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/task-report.md
View on GitHub# <Task ID> report
STATUS: <ready_for_review | blocked | failed>
Role agent and rung: <crack_<role>, primary | fallback>
Workspace and baseline: <actual path and baseline>
Thread ID: <host-observed ID, if available>
## Changes
<Changed paths including untracked files, and behavior. List pre-existing changes separately.>
## Acceptance evidence
<For each acceptance criterion: implementation location, check/evidence location,
and observed result or explicitly missing evidence. This map guides review; it
is not self-approval. Include relevant failure/state-transition checks.>
## Verification evidence
<Each actual command, working directory, exit code, result, and log location.
Keep full logs on disk; summarize repeated passes and include failing assertions
with enough context to diagnose them.>
## Remaining risks or decisions
<Missing checks, limitations, and blockers. Never claim acceptance.>
## Resume checkpoint
<Completed steps, unfinished work, the last failure, and the exact next action.>
---
# Review record (reviewer role, then orchestrator)
Spec compliance: <pass | changes requested | blocked, with evidence>
Quality and security: <pass | changes requested | blocked, with evidence>
Orchestrator spot checks: <actual commands, or visual/runtime checks>
Routing evidence: <host or router metadata, never the worker's own claim>
Decision: <accepted | changes requested | escalated | blocked>
Review cycles on this rung: <count>
Integration status: <what is present in the dependent workspace>
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 |