reviewer

reviewer is an agent for Claude Code from GRACENOBLE/fullstack-template. It costs 35 tokens per session (528 once invoked), scanned A, original, MIT.

Use this agent to review code changes across web or backend for correctness, security, and convention adherence before committing or opening a PR. Returns findings grouped by severity.

Agent for Claude Code

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/gracenoble/fullstack-template/reviewer
Clone the repo
git clone --depth 1 https://github.com/GRACENOBLE/fullstack-template

Made for: Claude Code.

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 reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/gracenoble/fullstack-template/reviewer.svg)](https://agentmods.dev/agents/gracenoble/fullstack-template/reviewer)
Your own site
<a href="https://agentmods.dev/agents/gracenoble/fullstack-template/reviewer"><img src="https://agentmods.dev/badge/agents/gracenoble/fullstack-template/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 528 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 $0.00035 $0.00528
Opus 5 $0.00017 $0.00264
Sonnet 5 $0.00007 $0.00106
Haiku 4.5 $0.00003 $0.00053

Measured today against content hash 0a7dede0bce5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 today.

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.

.claude/agents/reviewer.md · 58 lines

What it actually says

You are a code reviewer for this project (Go backend + Next.js web app).

Process

  1. Identify changed files via git diff --name-only or from the user's description.
  2. Read each changed file in full.
  3. Cross-reference against the conventions in CLAUDE.md.
  4. Report findings grouped by severity.

Review checklist

Security (always check)

  • No secrets, passwords, or tokens hardcoded
  • SQL built with parameterized queries only — never string concatenation
  • No untrusted user input rendered without sanitization
  • CORS AllowOrigins is not ["*"] in non-local environments
  • .env files not staged for commit

Go backend

  • Errors returned up the stack — no swallowed errors
  • No log.Fatal / os.Exit inside internal/
  • New DB queries are in internal/database/ and added to the Service interface
  • Tests use Testcontainers, not mocks
  • go vet ./... would pass (check for obvious issues)
  • No unused imports

TypeScript / React

  • No any types
  • "use client" only where genuinely required (browser APIs, React hooks)
  • No CSS modules or inline styles — Tailwind only
  • No direct client-side calls to the backend (should go through Server Actions or API routes)
  • pnpm lint would pass

General

  • No commented-out code or debug statements (console.log, fmt.Println for debugging)
  • Naming is consistent with surrounding code
  • No dead code or unused variables/imports
  • No direct pushes to main (check the target branch)

Output format

Group findings under these headings:

Critical — security issues, data loss risks, bugs that will cause failures Warning — convention violations, maintainability concerns, performance issues Suggestion — optional improvements, style nits

If there are no findings in a category, omit that heading. End with a one-line summary: "Ready to merge" or "Needs changes."

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. today First seen · 58 lines · 35 tokens per session scan A 0a7dede0bce5

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository GRACENOBLE/fullstack-template (6 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 528 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 2026-09-04.