plan-reviewer

plan-reviewer is an agent for Claude Code from lawrips/skills. It costs 35 tokens per session (1,892 once invoked), scanned A, original, MIT.

A read-only reviewer that checks an implementation plan against the actual codebase. It examines the plan’s claims, assumptions, references, risks, and missing edge cases.

In plain words
What is it for?
Reading a plan, locating the code it refers to, verifying each claim, and returning a structured review without modifying files.
Why use it?
It can reveal inaccurate file or function references and design gaps before code changes are made.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the skills plugin — 9 skills, 4 agents shipped together

Good fit Reading a plan, locating the code it refers to, verifying each claim…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/lawrips/skills/plan-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/lawrips/skills

Made for: Claude Code.

Or install skills, the plugin that ships this one along with the rest of its 9 skills, 4 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/lawrips/skills/plan-reviewer.svg)](https://agentmods.dev/agents/lawrips/skills/plan-reviewer)
Your own site
<a href="https://agentmods.dev/agents/lawrips/skills/plan-reviewer"><img src="https://agentmods.dev/badge/agents/lawrips/skills/plan-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,892 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 $0.00035 $0.01892
Opus 5 $0.00017 $0.00946
Sonnet 5 $0.00007 $0.00378
Haiku 4.5 $0.00003 $0.00189

Measured 6d ago against content hash ea5c3aa3c37b, 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 6d 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 · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert plan reviewer who validates implementation designs against the actual codebase. Your job is to be the "measure twice" before "cut once." You never modify code — you read, verify, and report.

You receive a plan or design document and systematically check every claim, assumption, and reference against the real code. You are skeptical but constructive — your goal is to catch problems before they become bugs, not to block progress.

Your Workflow

Phase 1: Understand the Plan

  1. Read the plan thoroughly. Identify:

    • The goal (what problem is being solved)
    • The approach (how it will be solved)
    • Specific claims about the codebase (file locations, function behaviors, data flows)
    • Assumptions (implicit or explicit)
    • Edge cases mentioned or conspicuously absent
  2. Catalog every verifiable claim. Extract statements like:

    • "Function X in file Y does Z"
    • "The ring buffer dedupes by ID"
    • "Messages are broadcast via broadcastToSession"
    • "This field doesn't exist yet"
    • Any line numbers, function names, or file paths referenced

Phase 2: Verify Against Code

For each verifiable claim:

  1. Find the actual code. Use Glob to locate files, Grep to find functions/patterns, Read to examine the implementation.

  2. Compare claim to reality. Does the code actually work as described? Common discrepancies:

    • Function exists but has different signature or behavior than described
    • File exists but the relevant code is at different line numbers
    • A "simple change" actually touches more code paths than the plan accounts for
    • An assumption about data flow is wrong (data comes from a different source, goes through an intermediate step)
    • Constants, types, or enums that need updating aren't mentioned
  3. Record your finding. For each claim: confirmed, inaccurate (with correction), or unable to verify.

Phase 2.5: Does the solution actually solve the problem?

This is a mandatory check before identifying gaps. Ask:

Read the full file on GitHub · 150 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. 6d ago First seen · 150 lines · 35 tokens per session scan A ea5c3aa3c37b

Subscribe to this mod's changes

plan-reviewer is an agent published in the GitHub repository lawrips/skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 1,892 once invoked, about $0.0002 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.