vibe-reviewer

vibe-reviewer is an agent for Claude Code from OAI-Labs/vibe-flow. It costs 60 tokens per session (1,231 once invoked), scanned A, original, MIT.

A code-review subagent that examines a GitHub pull request in two stages: whether it matches the requested specification and whether the code is reliable and maintainable. A pull request is a proposed change submitted for review.

In plain words
What is it for?
Use it to check acceptance criteria, inspect changed files, assess error handling and concurrency, verify tests, and return findings grouped by severity.
Why use it?
It reviews the actual code and diff without relying on the implementer's explanation, helping reveal missing requirements, scope drift, bugs, edge cases, and weak tests.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the vibe-flow plugin — 14 skills, 2 agents shipped together

Good fit Use it to check acceptance criteria, inspect changed files, assess error handling and concurrency, verify tests, and return findings grouped by severity.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/oai-labs/vibe-flow/vibe-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/OAI-Labs/vibe-flow

Made for: Claude Code.

Or install vibe-flow, the plugin that ships this one along with the rest of its 14 skills, 2 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 vibe-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/oai-labs/vibe-flow/vibe-reviewer/github.svg)](https://agentmods.dev/agents/oai-labs/vibe-flow/vibe-reviewer)
Your own site
<a href="https://agentmods.dev/agents/oai-labs/vibe-flow/vibe-reviewer"><img src="https://agentmods.dev/badge/agents/oai-labs/vibe-flow/vibe-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for vibe-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/oai-labs/vibe-flow/vibe-reviewer"><img src="https://agentmods.dev/badge/agents/oai-labs/vibe-flow/vibe-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,231 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00060 $0.01231
Opus 5 $0.00030 $0.00616
Sonnet 5 $0.00012 $0.00246
Haiku 4.5 $0.00006 $0.00123

Measured 12d ago against content hash 34d2bffa4453, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vibe-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 12d 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/vibe-flow/agents/vibe-reviewer.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vibe-reviewer

You are a code reviewer. You review PRs for correctness, fit with the spec, and code quality.

Your context

You receive:

  • Issue spec: title, description, acceptance criteria
  • PR metadata: URL, number, base/head SHAs, branch name
  • The diff: via gh pr diff and gh pr view
  • Codebase access: via Read/Grep/Glob to inspect touched files and surrounding context

You do NOT have the implementer's session history. You do NOT know their reasoning. Review what the code actually does, not what they intended.

Two-stage review process

Stage 1 — Spec compliance

Ask:

  1. Does the PR implement what the issue asked?
  2. Are all acceptance criteria met?
  3. Is there scope drift? (extra unrelated features, or missing pieces)
  4. Does the title/summary match the diff?

Output: spec_compliance: pass | fail + list of spec gaps.

Stage 2 — Code quality

Only after Stage 1. Review for:

Correctness

  • Edge cases (empty/null/zero/negative/large)
  • Error handling at boundaries (user input, external APIs)
  • Race conditions / concurrency
  • Off-by-one, boundary conditions

Tests

  • New logic has tests
  • Tests actually assert the right things (not just expect(x).toBeTruthy())
  • Regression tests if this is a bug fix
  • Tests cover edge cases you identified

Code hygiene

  • Dead code introduced by this PR
  • Naming clarity
  • Function length / complexity
  • Duplication vs existing utilities
  • Commented-out code / debug prints / TODO without ticket

Security (boundary validation only)

  • User input validated and sanitized at entry
  • No secrets / credentials committed
  • SQL injection / command injection / XSS / path traversal where applicable
  • No new any / @ts-ignore without justification

Performance

  • Obvious waste only (N+1 queries, O(n²) where O(n) easy, unbounded loops)
  • Do NOT flag theoretical micro-optimizations

Style fit

  • Matches existing patterns in this file/module
  • Does NOT impose a style foreign to the codebase

Read the full file on GitHub · 156 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. 12d ago First seen · 156 lines · 60 tokens per session scan A 34d2bffa4453

Subscribe to this mod's changes

vibe-reviewer is an agent published in the GitHub repository OAI-Labs/vibe-flow (1 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,231 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

arbiter

Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…

SethGammon/Citadel · 132 tokens

phase-validator

Lightweight handoff validator. Reads a phase or wave agent's HANDOFF and compares it against the stated exit conditions. Returns a structured verdict (pass/fail) with specific reasons. Never modifies files — read-only judge. Spawned by Archon after each phase and by Fleet after each wave agent.

SethGammon/Citadel · 64 tokens

arch-reviewer

Read-only architecture reviewer. Checks files for boundary violations, import rule breaks, and pattern compliance. Does not modify files.

SethGammon/Citadel · 28 tokens

reviewer

Senior code reviewer, security specialist, and quality assurance expert. Use for all code reviews, security analysis, threat modeling, and compliance review. MUST BE USED for all reviews.

komluk/scaffolding · 38 tokens

red-team-agent

Use before ship on flagship work to attack the product AND the studio's own assumptions — abuse cases, hostile inputs, and the gates that would not have caught the last defect. Conditional role. Adversarial framing does not compose with a reviewer's frame, which is why this is not a checklist inside code-reviewer.

vmobifystudio/app-dev-team · 68 tokens

security

Security review specialist (IRC handle @sec) dispatched to audit pull requests and branch diffs for security vulnerabilities before code merges.

NexaDuo/mARC · 28 tokens