Skip to content

dayfinggg/openai-codex-agent-skills / codex/skills/planning

planning

Verified

Breaks work into ordered, verifiable tasks before implementation. Use it whenever the user asks for a plan, a roadmap, or an estimate, when requirements or a spec must become tasks, when the work spans several modules, sessions, or agents, or when a task feels too large or vague to start. Skip it for a change whose scope and order are already obvious.

FileKindSize
SKILL.mdskill md9.2 KB
references/github-issues.mdmarkdown1.5 KB

references/github-issues.md

View on GitHub
# Planning with GitHub issues

Use this only when the user asks to turn work into GitHub issues, or the project workflow explicitly authorizes that tracker operation. Issue creation and editing change an external system. A local plan does not authorize those changes by itself.

- Read the project rules and the existing issues first. Check `gh --version` and the installed `gh issue create --help` and `gh issue edit --help`; flags and dependency support vary by CLI and GitHub service.
- Write each issue as one independently verifiable vertical slice. State the user-visible behavior, acceptance criteria, focused check, prerequisites, and out-of-scope behavior. Link prerequisites as blockers only when the installed CLI and target service support the relationship.
- Create or identify prerequisites before dependent issues so each blocker reference resolves to the right issue. If the service lacks dependency links, write a clear `Blocked by` section in the issue body.
- Check existing parent issues and incomplete plans before adding or changing children. Do not overwrite another plan or close unrelated issues to make room.
- Treat `gh issue` numbers, GitHub API database IDs, sub-issue limits, and Enterprise Server support as distinct. Use the CLI's documented commands where possible, and check the current official service documentation before using API endpoints or relying on limits.
- After creating issues, reread them and verify each title, body, parent, blocker, and open state. Report the issue references and any relationship the service could not represent.
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: 471kUpdated 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