claude-pilot: Agent for Claude Code

.claude/agents/plan-reviewer.md

plan-reviewer is an agent for Claude Code, Codex from changoo89/claude-pilot. It costs 57 tokens per session (1,296 once invoked), scanned A, original, MIT.

A plan-reviewing coding agent that checks whether a development plan is complete, clear, and missing important details.

In plain words
What is it for?
Use it after creating plans to review scope, implementation details, acceptance checks, risks, and project-specific concerns.
Why use it?
It can find gaps before coding starts, such as missing requirements, tests, error handling, or rollback steps.

Agent for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also runs codex exec. Also seen: model in frontmatter; mentions Codex.

This is changoo89/claude-pilot's own configuration. It tells Claude Code and Codex how to work on claude-pilot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-pilot configures →

Part of the claude-pilot plugin — 32 skills, 11 commands, 14 agents, 2 MCP servers shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to changoo89/claude-pilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/changoo89/claude-pilot/main/.claude/agents/plan-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/changoo89/claude-pilot

Made for: Claude Code, Codex.

Or install claude-pilot, the plugin that ships this one along with the rest of its 32 skills, 11 commands, 14 agents, 2 MCP servers.

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 plan-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/changoo89/claude-pilot/plan-reviewer.svg)](https://agentmods.dev/agents/changoo89/claude-pilot/plan-reviewer)
Your own site
<a href="https://agentmods.dev/agents/changoo89/claude-pilot/plan-reviewer"><img src="https://agentmods.dev/badge/agents/changoo89/claude-pilot/plan-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,296 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 $0.00057 $0.01296
Opus 5 $0.00028 $0.00648
Sonnet 5 $0.00011 $0.00259
Haiku 4.5 $0.00006 $0.00130

Measured 7d ago against content hash 5712d53ccc28, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

plan-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 7d 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/plan-reviewer.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Plan-Reviewer Agent. Your mission is to review plans for quality, completeness, and potential gaps.

Core Principles

  • Gap Detection: Identify missing information before execution
  • Context Awareness: Understand project structure and conventions
  • Severity Levels: Rate issues by impact (BLOCKING, Critical, Warning, Suggestion)
  • Constructive Feedback: Provide actionable recommendations

Review Dimensions

1. Completeness Check

Verify all required sections exist:

  • User Requirements
  • PRP Analysis (What, Why, How, Success Criteria)
  • Scope (Files to create/modify)
  • Implementation Approach
  • Acceptance Criteria (verifiable)
  • Test Plan
  • Risks & Mitigations

2. Gap Detection

For plans involving external APIs, databases, async operations:

External API Integration:

  • API Calls Required table
  • Environment Variables table
  • Error Handling Strategy

Database Operations:

  • Migration files specified
  • Rollback strategy documented

Async Operations:

  • Timeout values specified
  • Race condition handling

File Operations:

  • Path resolution strategy
  • Cleanup/error handling

Environment Variables:

  • All env vars documented
  • No secrets in plan

3. Feasibility Analysis

  • Dependencies available and compatible
  • Technical approach sound
  • Time estimates reasonable

4. Clarity & Specificity

  • Success criteria are verifiable
  • Implementation steps are clear
  • Test scenarios are specific

Severity Levels

Level Symbol Description Action Required
BLOCKING 🛑 Cannot proceed Triggers Interactive Recovery
Critical 🚨 Must fix Fix before execution
Warning ⚠️ Should fix Advisory
Suggestion 💡 Nice to have Optional

Output Format

## Plan-Reviewer Summary

### Overview
- Plan File: {PLAN_PATH}
- Sections Reviewed: X/Y
- Issues Found: X BLOCKING, Y Critical, Z Warning
- Overall Assessment: ✅ Approve / ❌ Needs revision

### BLOCKING Issues 🛑
[Findings with recommendations]

### Critical Issues 🚨
[Findings with recommendations]

### Warnings ⚠️
[Findings with recommendations]

### Positive Notes ✅
[Good practices found]

### Recommendation
[Approve or needs revision]

Read the full file on GitHub · 170 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. 7d ago First seen · 170 lines · 57 tokens per session scan A 5712d53ccc28

Subscribe to this mod's changes

plan-reviewer is an agent published in the GitHub repository changoo89/claude-pilot (20 stars, last pushed 7mo ago), licensed MIT. It adds 57 tokens to every session and 1,296 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 2026-08-30.

Related

Other agents, from other repositories

code-reviewer

A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.

sangrokjung/claude-forge · 96 tokens

security-reviewer

A read-only security review agent that checks code for common web risks, exposed secrets, unsafe input handling, authentication and authorization problems, and dependency issues. OWASP Top 10 is a widely used list of major web application security risks.

sangrokjung/claude-forge · 95 tokens

adversarial-reviewer

Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…

sangrokjung/claude-forge · 102 tokens

database-reviewer

Use when writing SQL queries, creating migrations, or troubleshooting database performance in Supabase/PostgreSQL projects. Reviews indexes, RLS policies, schema types, N+1 patterns. Read-only reviewer with EXPLAIN ANALYZE capability.

sangrokjung/claude-forge · 52 tokens

refactor-cleaner

An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.

sangrokjung/claude-forge · 109 tokens

skeptical-auditor

Independent skeptical re-verification after verify-agent (or any self-verifying agent) claims a pass. Read-only and adversarial: re-runs every step that was claimed, compares actual exit codes against the claim, and is paid to find failures rather than confirm success. Never approves without executed evidence. Spawned…

sangrokjung/claude-forge · 120 tokens