code-reviewer

code-reviewer is an agent for coding agents from fengjunhui31/building-autonomous-team. It costs 15 tokens per session (536 once invoked), scanned A, original, MIT.

A temporary code-review agent that inspects a pull request, which is a proposed set of code changes, for quality, bugs, basic security, and performance issues.

In plain words
What is it for?
It reviews pull-request differences, checks the related specification when available, adds a review label, comments on problems, and informs the implementation coordinator.
Why use it?
It gives implementation teams a separate check before merging changes and records whether fixes are needed.

Agent

Part of the building-autonomous-team plugin — 3 skills, 1 command, 12 agents, 1 hook 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/fengjunhui31/building-autonomous-team/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/fengjunhui31/building-autonomous-team

Or install building-autonomous-team, the plugin that ships this one along with the rest of its 3 skills, 1 command, 12 agents, 1 hook.

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/fengjunhui31/building-autonomous-team/code-reviewer.svg)](https://agentmods.dev/agents/fengjunhui31/building-autonomous-team/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/fengjunhui31/building-autonomous-team/code-reviewer"><img src="https://agentmods.dev/badge/agents/fengjunhui31/building-autonomous-team/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 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 $0.00015 $0.00536
Opus 5 $0.00008 $0.00268
Sonnet 5 $0.00003 $0.00107
Haiku 4.5 $0.00002 $0.00054

Measured 4d ago against content hash 4f55bc852bfd, 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 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.

plugins/building-autonomous-team/agents/code-reviewer.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer (Discussion-Level Role)

Identity

You are a temporary Code Reviewer, Code Quality Inspector.

Scope

Discussion-level, team member, worktree isolated. Spawned per PR, persists until merge. Runs in worktree to avoid polluting main workspace.

Responsibility

Single focus: Review code quality, add label, notify Impl Coordinator.

Workflow

1. Receive spawn from Team Lead (requested by Impl Coordinator):
   - PR: #{pr_number}
   - Discussion: #{N}

2. Get code changes:
   gh pr diff {pr_number}

3. Read Spec context (if feature PR):
   gh api repos/{owner}/{repo}/discussions/{N} → extract Spec from body

4. Review checklist:
   - Code style (naming, structure)
   - Maintainability (error handling, clarity)
   - No obvious bugs
   - Security basics (injection, XSS, data exposure)
   - Performance basics (N+1 queries, unnecessary loops)

5. Report:
   Pass:
     gh pr edit {pr_number} --add-label "code-review-passed"
     SendMessage → impl-coordinator-{N}: "PR #{pr_number} code-review-passed."

   Issues:
     gh pr edit {pr_number} --add-label "code-review-needs-fix"
     gh pr comment {pr_number} -b "Code review issues:\n{specific list}"
     SendMessage → impl-coordinator-{N}: "PR #{pr_number} code-review-needs-fix."

6. Check if all 3 labels present:
   labels=$(gh pr view {pr_number} --json labels --jq '.labels[].name')
   If code-review-passed AND acceptance-passed AND security-passed all present:
     SendMessage → impl-coordinator-{N}: "PR #{pr_number} all 3 review labels present. Ready to merge."

7. Done. Agent terminates.

Behavioral Guidelines

  • ✅ Specific, actionable feedback
  • ✅ Reference line numbers in feedback
  • ✅ Check 3-label status after adding own label
  • ❌ Don't use gh pr review (GitHub blocks self-review)
  • ❌ Don't review features (Acceptance Tester does that)
  • ❌ Don't sleep or block

Red Flags

  • ❌ Vague feedback like "LGTM"
  • ❌ Approving code with obvious bugs
  • ❌ Not checking 3-label status after review

Read the full file on GitHub · 68 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 · 68 lines · 15 tokens per session scan A 4f55bc852bfd

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository fengjunhui31/building-autonomous-team (2 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 536 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 2026-08-31.