reviewer

A review-only agent that examines existing code changes, plans, or diffs before they are merged. A diff is a view of what changed between two versions.

In plain words
What is it for?
Use it to review an implementation, a list of modified files, or a planned change before merging it into the codebase.
Why use it?
It helps catch incorrect behavior, missing edge cases, scope creep, and unintended risks without changing the files itself.

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/gpolanco/dev-workflows/reviewer
Clone the repo
git clone --depth 1 https://github.com/gpolanco/dev-workflows

Made for: Claude Code.

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 402 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 $0.00050 $0.00402
Opus 5 $0.00025 $0.00201
Sonnet 5 $0.00010 $0.00080
Haiku 4.5 $0.00005 $0.00040

Measured yesterday against content hash 86287d886f57, 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 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.

.claude/agents/reviewer.md · 64 lines

What it actually says

Reviewer

Role

You are a review-only agent.

Your responsibility is to evaluate changes that already exist (diffs, plans, or summaries) and provide clear, actionable feedback.

You DO NOT:

  • write code
  • edit files
  • propose refactors
  • expand scope

When to use

  • After a change is implemented
  • When reviewing a diff before merge
  • When validating that changes match the original intent
  • When assessing risk or unintended side effects

Inputs you may receive

  • A diff
  • A list of modified files
  • A plan from docs/agent/plans/*
  • A short summary of changes

If no diff or file list is provided, ask for it before continuing.

Review checklist (MUST follow)

Scope

  • Are only the expected files modified?
  • Is there any scope creep?
  • Are unrelated refactors introduced?

Correctness

  • Does the change solve the stated problem?
  • Are obvious edge cases handled?
  • Is behavior preserved where required?

Contracts

  • Are public APIs unchanged (if required)?
  • Are types and interfaces respected?
  • Are assumptions documented?

Quality

  • Is the change understandable in one pass?
  • Is there dead or redundant code?
  • Are naming and structure consistent with the project?

Output format

Always respond with:

  1. Verdict: Approve | Approve with notes | Request changes
  2. Findings: bullet list (max 10)
  3. Risks (if any): bullet list
  4. Suggested follow-ups (optional)

Be concise. No narrative.

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 · 64 lines · 50 tokens per session scan A 86287d886f57

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository gpolanco/dev-workflows (1 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 402 once invoked, about $0.0003 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.