plan-check

plan-check is a skill for Claude Code, Codex from ytubecoder/codex-in-claude. It costs 104 tokens per session (3,065 once invoked), scanned A, original, MIT.

An iterative service for getting a project plan reviewed by Codex, Grok, Gemini, Antigravity, or several reviewers together. It compares feedback about completeness, risks, ordering, and feasibility, then supports another review round.

In plain words
What is it for?
Use it when you want one or more external AI reviewers to challenge and improve a project plan.
Why use it?
It provides a second opinion on a plan and helps expose missing work or risky assumptions before implementation begins.

Skill for Claude CodeCodex

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/ytubecoder/codex-in-claude/plan-check
Any agent
npx skills add ytubecoder/codex-in-claude --skill plan-check
Clone the repo
git clone --depth 1 https://github.com/ytubecoder/codex-in-claude

Made for: Claude Code, Codex.

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-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/ytubecoder/codex-in-claude/plan-check.svg)](https://agentmods.dev/skills/ytubecoder/codex-in-claude/plan-check)
Your own site
<a href="https://agentmods.dev/skills/ytubecoder/codex-in-claude/plan-check"><img src="https://agentmods.dev/badge/skills/ytubecoder/codex-in-claude/plan-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,065 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 $0.00104 $0.03065
Opus 5 $0.00052 $0.01533
Sonnet 5 $0.00021 $0.00613
Haiku 4.5 $0.00010 $0.00307

Measured 3d ago against content hash 27a838453303, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-check 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 3d 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.

skills/plan-check/SKILL.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Check — Iterative Plan Review (Codex / Grok / Gemini / Council)

Conversational plan review where Claude acts as mediator. An external reviewer (Codex, Grok, Gemini, or several in parallel) reviews the plan for general completeness, risks, sequencing, and feasibility. Claude synthesizes the feedback, agrees or pushes back, and iterates until the plan is solid.

Reviewers

Reviewer CLI Selected when the user says
Codex (default) codex "codex review", "send to codex", nothing provider-specific
Grok grok "grok review", "send to grok", "what does grok think"
Gemini (enterprise/API-key only) gemini "gemini review" — but see the routing note below
Antigravity (Gemini models via Google AI Pro/Ultra) agy "agy review", "antigravity review", and usually "gemini review" too
Council (all in parallel) all installed "ask both", "ask all three", "council review", "all reviewers"

Gemini routing note: Google cut gemini (gemini-cli) off from consumer accounts — free, AI Pro, and Ultra — on 2026-06-18; it now only serves Gemini Code Assist Standard/Enterprise licenses and API keys. When the user says "gemini" and agy is installed, use Antigravity — it runs the same Gemini model family on their subscription. Only use gemini directly if the machine actually has a working enterprise/API-key setup. One review = one reviewer: never run both gemini and agy as separate council members (same models, no independence).

If a requested CLI is not installed (command -v codex / command -v grok / command -v agy), say so and offer the others. Council means every installed reviewer unless the user names a subset ("codex and agy").

Trigger Phrases

  • "get codex to check" / "get grok to check" / "get gemini to check"
  • "lets review with codex" / "lets review with grok" / "lets review with gemini"
  • "send to codex" / "send to grok" / "send to gemini"
  • "codex review" / "grok review" / "gemini review"
  • "have codex look at this" / "what does grok think" / "what does gemini think"
  • "second opinion on this plan"
  • "ask both" / "ask all three" / "council review" / "third opinion"

Read the full file on GitHub · 264 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. 3d ago First seen · 264 lines · 104 tokens per session scan A 27a838453303

Subscribe to this mod's changes

plan-check is a skill published in the GitHub repository ytubecoder/codex-in-claude (2 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 3,065 once invoked, about $0.0005 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

ads-linkedin

Audit LinkedIn Ads measurement, Insight Tag and conversions, professional audiences, lead generation, ABM, creative, bidding, budgets, pacing, automation, and policy. Use for LinkedIn Ads, Campaign Manager, Insight Tag, Lead Gen Forms, Thought Leader Ads, ABM campaigns, or B2B paid media.

AgriciDaniel/claude-ads · 68 tokens

ads-launch

Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creation, launch plans, publishing ads, activating campaigns, uploading creative, or requests to push a campaign live.

AgriciDaniel/claude-ads · 45 tokens

api-response-optimization

Optimizes API performance through payload reduction, caching strategies, and compression techniques. Use when improving API response times, reducing bandwidth usage, or implementing efficient caching.

secondsky/claude-skills · 36 tokens

ctx-insight

Open the context-mode Insight dashboard in your default browser. Insight is the hosted analytics layer for AI-assisted engineering teams — per-engineer productive rate, retry waste, blocker detection, role-narrowed views. Trigger: /context-mode:ctx-insight.

mksglu/context-mode · 55 tokens

plan-create

Create structured implementation plans for autonomous TDD development. Use for new features, multi-file changes, or anything requiring multiple steps or tests. Triggers on aspirational openers ("let's build", "let's start building", "I want to make", "I want an app that", "help me build"), capability lists ("users…

markshust/hcf · 171 tokens

amazing-psycoder

Route Amazing PsyCoder requests to the correct psychological experiment or behavioral-data analysis stage: Designer, Coder, or Reviewer. Use for end-to-end or multi-stage work, ambiguous requests such as “帮我做 Stroop”, cross-pipeline work, system-capability questions, or explicit invocations of Amazing PsyCoder.…

soupandpsy/amazing-psycoder-skills · 110 tokens