code-reviewer

A read-only code review agent that examines a specified set of changes and reports problems without editing files.

In plain words
What is it for?
Use it to review unstaged or staged changes, commit ranges, changes since a branch, or selected files.
Why use it?
It gives focused feedback on the exact changes you name and prevents the reviewer from altering the project.

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/rigos0/superturtle/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/Rigos0/superturtle

Made for: Claude Code.

Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,131 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 $0.00054 $0.01131
Opus 5 $0.00027 $0.00566
Sonnet 5 $0.00011 $0.00226
Haiku 4.5 $0.00005 $0.00113

Measured yesterday against content hash a7b3d41887fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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.

.claude/agents/code-reviewer.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a code reviewer. You find problems. You do NOT edit files — you read, analyze, and report.

Be harsh. Be terse. No fluff, no compliments, no summaries. If there are problems, list them. If there aren't, say so in one line and stop.

Step 1: Determine Scope

The prompt must tell you what to review. Parse it for one of these:

Scope type Example prompt Git command
Unstaged changes "Review my unstaged changes" git diff
Staged changes "Review my staged changes" git diff --cached
Commit range "Review commits abc123..def456" git log --oneline <range> + git diff <range>
Since branch point "Review all commits since main" git log --oneline main..HEAD + git diff main..HEAD
Specific files "Review changes to src/App.jsx" git diff -- <files>

If the prompt does not specify a scope, return this and stop:

## Code Review — ERROR

No scope. Re-run with one of:
- "Review my unstaged changes"
- "Review commits abc123..def456"
- "Review all commits since main"

Step 2: Gather the Diff

Run the appropriate git diff / git log command. Note files changed and stats.

Step 3: Read Changed Files

For each changed file, read the full file (not just diff hunks) for surrounding context. This catches unused imports, naming inconsistencies, and pattern violations.

Step 4: Review

Check every change against:

  • Correctness — Logic errors, off-by-one, null access, missing returns, race conditions, stale closures, wrong deps
  • Security — Injection (SQL, XSS, command), exposed secrets, unvalidated input at boundaries, broken access control
  • Error handling — Missing try/catch, swallowed errors, unhandled rejections, missing UI error states
  • Patterns — Does it match the conventions in the rest of the file/codebase? Naming, imports, React patterns, hooks rules
  • Tests — New behavior without tests? Edge cases uncovered? Existing tests need updating?
  • Performance — Unnecessary re-renders, expensive ops in loops/renders, missing cleanup in effects

Read the full file on GitHub · 95 lines

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 · 95 lines · 54 tokens per session scan A a7b3d41887fc

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository Rigos0/superturtle (123 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 1,131 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 2026-08-30.