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.
npx skills add ytubecoder/codex-in-claude --skill plan-checkgit clone --depth 1 https://github.com/ytubecoder/codex-in-claudeWrote 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.
[](https://agentmods.dev/skills/ytubecoder/codex-in-claude/plan-check)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00104 | $0.03065 |
| Opus 5.5 | $0.00042 | $0.01226 |
| Sonnet 5.5 | $0.00021 | $0.00613 |
| Haiku 4.5 | $0.00010 | $0.00307 |
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 2mo 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.
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"
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.
- 2mo ago First seen · 264 lines · 104 tokens per session scan A 27a838453303
plan-check is a skill published in the GitHub repository ytubecoder/codex-in-claude (2 stars, last pushed 7d ago), licensed MIT. It adds 104 tokens to every session and 3,065 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
ads-youtube
Audit YouTube Ads campaign setup, video inventory, Shorts, in-stream, CTV, creative, audiences, brand safety, bidding, and measurement. Use for YouTube Ads, video ads, pre-roll, bumper ads, skippable in-stream, Shorts ads, VAC migration, or CTV. Read-only; use ads-google for Google-managed campaign types and…
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.
bun-test-mocking
Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.
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.
alibaba-maestro
Alibaba Cloud Maestro routing skill. Classify the user's Alibaba Cloud task, select the narrowest specialist agent or the right team of specialists from the catalog, and dispatch them — single specialist for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-dispatch live-guard agents.…
alibaba-certificate-manager-issuer-review
Review Alibaba Cloud SSL Certificate Service — DV/OV/EV certificate lifecycle, auto-renewal configuration, certificate deployment to SLB/ALB/CDN/OSS, domain validation status, CAA record compliance, and expiry monitoring.