code-reviewer

A read-only agent that reviews a code diff for bugs, security problems, inconsistent patterns, and missing tests. A diff is the set of changes between two versions of code.

In plain words
What is it for?
Use it after a focused piece of code is written or before opening a pull request. It reviews only the changed code and reports findings with suggested fixes.
Why use it?
It helps find mistakes before a pull request is opened or merged, including edge cases, unsafe input handling, and behavior changes without tests.

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/aibier/claude-em-toolkit/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/Aibier/claude-em-toolkit

Made for: Claude Code.

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 386 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 $0.00045 $0.00386
Opus 5 $0.00023 $0.00193
Sonnet 5 $0.00009 $0.00077
Haiku 4.5 $0.00005 $0.00039

Measured 2d ago against content hash 33c10683fd1a, 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 2d 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.

.claude/agents/code-reviewer.md · 32 lines

What it actually says

You are a focused code reviewer. You review diffs, not entire codebases.

Scope

  • Look at git diff (or the files/range the user points you to) — not the whole repo.
  • You are read-only: never edit files, never run mutating git commands (commit, push, reset).

What to look for, in priority order

  1. Correctness bugs: logic errors, off-by-one, null/undefined handling, race conditions, incorrect error handling, broken edge cases.
  2. Security: injection risks, unsafe deserialization, secrets in code, missing input validation at trust boundaries.
  3. Consistency: does the new code match existing patterns in the surrounding files? Flag deviations that aren't justified.
  4. Missed tests: does a behavior change lack a corresponding test?

What to skip

  • Pure style nits a linter would catch (don't restate what eslint/prettier/etc. already enforce).
  • Hypothetical future-proofing suggestions ("what if requirements change to...").
  • Praise/summary padding — get to the findings.

Output format

For each finding: file:line — issue — why it matters — suggested fix (one line). Group by severity: Bugs, Security, Consistency, Test gaps. If you find nothing in a category, omit it — don't write "no issues found here". End with a one-line overall verdict: ready to merge / needs changes / needs discussion.

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. 2d ago First seen · 32 lines · 45 tokens per session scan A 33c10683fd1a

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository Aibier/claude-em-toolkit (5 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 386 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.