ethanplusai/codex-on-crack / plugins/codex-on-crack/skills/crack
crack
UnverifiedLead substantial Codex builds with one configured implementation worker and lead acceptance. Use when the user requests codex-on-crack, names a model to delegate work to, asks to run subagents through Claude, or requests a lead/worker split. Keep host-only work direct; honor explicit external model choices. Workers must not invoke this orchestrator.
scripts/trial.mjs
View on GitHub#!/usr/bin/env node
import { parseArgs } from 'node:util';
import { CrackError, failure } from './lib/io.mjs';
import { trial } from './lib/trial.mjs';
const COMMON = ['dir', 'format'];
const ALLOWED = {
start: [...COMMON, 'id', 'task', 'mode', 'category', 'lead-model', 'worker-model', 'lead-effort', 'worker-effort', 'acceptance'],
finish: [...COMMON, 'id', 'quality', 'checks', 'rework-minutes', 'notes', 'root-session', 'session-log'],
show: [...COMMON, 'id'], list: COMMON,
};
const USAGE = 'Usage: trial.mjs <start|finish|show|list> --dir DIR [--id ID] [--format json|markdown]. Start: --task TEXT --mode plain|orchestrated --category CATEGORY --lead-model MODEL [--lead-effort EFFORT] [--worker-model MODEL ...] [--worker-effort EFFORT ...] --acceptance TEXT. Finish: --quality usable|needs-fixes|unusable --checks passed|failed|not-run --rework-minutes N [--notes TEXT] [--root-session ID --session-log PATH ...].';
let result; let format = 'json';
try {
const [command, ...args] = process.argv.slice(2);
if (!ALLOWED[command]) throw new CrackError('usage', 'Choose start, finish, show, or list.', USAGE);
let values;
try { ({ values } = parseArgs({ args, strict: true, options: Object.fromEntries(ALLOWED[command].map((key) => [key,
{ type: 'string', ...(['worker-model', 'worker-effort', 'session-log'].includes(key) ? { multiple: true } : {}) }])) })); }
catch { throw new CrackError('usage', 'Invalid trial arguments.', USAGE); }
format = values.format ?? 'json';
if (!['json', 'markdown'].includes(format)) throw new CrackError('usage', '--format must be json or markdown.', USAGE);
result = trial(command, values);
} catch (error) { result = failure(error); }
process.stdout.write(result.ok && format === 'markdown' ? `${result.markdown}\n` : `${JSON.stringify(result, null, 2)}\n`);
process.exitCode = result.ok ? 0 : 2;
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |