Kbediako/evergreen-codex-skills / skills/native-codex-coordination
native-codex-coordination
VerifiedChoose between solo work, native-agent execution, deliberation, evaluation, and waiting when the appropriate coordination workflow is unclear.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.1 KB |
| agents/openai.yaml | config | 236 B |
| references/app-task-waiting.md | markdown | 1.2 KB |
references/app-task-waiting.md
View on GitHub# App task and thread waiting
For a Codex app task or thread:
1. When the active runtime exposes `wait_threads`, call it directly with the exact task/thread ID. If the app event-wait tool is unavailable, report that missing capability; do not invent a callable tool or substitute an external monitor. Preserve every returned cursor unchanged and supply it to the next wait. Continue in the active turn by default.
2. Never route the task to `long-poll-wait`, a custom external awaiter, or another external-monitoring path.
3. Use a scheduled continuation only after verifying that scheduling is authorized, the next context can call `wait_threads` and is authorized for the task/thread, and that context can durably retain the cursor or reacquire and rebind it from preserved state.
4. After expiry, restart, or intervention, revalidate the task/thread ID and latest state, then reacquire and rebind the cursor before waiting again.
5. If the scheduled-context or rebinding proof is unavailable, return `needs-scheduled-handoff` with the task/thread ID, preserved cursor, latest state and timestamp, plus the exact host, tool, context, authorization, and cursor-reacquisition requirements.
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 |