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-wrapperWrapped access to Claude Code CLI. Captures claude --help, caches subcommands, validates flags against pre-built digest, post-processes output for minimal token consumption. Use for ANY Claude Code CLI invocation from this or other harnesses. Saves ~85% tokens vs raw claude help/output.
Delegates tasks to OpenAI Codex CLI from agent environments. Covers installation checks, prompt execution, session resume, file/image input, and image output.
Delegates coding tasks to OpenAI Codex CLI for code review, refactoring, CI fixes, and feature implementation.