Ask Codex

Community

ryoppippi

ask-codex

Gets a Codex second opinion or delegates bulky work to a Codex subagent. Use before a significant approach is settled, or instead of reading pages and long output here.

Overview

Publisher	ryoppippi
Repository	`dotfiles`
Skill name	`ask-codex`
Stars	263
Forks	5
Bundled files	Instructions only
License	MIT
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.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by ryoppippi on GitHub. Read the source before you install it.

Installation

Install the Ask Codex 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.
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/ryoppippi/dotfiles.git /tmp/dotfiles
mkdir -p .claude/skills
cp -r /tmp/dotfiles/agents/skills/ask-codex .claude/skills/ask-codex

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

Use it in TypingMind

Enable Ask Codex 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 Ask Codex 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 Ask Codex 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.

Ask Codex

This skill is shared by Codex Desktop, Codex CLI, and other agents. Choose the execution path that matches the current agent:

Inside Codex (Desktop or CLI): delegate to a native subagent. Never run codex exec from here; that starts a nested Codex process.
Outside Codex: use the Codex CLI path below for an independent agent.

Both paths take a self-contained prompt: the subagent sees none of this conversation, so whatever it cannot infer has to be in the prompt.

Native subagent path

Use one native subagent for either job. Ask it to return the requested facts with citations (URL or file:line), and ask for verbatim quotes where exact spelling matters.

For a second opinion, ask for an independent assessment, then compare it with your own reading and preserve disagreements in the response. For delegated grunt work, ask for the small conclusion rather than forwarding the whole transcript.

The repository's Codex configuration sets native subagents to gpt-5.6-luna with max reasoning and the fast service tier. Keep those defaults unless the user requests another model or effort.

Codex CLI path

Use this path only outside Codex:

sh
codex exec "<question>"

Leave the model alone — the reasoning effort in Codex's own config is what makes the answer worth having. Treat the reply as one data point: compare it against your own reading of the codebase, report both views to the user with the disagreements intact, and prefer established project patterns where they conflict.

Delegated grunt work

sh
codex exec --skip-git-repo-check --ephemeral -m gpt-5.6-luna "<task>"

For work whose output is bulky but whose conclusion is small: web search, page reading, codebase investigation, summarising long output, drafting a commit message from a diff. A cheap model is the point — the subscription pays for it and only the answer costs tokens here. codex exec --help carries the rest; reach for -o to capture the final message alone, and --sandbox/--add-dir to widen what it may touch.

Measured, and not visible in the help output:

Keep model_reasoning_effort at medium or above. At low it answered a "latest release version" search from stale knowledge.
Never --disable multi_agent. Native web search runs through it, so disabling it makes a search task hang indefinitely with no tool call.
Shell commands only reach the network under --sandbox workspace-write with -c sandbox_workspace_write.network_access=true. The native web search needs neither.
exa cannot run there at all: no sandbox mode reaches its 1Password key, so run exa in this session. ax and tgrab live in ~/.agents/skills/web-fetch/ — prepend that to PATH when the task needs them.

Briefing it:

Say which facts to return, and demand a citation for each — a URL, or a file:line.
Ask for verbatim quotes wherever exact spelling matters: API options, flags, version numbers. A digest paraphrases them away.
The web-fetch skill holds the search tool selection; name the choice rather than leaving it open.

Frequently asked questions

What does the Ask Codex AI skill do?

Gets a Codex second opinion or delegates bulky work to a Codex subagent. Use before a significant approach is settled, or instead of reading pages and long output here.

Why use Ask Codex on TypingMind?

Because you install it once and use it with any model. Ask Codex 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 Ask Codex in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ryoppippi/dotfiles/tree/main/agents/skills/ask-codex. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ask Codex?

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 Ask Codex?

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

Is the Ask Codex AI skill free?

Yes. It is published on GitHub by ryoppippi under the MIT license. 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

Systematic Debugging

obra

CommunityPopular

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

Test Driven Development

obra

CommunityPopular

Use when implementing any feature or bugfix, before writing implementation code

Using Git Worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Using Superpowers

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Ask Codex

Native subagent path

Codex CLI path

Delegated grunt work

Frequently asked questions

Related AI Skills

Set up your own AI workspace now