Stats
Actions
Tags
From Darkroom Engineering
Bridges Claude with OpenAI Codex CLI for delegating bulk work, reviewing uncommitted diffs, or asking read-only questions. Uses exec, review, and ask subcommands.
How this skill is triggered — by the user, by Claude, or both
Slash command
/darkroom:codexThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Invoke the OpenAI Codex CLI from inside a Claude session. Three subcommands map to three distinct use cases.
Invoke the OpenAI Codex CLI from inside a Claude session. Three subcommands map to three distinct use cases.
All subcommands are called via:
bun "$HOME/.claude/src/scripts/codex-run.ts" <subcommand> [args]
bun "$HOME/.claude/src/scripts/codex-run.ts" exec "the full task description"
Runs Codex in a workspace-write sandbox. Use this when a task is:
Quota routing: Codex is metered by messages per ~5-hour window, not by tokens. Hand it one big complete task, not a sequence of small steps. A single exec call for a whole feature costs the same quota as one exec call for a single file.
After exec returns, ALWAYS review Codex's diff before trusting it:
git diff
Then run the proof gate:
bun run proof
bun "$HOME/.claude/src/scripts/codex-run.ts" review
Runs in a read-only sandbox. Codex reads the repo itself (git diff, git status) and reports findings by severity (HIGH / MEDIUM / LOW), covering correctness bugs, security issues, and obvious quality problems.
Use this after you have finished a diff and want a second opinion from a different model family. Codex and Claude have different blind spots — cross-model review catches what Opus self-review misses. This is the primary reason to prefer review over asking Claude to review its own output.
bun "$HOME/.claude/src/scripts/codex-run.ts" ask "your question here"
Runs in a read-only sandbox. Use for quick factual questions, architecture opinions, or anything where you want a fast external perspective without making any changes.
exec a whole feature or module, not one function at a time.review and ask are read-only and cheap — use them freely as a cross-check.The script handles all availability states gracefully. On failure it prints guidance to stderr and exits 1. Possible states:
not-installed -- install Codex CLI and run codex loginunauthenticated -- run codex loginno-access -- plan entitlement issue; try codex logout && codex loginrate-limited -- usage window exhausted; retry after the ~5-hour resetunknown -- one-off error; safe to retryWhen any of these fire, Claude continues without Codex. The bridge is an enhancement, not a dependency.
npx claudepluginhub darkroomengineering/cc-settings --plugin darkroomRuns OpenAI Codex CLI as a subagent for second opinions, code reviews, and questions. Useful when you want a different AI model's perspective.
Delegates complex code generation, refactoring, architectural analysis, and review tasks to OpenAI's Codex CLI (GPT-5.3-codex models) via safe workflows with sandboxing and approvals. Activates on explicit triggers like 'use codex' or 'codex exec'.
Cross-model review using OpenAI Codex to independently verify plans or code diffs, iterating up to 5 rounds. Useful for architecture decisions, non-trivial refactors, and critical config changes.