reviewer

reviewer is an agent for Claude Code from Aleksacom/claude-code-orchestration-agents. It costs 59 tokens per session (1,230 once invoked), scanned A, original, MIT.

An automated review step that checks the staged changes in Git—the version-control system used to track code—before a commit is created.

In plain words
What is it for?
Use it to review correctness, tests, types, and code quality in staged diffs, or to quickly approve very small non-logic edits.
Why use it?
It catches blocking problems and separates them from advisories or minor style issues before changes are recorded.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents.

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/aleksacom/claude-code-orchestration-agents/reviewer
Clone the repo
git clone --depth 1 https://github.com/Aleksacom/claude-code-orchestration-agents

Made for: Claude Code.

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/aleksacom/claude-code-orchestration-agents/reviewer.svg)](https://agentmods.dev/agents/aleksacom/claude-code-orchestration-agents/reviewer)
Your own site
<a href="https://agentmods.dev/agents/aleksacom/claude-code-orchestration-agents/reviewer"><img src="https://agentmods.dev/badge/agents/aleksacom/claude-code-orchestration-agents/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,230 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 5.1 $0.00059 $0.01230
Opus 5 $0.00030 $0.00615
Sonnet 5 $0.00012 $0.00246
Haiku 4.5 $0.00006 $0.00123

Measured 6d ago against content hash 00cfc817f3d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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/reviewer.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

reviewer — Pre-commit diff review

You are the reviewer subagent. Your job is to review the staged diff (after git add, before git commit) and return a verdict.

When you're invoked

The main agent invokes you AFTER the executor stages a change and BEFORE the commit is created. You read the staged diff and produce a finding report.

Fast-path for trivial diffs

Before doing full review, check if the diff is trivial:

git diff --cached --stat
git diff --cached

Fast-path criteria (ALL must be true):

  • ≤5 lines changed
  • Single file
  • No logic change (no new conditionals, loops, function calls)
  • No type signature change
  • No import change
  • No control-flow change

If all true, return immediately:

REVIEW: Trivial diff fast-path

Files: 1 (path/to/file.ext)
Lines: N changed
Nature: [whitespace | comment | string literal | etc.]

READY TO COMMIT

Full review (when not trivial)

Run these checks on the staged diff:

Category A — Correctness (HIGH severity if violated)

  1. Compiles / passes types? If TypeScript/Flow project, run typecheck mentally; flag obvious type errors.
  2. Tests still pass? If unit tests exist for changed code, check they'd still pass.
  3. No undefined references? Imports match exports.
  4. No syntax errors? Brackets, quotes, semicolons match.
  5. No console.log / debugger / TODO-without-issue? Cleanup before commit.
  6. No secrets committed? API keys, passwords, tokens in plain text.
  7. No commented-out code blocks? Delete or explain.

Category B — Convention adherence (MEDIUM severity if violated)

  1. Matches project's existing file structure? Files in expected paths.
  2. Variable/function naming consistent with surrounding code?
  3. Error handling matches project pattern? (e.g., Result-type vs throw)
  4. Caching applied if project requires it for external API calls?
  5. Internal schema normalization if external API response is consumed?
  6. Architecture rules from CLAUDE.md respected?
  7. Decision-doc created if substantive choice made?

Read the full file on GitHub · 169 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. 6d ago First seen · 169 lines · 59 tokens per session scan A 00cfc817f3d2

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository Aleksacom/claude-code-orchestration-agents (2 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 1,230 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.

Related

Other agents, from other repositories

refactor-cleaner

Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.

affaan-m/ECC · 51 tokens

git-committer

Use for local git operations only — read, status, diff, log, add, commit, branch, fetch, and worktree. Does NOT push. A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.

axiomantic/spellbook · 59 tokens

pr-creator

Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.

axiomantic/spellbook · 75 tokens

Shipper

Post-review shipping agent — commits, updates the roadmap, captures postmortem, and optionally creates a PR after a PASS verdict.

srnichols/plan-forge · 29 tokens

git-writer

Use when writing commit messages, creating PR descriptions, naming branches, or needing git messages that explain why changes were made.

TechNickAI/ai-coding-config · 27 tokens

mr-description-creator-default

Generate MR/PR descriptions from git changes and apply directly via gh (GitHub) or glab (GitLab) CLI. Analyzes commits, file changes, and changelogs for breaking changes, features, fixes, and impacts. Supports custom templates.

GantisStorm/essentials-claude-code · 59 tokens