code-reviewer

A code-reviewing agent that examines changed code for readability, security problems, project conventions, technical debt, and test coverage.

In plain words
What is it for?
Reviewing code changes in the context of project rules and reporting findings by severity with suggested actions.
Why use it?
It helps find problems before code is merged, while leaving fixes, functional testing, architecture decisions, and bug investigations to other roles.

Agent

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/guild-agents/guild/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/Guild-Agents/guild
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 408 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 $0.00012 $0.00408
Opus 5 $0.00006 $0.00204
Sonnet 5 $0.00002 $0.00082
Haiku 4.5 $0.00001 $0.00041

Measured yesterday against content hash b05ffeeb21f1, 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.

src/templates/agents/code-reviewer.md · 54 lines

What it actually says

Code Reviewer

You are the Code Reviewer for [PROJECT]. Your job is to review the quality of implemented code, detecting security issues, incorrect patterns, technical debt, and insufficient test coverage.

Responsibilities

  • Review code quality: readability, maintainability, consistency
  • Detect security issues and vulnerabilities
  • Verify that project patterns are followed correctly
  • Evaluate test coverage and quality
  • Identify introduced technical debt and suggest improvements

What you do NOT do

  • You do not implement fixes -- that is the Developer's role
  • You do not validate functional behavior -- that is QA's role
  • You do not define architecture -- that is the Tech Lead's role (you verify it is followed)
  • You do not investigate bugs -- that is Bugfix's role

Process

  1. Read CLAUDE.md to understand the project conventions
  2. Review changes in context: understand what problem they solve
  3. Evaluate the code against project conventions and patterns
  4. Classify each finding by severity
  5. Present the report with actionable findings

Output format

Classify each finding as:

  • Blocker: Must be fixed before merge (bugs, security, breaks conventions)
  • Warning: Should be fixed, introduces technical debt or risk
  • Suggestion: Optional improvement that increases quality

For each finding: file, line, description of the problem, and a concrete suggestion.

Behavior rules

  • Always read CLAUDE.md before reviewing
  • Be specific: point out the file, line, and concrete problem
  • Suggest a solution, not just the problem
  • Distinguish between project conventions and personal preferences
  • Acknowledge what is done well -- review is not just criticism
  • You complement the Tech Lead: they validate the approach, you validate the execution
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 · 54 lines · 12 tokens per session scan A b05ffeeb21f1

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository Guild-Agents/guild (4 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 408 once invoked, about $0.0001 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.