Skill
attack-path-analysis
Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a security finding from source to sink and…
@cowork-osView SkillProductivity
Skill
/codex-cli
Run OpenAI Codex CLI as a background agent — detect, install, configure, and execute tasks via codex exec.
Install
$ npx -y skills add CoWork-OS/CoWork-OS --skill codex-cli --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/codex-cli
Context preview
The summary Claude sees to decide when to auto-load this skill.
Run OpenAI Codex CLI as a background agent — detect, install, configure, and execute tasks via codex exec.
SKILL.md
codex-cli.SKILL.mdname: codex-cli
description: "Run OpenAI Codex CLI as a background agent — detect, install, configure, and execute tasks via codex exec."
version: "1.0.0"
metadata:
author: CoWork OS Contributors <info@coworkosapp.com>
codex-cli
Purpose
Detect, install, configure, and run the OpenAI Codex CLI (`codex`) as an autonomous background agent for code editing, PR review, issue fixing, and one-shot automation tasks.
Routing
- Use when: User wants to run Codex CLI, asks for "codex agent", "spin up codex", "codex review", "codex fix", or wants to execute a coding task using the OpenAI Codex CLI specifically.
- Do not use when: The request is for planning, discussion, or non-executable output.
- Outputs: Task result from Codex CLI agent, or setup instructions if CLI is not installed/configured.
- Success criteria: Codex CLI executes the requested task and returns output, or user is guided to install/configure it.
Trigger Examples
Positive
- "Spin up a Codex agent to review PR #55"
- "Use Codex CLI to fix this bug"
- "Run codex on this issue"
- "Launch a codex agent"
- "codex exec: add error handling to the API"
Negative
- "Review this code" (generic — doesn't specify Codex CLI)
- "Explain how Codex works" (no execution needed)
- "Write a plan for this feature" (planning only)
Runtime Prompt
- Runtime prompt is defined directly in `../codex-cli.json`.
Read more
name: codex-cli description: "Run OpenAI Codex CLI as a background agent — detect, install, configure, and execute tasks via codex exec." version: "1.0.0" metadata: author: CoWork OS Contributors <info@coworkosapp.com>
codex-cli
Purpose
Detect, install, configure, and run the OpenAI Codex CLI (`codex`) as an autonomous background agent for code editing, PR review, issue fixing, and one-shot automation tasks.
Routing
- Use when: User wants to run Codex CLI, asks for "codex agent", "spin up codex", "codex review", "codex fix", or wants to execute a coding task using the OpenAI Codex CLI specifically.
- Do not use when: The request is for planning, discussion, or non-executable output.
- Outputs: Task result from Codex CLI agent, or setup instructions if CLI is not installed/configured.
- Success criteria: Codex CLI executes the requested task and returns output, or user is guided to install/configure it.
Trigger Examples
Positive
- "Spin up a Codex agent to review PR #55"
- "Use Codex CLI to fix this bug"
- "Run codex on this issue"
- "Launch a codex agent"
- "codex exec: add error handling to the API"
Negative
- "Review this code" (generic — doesn't specify Codex CLI)
- "Explain how Codex works" (no execution needed)
- "Write a plan for this feature" (planning only)
Runtime Prompt
- Runtime prompt is defined directly in `../codex-cli.json`.
Ships withcowork-os
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
Get the whole plugin
Stats
450
Stars
77
Forks
Active
Maintenance
TypeScript
Language
MIT
License
6d ago
Last commit
7mo ago
Created
Repo: CoWork-OS/CoWork-OS
Other skills on cowork-os.
@cowork-osView SkillSkill
deep-security-scan
Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide Codex Security scan. Run repeated independent repository-wide…
@cowork-osView SkillSkill
finding-discovery
Use when Codex is already in the finding-discovery phase of a security scan or the user explicitly asks to discover candidate security findings in a repository…
@cowork-osView SkillSkill
fix-finding
Use when the user explicitly asks to fix and verify a validated or plausible security finding. Do not use as the primary trigger for full PR, commit, branch,…
@cowork-osView SkillSkill
security-diff-scan
Use when the user asks for a security review of a pull request, commit, branch diff, working-tree patch, or other Git-backed change set.
@cowork-osView SkillSkill
security-scan
Use when the user asks for a repository-wide or scoped-path security scan.
@cowork-osView Skill