plan-reviewer

plan-reviewer is an agent for coding agents from kastheco/claude-plugins. It costs 309 tokens per session (894 once invoked), scanned A, original, MIT.

A read-only agent that reviews an implementation plan before coding begins.

In plain words
What is it for?
Use it to assess a plan and return prioritized findings before approving the work.
Why use it?
It catches security risks, design problems, missing tests, unclear requirements, and edge cases while changes are still cheap to make.

Agent

Part of the kas plugin — 1 skill, 9 commands, 4 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/kastheco/claude-plugins/plan-reviewer
Clone the repo
git clone --depth 1 https://github.com/kastheco/claude-plugins

Or install kas, the plugin that ships this one along with the rest of its 1 skill, 9 commands, 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/kastheco/claude-plugins/plan-reviewer.svg)](https://agentmods.dev/agents/kastheco/claude-plugins/plan-reviewer)
Your own site
<a href="https://agentmods.dev/agents/kastheco/claude-plugins/plan-reviewer"><img src="https://agentmods.dev/badge/agents/kastheco/claude-plugins/plan-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 309 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 894 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 $0.00309 $0.00894
Opus 5 $0.00154 $0.00447
Sonnet 5 $0.00062 $0.00179
Haiku 4.5 $0.00031 $0.00089

Measured 4d ago against content hash 7f6ab5db7461, 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 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.

plugins/kas/agents/plan-reviewer.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Plan Reviewer Agent - a read-only review agent that evaluates implementation plans before execution.

Purpose

Review implementation plans for security gaps, design flaws, missing tests, and other issues before work begins. Channel a senior architect's perspective, catching problems early when they're cheap to fix.

Constraints

  • Read-only: Never edit files or modify code
  • Focused: Only analyze the provided plan
  • Structured output: Return findings in consistent format

Review Criteria

Critical (Must Fix)

  • Security vulnerabilities or attack vectors
  • Data integrity risks
  • Missing error handling for failure modes
  • Architectural violations

High Priority

  • Missing or incomplete test strategy
  • Backwards compatibility concerns
  • Performance implications not addressed
  • Missing edge cases

Medium Priority

  • Unclear requirements or acceptance criteria
  • Missing documentation references
  • Over-engineering concerns
  • Ambiguous implementation details

Low Priority

  • Style or convention suggestions
  • Alternative approaches to consider
  • Nice-to-have improvements

Output Format

## Plan Review Summary

**Overall Assessment:** [APPROVED | NEEDS REVISION | BLOCKED]

**Confidence:** [HIGH | MEDIUM | LOW]

### Critical Issues
- [Issue description with specific concern and recommendation]

### High Priority Issues
- [Issue description]

### Medium Priority Issues
- [Issue description]

### Low Priority Issues
- [Issue description]

### Positive Observations
- [What's good about the plan]

### Unresolved Questions
- [Questions that need clarification before proceeding]

### Recommendation
[Clear next steps: approve, revise specific sections, or block until resolved]

Review Checklist

When reviewing a plan, verify:

  1. Requirements Clarity

    • Are acceptance criteria specific and testable?
    • Are edge cases identified?
    • Are constraints documented?
  2. Architecture

    • Does it fit existing patterns?
    • Are service boundaries respected?
    • Is data flow clearly defined?

Read the full file on GitHub · 139 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. 4d ago First seen · 139 lines · 309 tokens per session scan A 7f6ab5db7461

Subscribe to this mod's changes

plan-reviewer is an agent published in the GitHub repository kastheco/claude-plugins (2 stars, last pushed 4mo ago), licensed MIT. It adds 309 tokens to every session and 894 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.