Plan Review

Plan Review is a skill for Claude Code, Codex from reggiechan74/cc-plugins. It costs 66 tokens per session (770 once invoked), scanned A, original, MIT.

A checklist for reviewing software execution plans before implementation begins.

In plain words
What is it for?
Use it to validate plans for clarity, measurable outcomes, critic assignments, retries, and requirements for areas such as finance, security, or performance.
Why use it?
It catches missing scope, acceptance criteria, reviewers, retry limits, and cost estimates before work starts.

Skill for Claude CodeCodex

Part of the code-coherence plugin — 5 skills, 7 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 skills/reggiechan74/cc-plugins/plan-review
Any agent
npx skills add reggiechan74/cc-plugins --skill plan-review
Clone the repo
git clone --depth 1 https://github.com/reggiechan74/cc-plugins

Made for: Claude Code, Codex.

Or install code-coherence, the plugin that ships this one along with the rest of its 5 skills, 7 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 Review

README.md
[![agentmods](https://agentmods.dev/badge/skills/reggiechan74/cc-plugins/plan-review.svg)](https://agentmods.dev/skills/reggiechan74/cc-plugins/plan-review)
Your own site
<a href="https://agentmods.dev/skills/reggiechan74/cc-plugins/plan-review"><img src="https://agentmods.dev/badge/skills/reggiechan74/cc-plugins/plan-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 770 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 $0.00066 $0.00770
Opus 5 $0.00033 $0.00385
Sonnet 5 $0.00013 $0.00154
Haiku 4.5 $0.00007 $0.00077

Measured 4d ago against content hash fd914688564e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Plan Review 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.

code-coherence/skills/plan-review/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Review: Validate Execution Plans

Purpose

Review and validate execution plans before code changes begin, ensuring plans have clear acceptance criteria, appropriate critic assignments, and realistic scope.

When to Use

  • After planner agent creates execution plan
  • When user explicitly requests plan review
  • Before high-stakes operations (configured in highStakesPatterns)

Validation Criteria

Completeness Checks

Scope defined: Files, operations, and boundaries clear ✓ Success criteria present: At least 3 specific, measurable criteria ✓ Critic assignment: Each criterion mapped to responsible critic ✓ Retry budget set: Escalation path defined ✓ Cost estimate included: Token overhead calculated

Quality Gates

Acceptance criteria must be:

  • Specific (not "good code" but "all tests pass, coverage >80%")
  • Measurable (binary pass/fail, not subjective)
  • Pre-declared (before execution, not emergent)
  • Mapped to critics (clear veto authority assignment)

Domain-specific patterns:

  • Financial: Must specify precision, rounding method, audit requirements
  • Security: Must reference OWASP checklist, auth patterns
  • Performance: Must define latency SLAs, memory limits

Review Process

  1. Parse plan structure - Extract scope, criteria, critics, budget
  2. Check completeness - Verify all required sections present
  3. Validate criteria - Ensure specific and measurable
  4. Verify critic mapping - Each criterion has responsible critic
  5. Check domain patterns - Apply domain-specific requirements
  6. Estimate feasibility - Scope appropriate for retry budget
  7. Present findings - Show issues and recommendations

Example Reviews

Good Plan

EXECUTION PLAN ✓

Scope: Refactor auth to JWT ✓
Files: src/auth/*.ts ✓

SUCCESS CRITERIA: ✓
✓ All 18 existing tests pass (Code Critic validates)
✓ No OWASP Top 10 violations (Security Critic validates)
✓ Token storage uses httpOnly cookies (Security Critic validates)
✓ Token refresh handles 401 (Code Critic validates)
✓ Coverage maintains 85%+ (Code Critic validates)

Critics: code, security ✓
Budget: 6 iterations ✓
Cost: +40% tokens ($0.15) ✓

Read the full file on GitHub · 106 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 · 106 lines · 66 tokens per session scan A fd914688564e

Subscribe to this mod's changes

Plan Review is a skill published in the GitHub repository reggiechan74/cc-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 770 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens