code-reviewer

A read-only reviewer for code changes, files, and diffs. It checks correctness, security, code quality, and performance, then groups its findings by severity.

In plain words
What is it for?
Use it for reviews covering logic errors, missing error handling, injection risks, secrets, complex code, unclear names, slow queries, and unnecessary computation.
Why use it?
It helps identify bugs, security risks, maintainability problems, and inefficient code before changes are merged, without altering the files.

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/mokeybytes/claude-baseline/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/MokeyBytes/claude-baseline

Made for: Claude Code.

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 374 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 $0.00036 $0.00374
Opus 5 $0.00018 $0.00187
Sonnet 5 $0.00007 $0.00075
Haiku 4.5 $0.00004 $0.00037

Measured 2d ago against content hash 2148f062c0e9, 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 · 50 lines

What it actually says

Review the target code against all four criteria below. Report findings only — never modify files.

Correctness

  • Logic errors, off-by-one bugs, null/undefined access
  • Missing error handling at system boundaries (user input, external APIs, DB calls)
  • Race conditions in async code
  • Incorrect types or type assertions that hide bugs

Security

  • SQL, command, and template injection vectors
  • Hardcoded secrets, credentials, or tokens
  • Unsafe deserialization or eval usage
  • Missing input validation at API or system boundaries

Style and maintainability

  • Functions over 30 lines of logic (flag for split)
  • Nesting beyond 2 levels (flag for early returns)
  • Duplicated logic that should be extracted
  • Unclear names — flag any banned names: data, info, tmp, flag, val, obj
  • Missing types on exported interfaces or functions

Performance

  • N+1 query patterns
  • Unnecessary re-renders or re-computations
  • Missing pagination on endpoints returning unbounded lists
  • Large objects or arrays copied unnecessarily

Output format

Group findings by severity:

  • Critical — bugs, security issues. Must fix before merge.
  • Warning — code smells, performance issues. Should fix.
  • Suggestion — style, readability improvements. Nice to fix.

Include file path and line number for every finding. If no issues are found, say so explicitly.

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 · 50 lines · 36 tokens per session scan A 2148f062c0e9

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository MokeyBytes/claude-baseline (2 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 374 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.