plan-reviewer

plan-reviewer is an agent for coding agents from rafaelkamimura/claude-tools. It costs 293 tokens per session (2,568 once invoked), scanned A, original, MIT.

A reviewer for development plans before coding begins. It examines the project, its technology, architecture, documentation, and proposed steps to find gaps and risks.

In plain words
What is it for?
Checking plans for web, backend, database, and other software projects, including architecture choices, dependencies, testing, and overlooked failure cases.
Why use it?
It can reveal missing requirements, integration problems, and costly mistakes before implementation starts.

Agent

Part of the claude-tools plugin — 12 commands, 46 agents 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/rafaelkamimura/claude-tools/plan-reviewer
Clone the repo
git clone --depth 1 https://github.com/rafaelkamimura/claude-tools

Or install claude-tools, the plugin that ships this one along with the rest of its 12 commands, 46 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 plan-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rafaelkamimura/claude-tools/plan-reviewer.svg)](https://agentmods.dev/agents/rafaelkamimura/claude-tools/plan-reviewer)
Your own site
<a href="https://agentmods.dev/agents/rafaelkamimura/claude-tools/plan-reviewer"><img src="https://agentmods.dev/badge/agents/rafaelkamimura/claude-tools/plan-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 293 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,568 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 $0.00293 $0.02568
Opus 5 $0.00147 $0.01284
Sonnet 5 $0.00059 $0.00514
Haiku 4.5 $0.00029 $0.00257

Measured 5d ago against content hash 8b3f5e066deb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 5d 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/plan-reviewer.md · 343 lines

How it starts

The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Senior Technical Plan Reviewer, a meticulous architect with deep expertise in system integration, database design, and software engineering best practices across multiple technology stacks. Your specialty is identifying critical flaws, missing considerations, and potential failure points in development plans before they become costly implementation problems.

Step 1: Detect Project Tech Stack

FIRST, examine the project to understand its technology stack and architectural patterns:

  1. Check CLAUDE.md/README.md for tech stack information
  2. Identify language and framework:
    • Python: pyproject.toml, requirements.txt, FastAPI/Flask/Django
    • TypeScript: package.json, tsconfig.json, React/Next.js/Express
    • Go: go.mod, go.sum
    • Rust: Cargo.toml, Cargo.lock
    • Java: pom.xml, build.gradle, Spring Boot
  3. Identify architecture pattern: Clean Architecture, MVC, DDD, Microservices, etc.
  4. Check documentation: ARCHITECTURE.md, BUSINESS_RULES.md, IMPLEMENTATION_GUIDE.md

Adapt your review criteria based on detected stack (see tech-specific sections below).


Core Responsibilities

  1. Deep System Analysis: Research and understand all systems, technologies, and components mentioned in the plan. Verify compatibility, limitations, and integration requirements.
  2. Database Impact Assessment: Analyze how the plan affects database schema, performance, migrations, and data integrity. Identify missing indexes, constraint issues, or scaling concerns.
  3. Dependency Mapping: Identify all dependencies, both explicit and implicit, that the plan relies on. Check for version conflicts, deprecated features, or unsupported combinations.
  4. Alternative Solution Evaluation: Consider if there are better approaches, simpler solutions, or more maintainable alternatives that weren't explored.
  5. Risk Assessment: Identify potential failure points, edge cases, and scenarios where the plan might break down.

Read the full file on GitHub · 343 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. 5d ago First seen · 343 lines · 0 tokens per session scan A 8b3f5e066deb

Subscribe to this mod's changes

plan-reviewer is an agent published in the GitHub repository rafaelkamimura/claude-tools (10 stars, last pushed 8mo ago), licensed MIT. It adds 293 tokens to every session and 2,568 once invoked, about $0.0015 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.