/codex
Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.
$ npx -y skills add Pythoughts-labs/claude-architect --skill codex --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.
- You can call itInvoke it directly when you want it.
- Slash command
/codex
Context preview
The summary Claude sees to decide when to auto-load this skill.
Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.
Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.
Repo: Pythoughts-labs/claude-architect
Other skills on claude-architect.
- /delegate
Let Claude Architect route a versioned implementation spec through the trusted MCP runtime, independently review the Candidate Artifact, record a decision, and integrate only accepted bytes. Use for implementation delegation, Producer selection, or commitment-boundary review.
Open skill - /subagent-driven-delegation
Execute an implementation plan with the Superpowers subagent-driven-development loop while every task is implemented by a verified Claude Architect Producer — isolated worktree, frozen Candidate Artifact, independent verification, fresh-context review, runtime-gated acceptance.
Open skill - /systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Open skill - /test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
Open skill - /verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Open skill