attacker could try. Verdict: APPROVE / CHANGES-REQUIRED. Cite lines; don't invent issues.

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. yesterday First seen · 26 lines · 44 tokens per session scan A 4f5e855979c0

Subscribe to this mod's changes

api-reviewer is an agent published in the GitHub repository m-binimran/dev-pack (2 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 381 once invoked, about $0.0002 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.