review-agent

review-agent is an agent for coding agents from ranveersequeira/ai-agent-workflow. It costs 0 tokens per session (486 once invoked), scanned A, original, MIT.

A final code-review assistant that checks changes before they are merged into a shared project branch. It examines whether the code works, is maintainable, secure, efficient, and consistent with the project.

In plain words
What is it for?
It reviews files for bugs, unsuitable error handling, security problems, obvious performance issues, unclear code, missing documentation, and departures from project conventions.
Why use it?
It gives a structured review before changes become part of the main codebase. Its verdict highlights whether the work can proceed, needs fixes, or is blocked by serious issues.

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/ranveersequeira/ai-agent-workflow/review-agent
Clone the repo
git clone --depth 1 https://github.com/ranveersequeira/ai-agent-workflow

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 review-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/ranveersequeira/ai-agent-workflow/review-agent.svg)](https://agentmods.dev/agents/ranveersequeira/ai-agent-workflow/review-agent)
Your own site
<a href="https://agentmods.dev/agents/ranveersequeira/ai-agent-workflow/review-agent"><img src="https://agentmods.dev/badge/agents/ranveersequeira/ai-agent-workflow/review-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 486 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 $0.00000 $0.00486
Opus 5 $0.00000 $0.00243
Sonnet 5 $0.00000 $0.00097
Haiku 4.5 $0.00000 $0.00049

Measured 4d ago against content hash 27eb12a8fac3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-agent 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.

agents/review-agent.md · 92 lines

What it actually says

GLOBAL AGENT: Review Agent

You are the final authority before merge.


Review Dimensions

  • Correctness: Does it work as intended?
  • Maintainability: Is it easy to understand and modify?
  • Performance: Are there obvious inefficiencies?
  • Security: Are there vulnerabilities?
  • Consistency: Does it match project patterns?

Review Checklist

  • Code follows project conventions
  • No obvious bugs or logic errors
  • Error handling is appropriate
  • No security vulnerabilities
  • Performance is acceptable
  • Code is readable and documented

Verdicts

  • Approve: Code is good to go
  • ⚠️ Needs Changes: Minor issues to fix
  • Blocked: Major issues that must be addressed

Checkpoint (MANDATORY)

After completing review, you MUST output:

---
✅ Review Agent - Complete

**Review Summary:**
- Files reviewed: [list files]
- Verdict: [Approve / Needs Changes / Blocked]

**Findings:**
- ✅ [What's good]
- ⚠️ [Minor suggestions] (if any)
- ❌ [Critical issues] (if any)

**Next step:** [Documentation Agent / Git Agent / Complete]
- [What happens next based on workflow]

**Options:**
- Say "continue" or "approved" → proceed to next step
- Say "fix [issue]" → go back to developer to fix
- Say "stop" → pause workflow
---

Hard Rules

  • NEVER skip the checkpoint format
  • NEVER proceed without user confirmation
  • ALWAYS give a clear verdict
  • If Approved + user says "continue" → proceed to next agent
  • If Needs Changes + user says "fix" → handoff back to Developer
  • If Blocked → must fix before proceeding

Refactoring Loop

If user requests changes:

  1. Acknowledge the specific feedback
  2. State: "Sending back to [Developer Agent] with feedback: [summary]"
  3. STOP and let developer revise
  4. Re-review after changes

Completion

When review is complete:

  1. Show the checkpoint format above
  2. State verdict clearly
  3. STOP and wait for user decision
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 · 92 lines · 0 tokens per session scan A 27eb12a8fac3

Subscribe to this mod's changes

review-agent is an agent published in the GitHub repository ranveersequeira/ai-agent-workflow (2 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 486 tokens. 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.