Agent skill · Design & Presentation

codex

Invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. Trigger phrases include "use codex", "ask codex", "run codex", "call codex", "codex cli", "GPT-5 reasoning", "OpenAI reasoning", or when users request complex implementation challenges, advanced reasoning, architecture design, or high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.

majiayu000github.com/majiayu000GitHub ↗
codexclaude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill codex-alchimie-di-circe-extractor-desktop-ap-2 --agent codex

Same command for any agent — swap --agent for claude-code, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 27 KB
Bundled scripts: none
Version: 2.1.0
Path: skills/ai-llm/codex-alchimie-di-circe-extractor-desktop-ap-2/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Implements a Codex-based assistant that routes requests to a code-focused or general task model, and enforces the non-interactive codex exec workflow for all invocations. It supports explicit edit semantics to switch sandbox modes, session continuation, and a fallback model chain for availability.

How it works

  • Detects whether the task is code-related or general and selects the appropriate Codex model: use gpt-5.2-codex for code tasks, or gpt-5.2 for general tasks. Fallbacks exist (gpt-5.2 → gpt-5.1 → gpt-5.1-codex-max or gpt-5.1).
  • Enforces non-interactive execution via codex exec for all invocations; interactive codex is explicitly prohibited.
  • Uses a sandbox model: default read-only; switch to workspace-write only when the user explicitly requests editing (e.g., phrases like edit/modify/write).
  • Defaults include model_reasoning_effort=xhigh and web_search_request enabled; supports explicit edit prompts to grant workspace-write access.
  • Provides a structured CLI command pattern for code tasks and general tasks, with explicit examples illustrating read-only vs. edit modes.
  • Includes a session continuation workflow: resume using codex exec resume --last or by session-id, with guidance on when to start fresh vs continue.

When to use it

Use this skill when the user explicitly mentions Codex or requests high-reasoning coding help, architecture design, or iterative development requiring Codex collaboration. It should trigger for complex implementation challenges or requests for advanced model reasoning and continued Codex sessions.

What it can touch

  • Commands and tools: codex exec and codex resume.
  • Models: gpt-5.2-codex, gpt-5.2, gpt-5.1-codex-max, gpt-5.1.
  • Sandbox modes: read-only, workspace-write.
  • Configuration: model_reasoning_effort (e.g., xhigh), model_verbosity, --enable web_search_request.

Caveats

  • Requires Codex CLI v0.71.0+ and appropriate subscription.
  • Interactive mode with codex is not allowed; must use codex exec for non-interactive automation.
  • Some flags available only in interactive mode may not be usable in exec mode; use provided alternatives where applicable.
  • Default reasoning effort is set to xhigh for maximum capability.
From the SKILL.md

# Codex: High-Reasoning AI Assistant for Claude Code --- ## DEFAULT MODEL: Task-Based Model Selection with Read-Only Default **Codex uses task-based model selection. Sandbox is `read-only` by default - only use `workspace-write` when user explicitly requests file editing.** | Task Type | Model | Sandbox (default) | Sandbox (explicit edit) | |-----------|-------|-------------------|------------------------| | Code-related tasks | `gpt-5.2-codex` | read-only | workspace-write | | General tasks | `gpt-5.2` | read-only | workspace-write | - **Code-related tasks**: Use `gpt-5.2-codex` - optimized for agentic coding (56.4% SWE-Bench Pro) - **General tasks**: Use `gpt-5.2` - high-reasoning general model - **Sandbox default**: Always `read-only` unless user explicitly requests editing - **Explicit editing**: Only when user says "edit", "modify", "write changes", etc., use `workspace-write` - Always use `-c model_reasoning_effort=xhigh` for maximum capability ```bash # Code task (read-only default) codex exec -m gpt-5.2-codex -s read-only \ -c model_reasoning_effort=xhigh \ "analyze this function implementation" # General task (read-only default) codex exec -m gpt-5.2 -s read-only \ -c mode

What's inside
Steps it walks through
  1. DEFAULT MODEL: Task-Based Model Selection with Read-Only Default
  2. Model Fallback Chain
  3. CRITICAL: Always Use codex exec
  4. IMPORTANT: Interactive vs Exec Mode Flags
  5. Trigger Examples
  6. When to Use This Skill
  7. How It Works
  8. Detecting New Codex Requests
  9. Bash CLI Command Structure
  10. Model Selection Logic
  11. Default Configuration
  12. CLI Flags Reference
  13. Configuration Parameters
  14. Model Selection Guide
Ships with 1 file
  • metadata.json
Commands it runs
Code task (read-only default)
codex exec -m gpt-5.2-codex -s read-only \
General task (read-only default)
codex exec -m gpt-5.2 -s read-only \
Code task with explicit edit request
codex exec -m gpt-5.2-codex -s workspace-write \
General task with explicit edit request
codex exec -m gpt-5.2 -s workspace-write \
CORRECT - works in codex exec
codex exec --enable web_search_request "research topic"
More from claude-skill-registry
All skills →
descriptive-statisticsSummarizing and visualizing data through measures of center, spread, shape, and position. Covers…Data & Analyticsperplexity-researcher-reasoning-proHighest level of research and reasoning capabilities for complex decision-making with significant…OtherretroBrutally honest engineering retrospective. Analyzes git history for what actually happened — not…Data & AnalyticsanalyzeUniversal multi-perspective analyzer for any topic, file, idea, or decision. Extract key points…Otherarize-prompt-optimizationINVOKE THIS SKILL when optimizing, improving, or debugging LLM prompts using production trace data…Data & Analyticscellxgene-contextGuide for integrating CellxGene Census single-cell data with ENCODE bulk experiments. Use when…Data & Analytics
About this skill
What does the codex skill do?

Invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. Trigger phrases include "use codex", "ask codex", "run codex", "call codex", "codex cli", "GPT-5 reasoning", "OpenAI reasoning", or when users request complex implementation challenges, advanced reasoning, architecture design, or high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill codex-alchimie-di-circe-extractor-desktop-ap-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.