Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From cli-wrapper
Wrapped access to Codex CLI (OpenAI). Captures codex --help, caches subcommands, validates flags, post-processes output. Use for ANY Codex CLI invocation from Claude Code or other harnesses. Saves ~85% tokens vs raw codex output.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cli-wrapper:codex-cliThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Wrapped Codex CLI access. Digest-driven, token-optimized.
Wrapped Codex CLI access. Digest-driven, token-optimized.
/codex-cli invoke <args> — run codex command with validated flags
/codex-cli explain <cmd> — show what a codex subcommand does
/codex-cli audit — token savings report
/codex-cli wrap — rebuild digest from live codex --help
Codex CLI help output ~5KB+. Digest = ~400 bytes. 92% savings.
| Phase | Raw | Wrapped |
|---|---|---|
| Discovery | 5.0KB | 0.4KB |
| Invocation | variable | filtered + deduped |
| Flag validation | trial/error | first-try via digest |
/codex-cli invoke --version
/codex-cli invoke config list
/codex-cli invoke agent run <name>
/codex-cli invoke plugin list
.claude/cli-wrappers/codex.json — auto-refreshed on /codex-cli wrap
When Claude Code delegates to Codex CLI, always use this wrapper.
The wrapper agent codex-cli handles the full delegation lifecycle.
npx claudepluginhub andersonlimahw/lemon-ai-hub --plugin cli-wrapperGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.