Skip to content

dayfinggg/openai-codex-agent-skills / codex/skills/orchestration

orchestration

Verified

Plan or coordinate explicitly authorized multi-agent work, including worker briefs, model selection, independent workstreams, integration, and review rounds.

FileKindSize
SKILL.mdskill md1.5 KB
references/delegation-brief.mdmarkdown1.1 KB
references/other-agents.mdmarkdown2.2 KB
references/review-loop.mdmarkdown1.6 KB

references/delegation-brief.md

View on GitHub
# Define the worker contract

Delegate when authorized and when independent work or a fresh review will save time or catch blind spots. Keep dependent or small work in the current session. Assign separate files or an isolated checkout to each writer, and leave concurrent user work untouched.

Check the actual host tool for available models, effort, isolation, and completion signals. Keep the inherited model unless the user or runtime calls for another one. Use a fresh context when an independent reviewer must not see the author's reasoning. Use a fork only when the worker needs the conversation.

Give the goal, precise paths, work and write scope, relevant user constraints and rules, passing check, and stop conditions. State which external actions are out of scope. Give all workers the same shared capacity constraints and a way to take turns at heavy jobs. Ask for findings with file and line, check results, and any files or state changed. Pass long inputs as paths or narrow excerpts.

Use the runtime's completion mechanism. Continue independent work while workers run. Check their evidence and run the combined check before reporting the integrated result.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall