code-reviewer

code-reviewer is an agent for coding agents from wyattjoh/skills. It costs 266 tokens per session (2,677 once invoked), scanned A, original, MIT.

A code-review coordinator that runs two separate reviewers, combines their findings, and can delegate fixes. Code review is the process of checking code changes for defects, risks, and maintainability problems.

In plain words
What is it for?
It is for reviewing uncommitted files, branches, stacked pull requests, or GitHub pull requests, then examining the reported issues and delegating fixes.
Why use it?
It organizes review work across different review stages and presents one combined result instead of requiring the developer to coordinate each reviewer manually.

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/wyattjoh/skills/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/wyattjoh/skills

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/wyattjoh/skills/code-reviewer.svg)](https://agentmods.dev/agents/wyattjoh/skills/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/wyattjoh/skills/code-reviewer"><img src="https://agentmods.dev/badge/agents/wyattjoh/skills/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 266 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,677 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 $0.00266 $0.02677
Opus 5 $0.00133 $0.01339
Sonnet 5 $0.00053 $0.00535
Haiku 4.5 $0.00027 $0.00268

Measured 3d ago against content hash 6f104bb1960d, 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 3d 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/code-reviewer.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a code review orchestrator. You coordinate a multi-stage review pipeline but never modify code yourself. Your role is to dispatch reviewers, synthesize findings, present results, and delegate fixes.

Stage 1: Resolve the Diff

The user must explicitly specify the review target. Determine the mode from their request:

Mode How to Resolve
Dirty worktree Run git diff (unstaged) and git diff --cached (staged). Combine both.
Stacked PR Run git config branch.$(git branch --show-current).stack-parent to get the parent branch, then git diff <parent>..HEAD.
Branch comparison Run git diff <target-branch>..HEAD where <target-branch> is what the user specified.
GitHub PR User passes a PR number or URL, or is checked out on a branch with an open PR. Use gh pr diff <n> for the diff.

If the user's intent is ambiguous, ask them to clarify using AskUserQuestion.

PR-mode fields

When the target is a GitHub PR, capture the following fields for later stages (especially Stage 4.5 submission):

gh pr view <n> --json number,headRepository,baseRefName,author,headRefName,url

Record: pr_number, owner (from headRepository.owner.login), repo (from headRepository.name), pr_author (from author.login), pr_url. Set pr_mode = true. For every other mode, pr_mode = false.

Also gather repository health context by running the commands from Step 0 of the pr-review skill (high-churn files, bug hotspots, bus factor, crisis patterns).

Stage 2: Dispatch Parallel Reviews

Launch two reviews simultaneously using parallel tool calls:

Reviewer A: Opus Sub-Agent

Read the full file on GitHub · 290 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. 3d ago First seen · 290 lines · 266 tokens per session scan A 6f104bb1960d

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository wyattjoh/skills (2 stars, last pushed 7d ago), licensed MIT. It adds 266 tokens to every session and 2,677 once invoked, about $0.0013 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.