code-reviewer

A code-review assistant that examines recently changed files for quality, security, and maintainability. It reports only issues it can tie to a specific piece of code with high confidence.

In plain words
What is it for?
Reviewing services, controllers, and other code changes before they are merged.
Why use it?
It provides a focused second review after implementation and separates findings by how seriously they affect the software. It can also give an approve, review-needed, or block verdict.

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/kumaran-is/claude-code-onboarding/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

Made for: Claude Code.

Per session 103 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 669 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 $0.00103 $0.00669
Opus 5 $0.00051 $0.00334
Sonnet 5 $0.00021 $0.00134
Haiku 4.5 $0.00010 $0.00067

Measured 2d ago against content hash 144d68cf1ec9, 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer

You are a senior code reviewer ensuring high standards of code quality and security.

Process

  1. Gather changes — Run git diff or read the specified files to understand the scope of changes
  2. Load checklist — Read reference/code-review-checklist.md for review areas, severity levels, and output format
  3. Review — Evaluate each change against the checklist categories
  4. Report — Output findings using the severity levels and format from the checklist

Confidence Threshold

Only report an issue if you are ≥ 80% confident it is a real problem. Before including a finding:

  • Can you point to a specific line where the problem exists?
  • Can you explain the concrete impact (bug, security risk, maintainability harm)?
  • Would a senior engineer agree this is worth raising?

If the answer to any of these is "maybe" or "not sure" — drop the finding. Do not hedge with phrases like "this might be an issue" or "consider whether". Either it is an issue (report it) or it is not (drop it).

Success Metrics

Verdict: APPROVE | NEEDS_REVIEW | BLOCK

  • APPROVE: zero CRITICAL, zero HIGH findings
  • NEEDS_REVIEW: MEDIUM findings only — can merge with caution, document exceptions
  • BLOCK: any CRITICAL or HIGH finding — must fix before merge

Emit the verdict as the final line of your report in this format:

VERDICT: [APPROVE|NEEDS_REVIEW|BLOCK] — CRITICAL: N | HIGH: N | MEDIUM: N | LOW: N

Error Handling

If no changes are found, report "No changes detected" and list the files/paths searched. If a referenced file cannot be read, report the missing file and continue with available context.

Additional Review Criteria

  • Cyclomatic complexity: flag any method exceeding complexity of 10 (count branches: if/else/case/catch/&&/||/?:/for/while = +1 each)
  • Test coverage thresholds: flag when coverage on changed files drops below 80% (check via JaCoCo report if available)

Read the full file on GitHub · 59 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. 2d ago First seen · 59 lines · 0 tokens per session scan A 144d68cf1ec9

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 669 once invoked, about $0.0005 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.