keithhegit/ultra-orchestration / skills-vnext/ultra-planning
ultra-planning
VerifiedRigid decision-complete planning for Codex Ultra vNext. Use after intake, brainstorming, or OpenSpec bridge whenever work spans multiple files, roles, phases, or risk boundaries and must be turned into review-ready TaskManifest and WorkPackage artifacts with explicit dependencies, owned paths, acceptance checks, retry assumptions, and serial versus parallel execution rules.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.8 KB |
| agents/openai.yaml | config | 223 B |
| references/planning-anti-patterns.md | markdown | 922 B |
| references/planning-checklist.md | markdown | 529 B |
| references/planning-workflow.md | markdown | 833 B |
| references/work-package-examples.md | markdown | 1.1 KB |
references/work-package-examples.md
View on GitHub# Work Package Examples
## Example 1: Multi-File Feature
Task:
- add workspace-level model defaults to settings UI
Good plan shape:
- `TaskManifest`
- goal: add editable workspace defaults
- success criteria: value persists, UI shows current value, validation is explicit
- owned paths: settings UI, config store, shared types
- `WorkPackage 1`
- role: planner or worker
- scope: shared type and config store changes
- owned paths: `src/config/*`, `src/types/*`
- `WorkPackage 2`
- role: worker
- scope: settings UI
- owned paths: `src/ui/settings/*`
- serial note
- UI package depends on shared type package
## Example 2: OpenSpec Change
Task:
- implement the first slice of `workspace-model-defaults`
Good route:
1. `openspec-ultra-bridge-v2` reads proposal, design, tasks, and bridge assets
2. `ultra-planning` turns that into `TaskManifest` and `WorkPackage` items
3. planning marks:
- current slice
- owned paths for the slice
- review target
- QA scenario target
Good output:
- one execution-ready `TaskManifest`
- one or more `WorkPackage` items for the current slice only
- explicit note if later slices depend on this one
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 |