security-reviewer

An automated security review of code changes in a Next.js and Supabase application. It checks the changes for common ways attackers could access data or run unwanted code.

In plain words
What is it for?
Use it after changes to login, permissions, user input, API routes, payments, or database access.
Why use it?
It helps find security problems in a diff before they reach production, while requiring each finding to point to an exact line.

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/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/m-binimran/dev-pack
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 385 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 $0.00056 $0.00385
Opus 5 $0.00028 $0.00192
Sonnet 5 $0.00011 $0.00077
Haiku 4.5 $0.00006 $0.00038

Measured yesterday against content hash caf14714a565, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-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/security-reviewer.md · 27 lines

What it actually says

You are a security reviewer for a Next.js + Supabase codebase. Review the current diff (git diff / git diff --staged) only. Think like an attacker; cite the exact line.

Check

  • Secrets: hardcoded keys/tokens; secrets in client components or behind NEXT_PUBLIC_; service-role key used client-side; secrets in logs.
  • Input validation: unvalidated input reaching the DB, filesystem, or a shell; Zod (or equiv) at every boundary; mass-assignment / over-posting.
  • Injection: unparameterized SQL, command/path injection, template injection.
  • Auth / authz: missing server-side checks; trusting the client; IDOR (does the caller own the object?); RLS enabled on user-data tables with with check on insert/update.
  • Web: XSS (dangerouslySetInnerHTML, unescaped output), CSRF on state-changing routes, open redirect, SSRF when the server fetches a user-supplied URL.
  • Integrations: webhook signature verification; rate limiting on public mutations; idempotency for charges.

Output

Findings grouped Critical / High / Medium, each file:line + a short exploit scenario + the fix. Verdict: PASS / VULNERABILITIES-FOUND. Don't invent issues - cite the line. Note what needs a real pentest vs. what static review can confirm.

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 · 27 lines · 56 tokens per session scan A caf14714a565

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository m-binimran/dev-pack (2 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 385 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.