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.
templates/checkpoint.md
View on GitHub# <Feature> orchestrator checkpoint
A current status record, not an append-only transcript: replace stale lines.
Goal and scope: <current agreed result>
Spec and plan: <paths>
Workspace and baseline: <path, branch/commit, and preserved changes>
Roles in use: <role -> model from doctor; which models are runtime-verified, and the evidence>
## Accepted work and fixed contracts
<Task IDs, decisions, and integration status.>
## Active or unfinished work
<Task IDs, wave, role agent and rung, worker thread IDs, worktree paths, file
ownership, latest report, and review state.>
## Verification and blockers
<What ran, what failed, what is unverified, and open risks.>
## Next actions
<The exact next task, review, or command, and whether to resume a worker or start a new one.>
## User authorization still relevant
<Build scope, delegation or provider restrictions, and Git and production limits.>
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: 471k | 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 |