Codex Plan Review

Community

PiLastDigit

codex-plan-review

Iterative Codex CLI review of a planning document

Overview

Publisher	PiLastDigit
Repository	`TRIP-workflow`
Skill name	`codex-plan-review`
Stars	636
Forks	91
Bundled files	8
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
8 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by PiLastDigit on GitHub. Read the source before you install it.

Installation

Install the Codex Plan Review AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/PiLastDigit/TRIP-workflow/tree/master/skills/codex-plan-review
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/PiLastDigit/TRIP-workflow.git /tmp/TRIP-workflow
mkdir -p .claude/skills
cp -r /tmp/TRIP-workflow/skills/codex-plan-review .claude/skills/codex-plan-review

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Codex Plan Review in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Codex Plan Review on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Codex Plan Review is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Codex Plan Review

Iterative review of a planning document via Codex CLI. State (thread ID, review text, event log) persisted under .claude/skills/codex-plan-review/state/<sanitized-path>.{thread,review.txt,events.ndjson}.

The companion codex-code-review skill shares the same scripts with its own prompt templates and STATE_DIR.

Arguments

<plan-path> — auto: start if no thread, resume if exists. Trailing free-text is extra context.
reset <plan-path> — drop state, next call starts fresh.
show <plan-path> — display latest review without calling Codex.

Execution

Parse $ARGUMENTS: extract action (reset/show/auto) and plan path.
Auto — try start.sh first (exit code 2 = thread exists -> use resume.sh):
- Start: bash .claude/skills/codex-plan-review/scripts/start.sh --prompt-file .claude/skills/codex-plan-review/prompts/start.tpl <plan-path> [extra]
- Resume: bash .claude/skills/codex-plan-review/scripts/resume.sh --prompt-file .claude/skills/codex-plan-review/prompts/resume.tpl <plan-path> [extra]
Reset: bash .claude/skills/codex-plan-review/scripts/reset.sh <plan-path>
Show: bash .claude/skills/codex-plan-review/scripts/show.sh <plan-path>
Parse trailing tag:
- APPROVED — tell user, done.
- REQUEST_CHANGES — engage critically: fix legitimate findings by editing the plan, push back on incorrect ones. Surface review verbatim, propose fixes, let user confirm.
- NEEDS_REWORK — surface to user before mass-editing.

Notes

Run Codex calls in a background shell. Invoke start.sh / resume.sh via the Bash tool with run_in_background: true — never as a foreground/inline command. Codex runs at xhigh effort routinely outlast the foreground command timeout; the background task notifies on completion, then read its output. reset.sh / show.sh are instant and fine in the foreground.
Set CODEX_TIMEOUT=1800 (30 min) when invoking start.sh / resume.sh — a generous circuit breaker against hung runs, not a performance target; bump higher for unusually large targets rather than risk killing a legitimate run. Script default is 0 = no timeout. On expiry the script fails through the normal error path with a "timed out" message in the stderr tail. Requires GNU timeout/gtimeout (macOS: brew install coreutils); warns and runs unbounded if neither is present.
Model/effort/tier defaults live in codex-plan-review/scripts/_common.sh, derived from STATE_DIR: implementation → gpt-6-luna at high effort on the fast service tier; plan review → gpt-6-astra at xhigh on standard routing; code review → gpt-6-sol at xhigh on the fast tier; codex-ask → gpt-6-astra at xhigh on standard routing. Adjust that one file to your preferred models, or override per run via CODEX_MODEL / CODEX_EFFORT / CODEX_TIER env vars; the scripts echo the effective values.
--sandbox read-only. Safe to invoke autonomously.
On network failure, check *.events.ndjson.stderr. Run reset.sh and retry.
Thread IDs persisted per-plan (no --last). Concurrent reviews don't collide.
Extra context -> {{EXTRA_PROMPT}}. Keep short.

Loop Shape


turn 1: start.sh -> REQUEST_CHANGES (A B C)
         address A B C
turn 2: resume.sh -> REQUEST_CHANGES (A B addressed, C stale, new D)
         address C D
turn 3: resume.sh -> APPROVED

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Codex Plan Review AI skill do?

Iterative Codex CLI review of a planning document

Why use Codex Plan Review on TypingMind?

Because you install it once and use it with any model. Codex Plan Review is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Codex Plan Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/PiLastDigit/TRIP-workflow/tree/master/skills/codex-plan-review. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Codex Plan Review?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Codex Plan Review?

As many as you like. As long as a model supports skills, you can use Codex Plan Review with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Codex Plan Review AI skill free?

It is published on GitHub by PiLastDigit. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Lbo Model

NousResearch

OrganizationPopular

Build leveraged buyout workbooks with IRR/MOIC in Excel.

Pptx Author

Build PowerPoint decks headless with python-pptx.

Pokemon Player

Play Pokemon via headless emulator + RAM reads.

Docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document',…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Codex Plan Review

Arguments

Execution

Notes

Loop Shape

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now