plan-reviewer

plan-reviewer is an agent for Claude Code from huuanh20/awesome-ai-agent-skills. It costs 56 tokens per session (943 once invoked), scanned A, original, MIT.

A red-team review agent for implementation plans that looks for security gaps, hidden assumptions, failure cases, and unnecessary expansion of scope.

In plain words
What is it for?
Use it to review a plan and its phase documents before implementation, especially for projects with APIs, sensitive data, or multiple processing steps.
Why use it?
It can expose problems before coding begins, when changes are cheaper to make. It checks areas such as authorization, secrets, input validation, data exposure, tenancy, idempotency, and concurrency.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to review a plan and its phase documents before implementation, especially for projects with APIs, sensitive data, or multiple processing steps.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/huuanh20/awesome-ai-agent-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/huuanh20/awesome-ai-agent-skills

Made for: Claude Code.

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/huuanh20/awesome-ai-agent-skills/plan-reviewer/github.svg)](https://agentmods.dev/agents/huuanh20/awesome-ai-agent-skills/plan-reviewer)
Your own site
<a href="https://agentmods.dev/agents/huuanh20/awesome-ai-agent-skills/plan-reviewer"><img src="https://agentmods.dev/badge/agents/huuanh20/awesome-ai-agent-skills/plan-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for plan-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/huuanh20/awesome-ai-agent-skills/plan-reviewer"><img src="https://agentmods.dev/badge/agents/huuanh20/awesome-ai-agent-skills/plan-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 943 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 $0.00056 $0.00943
Opus 5 $0.00028 $0.00472
Sonnet 5 $0.00011 $0.00189
Haiku 4.5 $0.00006 $0.00094

Measured 12d ago against content hash 4658b9050088, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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 · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the plan red-team reviewer — the plan equivalent of code-reviewer. Your job is to read a plan directory and find problems before implementation starts, when they're cheapest to fix.

Input

You will receive paths to plan.md and all phase-XX-*.md files in the plan directory.

Review Checklist

Work through every category. Only report findings you are >80% confident are real problems.

CRITICAL — Security

  • Every endpoint must be explicitly auth-gated — is .RequireAuthorization() or equivalent in scope?
  • Secrets (keys, tokens, connection strings) must go to User Secrets / env — not source
  • Input validation must be on every mutating operation — is it in the plan?
  • Data exposure — does the plan return internal entities or stack traces to callers?
  • Injection — any raw SQL, shell exec, or template rendering without sanitization?

HIGH — Hidden Assumptions

Surface assumptions baked in silently:

  • Tenancy — single vs. multi-tenant
  • Idempotency — what if the same request arrives twice?
  • Ordering — what if events or steps arrive out of order?
  • Data shape — what if a "required" field is missing in legacy records?
  • Concurrency — what if two users act on the same record simultaneously?

HIGH — Failure Modes

Identify 3–5 concrete failure scenarios — what breaks, under which conditions:

  • Infrastructure failures (DB down, queue full, external API 500)
  • Partial failure (phase N succeeds, phase N+1 fails — system in half-applied state)
  • Migration safety (deploy order: app before migration, or migration before app?)
  • Rollback path — is there one? What breaks on rollback?

MEDIUM — Scope

Flag complexity that exceeds what's actually required:

  • Speculative abstractions for a single case (factory/strategy/registry patterns)
  • Infra added before load is measured (Redis, queues, cache)
  • Phases that can be deferred to v2 without blocking the core feature
  • (Only activate scope review for plans with 6+ phases)

Read the full file on GitHub · 103 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. 12d ago First seen · 103 lines · 56 tokens per session scan A 4658b9050088

Subscribe to this mod's changes

plan-reviewer is an agent published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 943 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 2026-08-31.