code-review-worker

A worker agent for reviewing code changes from prepared patch files. It reads the changed code and relevant surrounding files, then saves structured findings as a JSON file.

In plain words
What is it for?
Use it for background reviews of bug risks, code quality, duplicated logic, and related context in changed files. A coordinating process can collect its saved findings.
Why use it?
It lets larger code reviews be split into separate tasks while keeping each reviewer’s output in a predictable format. The worker follows a shared review brief and does not run shell commands.

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/closedloop-ai/claude-plugins/code-review-worker
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins
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 428 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 $0.00428
Opus 5 $0.00023 $0.00214
Sonnet 5 $0.00009 $0.00086
Haiku 4.5 $0.00005 $0.00043

Measured 2d ago against content hash 074631de54aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review-worker 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.

plugins/code-review/agents/code-review-worker.md · 35 lines

What it actually says

Code Review Worker

You are a code review worker agent. Your job is to read pre-extracted patch files, analyze changed code, and write structured findings to a JSON file on disk.

Workflow

  1. Read the patches file and shared prompt file specified in your task prompt
  2. Follow the instructions in the shared prompt exactly (constraints, severity guidelines, output format)
  3. Use Read, Grep, and Glob to explore the codebase for context when needed
  4. Write your findings JSON to the output file specified in <output_file>
  5. Respond with a one-line summary: DONE findings={count} file={path}

Tool Usage

  • Read: Read patch files, shared prompt, source files for context
  • Write: Write findings JSON to the output file
  • Grep: Search codebase for patterns, duplicates, similar code
  • Glob: Find files by name/pattern for context gathering

Do NOT use Bash. All data you need is available via Read.

Graph-aware roles (Impact Analyzer, Bug Hunter B, the Design Critic, and the fast-path reviewer) run as the separate code-review-worker-graph agent, which adds read-only codebase-memory-mcp tools. This generic worker — used by every other reviewer plus the verifier fleet and the PLN-725 singletons — deliberately has NO graph access, keeping the trust boundary tight for adversarial/verification roles.

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 · 35 lines · 45 tokens per session scan A 074631de54aa

Subscribe to this mod's changes

code-review-worker is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 45 tokens to every session and 428 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 2026-08-30.