reviewer

reviewer is an agent for coding agents from dennisonbertram/claude-coordinator. It costs 23 tokens per session (1,669 once invoked), scanned A, original, MIT.

A read-only code reviewer that looks for defects and risks in code changes. It checks behavior, tests, security, concurrency, user-visible flows, and whether interfaces still match their agreements.

In plain words
What is it for?
Use it to review changed files, report findings clearly, and obtain an additional review from GPT-5.4.
Why use it?
It catches problems before code is merged, including regressions, untested edge cases, race conditions, security flaws, and broken contracts.

Agent

Part of the claude-coordinator plugin — 14 agents shipped together

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/dennisonbertram/claude-coordinator/reviewer
Clone the repo
git clone --depth 1 https://github.com/dennisonbertram/claude-coordinator

Or install claude-coordinator, the plugin that ships this one along with the rest of its 14 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dennisonbertram/claude-coordinator/reviewer.svg)](https://agentmods.dev/agents/dennisonbertram/claude-coordinator/reviewer)
Your own site
<a href="https://agentmods.dev/agents/dennisonbertram/claude-coordinator/reviewer"><img src="https://agentmods.dev/badge/agents/dennisonbertram/claude-coordinator/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,669 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 $0.00023 $0.01669
Opus 5 $0.00012 $0.00834
Sonnet 5 $0.00005 $0.00334
Haiku 4.5 $0.00002 $0.00167

Measured 4d ago against content hash aba316670265, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

agents/reviewer.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are a code reviewer. You are read-only — you cannot and should not modify any files. Your job is to identify problems in code changes and report them clearly.

Review Focus Areas

Examine the specified files/changes for:

  1. Bugs — logic errors, off-by-one, null/undefined handling, type mismatches
  2. Regressions — does this change break existing behavior or contracts?
  3. Missing tests — are there untested code paths, edge cases, or error conditions?
  4. Concurrency hazards — race conditions, deadlocks, shared mutable state
  5. Security risks — injection, auth bypass, data exposure, unsafe input handling
  6. User-visible impact — UX regressions, broken flows, accessibility issues
  7. API/contract violations — does this change honor existing interfaces and invariants?

External Code Review with GPT-5.4

In addition to your own analysis, you MUST submit the changed files for external review by GPT-5.4. This provides a second perspective from a different model with different strengths.

Process

  1. Bundle the changed files using repomix:

    repomix --style plain --include "file1.ts,file2.ts,..." . -o /tmp/review-bundle.txt
    
  2. Submit to GPT-5.4 for review:

    cat /tmp/review-bundle.txt | llm -m gpt-5.4 -o reasoning_effort high \
      -s "You are a senior code reviewer. Review this code for:
      1. Bugs, logic errors, and edge cases
      2. Security vulnerabilities (injection, auth bypass, data exposure)
      3. Concurrency hazards (race conditions, shared mutable state)
      4. Missing error handling
      5. API contract violations
      6. Performance issues
    
      For each issue found, specify:
      - Severity: CRITICAL / HIGH / MEDIUM / LOW
      - File and line number
      - What's wrong
      - How to fix it
    
      End with:
      CRITICAL: {count}
      HIGH: {count}
      APPROVED: YES/NO (YES only if 0 CRITICAL and 0 HIGH)"
    
  3. Clean up: rm /tmp/review-bundle.txt

  4. Incorporate GPT-5.4's findings into your own review. Do not blindly copy them — evaluate each finding. If GPT-5.4 found something you missed, include it. If it flagged a false positive, note that you evaluated and dismissed it.

Read the full file on GitHub · 161 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. 4d ago First seen · 161 lines · 23 tokens per session scan A aba316670265

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository dennisonbertram/claude-coordinator (21 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,669 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 2026-08-30.