Menu
Orchestrate CLI coding agents (codex, grok, aider, etc.) so agents write ALL implementation code while the orchestrator plans, reviews diffs, runs tests, and commits. Use for any implementation task in a multi-agent setup.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Cheap-model adversarial verification pass for the end of every implementation phase and before any merge. Framing beats model tier — a low-effort model with the right question finds real bugs the expensive authoring model missed.
Eight falsifiable rules for prompting CLI coding agents and review lanes, each derived from an observed failing-form vs working-form pair. Use when composing any prompt for a coding agent or reviewer fanout.
Discipline for algorithm and ranking changes — hand-designed signals are usually wrong in direction, not just magnitude. Build an offline backtest first; the backtest script becomes the behavior spec; numeric gates decide mergeability.
The laws that keep plausible-but-broken AI-generated code away from main, derived from a real 104-PR bulk-merge disaster. Apply to every merge, every "done" claim, and every batch operation.
Treat memory files, summaries, handoff docs, and other agents' reports as unverified claims. Inheritance tells you where to look; only the current checkout tells you what's true. Apply whenever acting on knowledge you did not derive this session.
| name | cli-agent-driver |
| description | Orchestrate CLI coding agents (codex, grok, aider, etc.) so agents write ALL implementation code while the orchestrator plans, reviews diffs, runs tests, and commits. Use for any implementation task in a multi-agent setup. |
Division of labor: the orchestrating model never writes implementation code. A CLI coding agent writes it; the orchestrator reviews the diff, runs the tests, and commits. This keeps an independent reviewer in the loop for every line, and makes model choice per-step (expensive model frames, cheap model executes).
codex exec --sandbox workspace-write "<prompt>" < /dev/null — the < /dev/null matters: without it codex can hang waiting on stdin).grok --always-approve -p "<prompt>").After every agent run, before committing:
git add ..If the agent fails twice on a step: do NOT write the code yourself. Re-scope into smaller prompts (single file, exact insertion point, expected diff shape) and retry. See skill agent-prompt-doctrine for what actually changes outcomes.
A driver's final report contains: commit list with hashes, per-step agent-vs-review notes, baseline-vs-final test results, deviations from plan (reported, never silently absorbed), open questions.