cskwork/supergoal-skill / skills/supergoal
supergoal
UnverifiedRoute objective-driven development, verification, planning, "teach/explain", codebase learning, and skill evaluation through the Supergoal workflow. Use when Supergoal is requested or an autonomous delivery workflow is needed.
templates/PLAN.md
View on GitHub# PLAN - <topic>
Frozen plan. A fresh-context implementer reads ONLY this file (plus the latest `R-LOOP.md` section on
re-entry) and builds it - the plan must be self-sufficient. Frozen after approval; changes append a
dated `## Amendment`.
## Approval
- Status: pending | approved-by-user | auto-approved
- Record: <timestamp; the user's OK verbatim, or "autonomous run (<harness-eval|background|pre-authorized>): auto-approved">
## Interview
- <question -> chosen answer or approved assumption -> the decision it drove; or one line stating why the skip was safe>
## Intent
- Goal / constraints / tradeoffs / rejected approaches:
- Completion promise: promised outcome, required proof, stop condition, `max_iterations` (default 3)
## Steps
1. <exact file paths, symbols, expected diff shape - plain language>
## Acceptance checklist
- [ ] <copied from GOAL.md Success Criteria, including edge-case/resilience criteria - the builder
reads ONLY this file, so the checklist must be complete here>
## Tools & Skills
- <test command(s), dev server, agent-browser, fallback driver, db client, skills to load>
## Verification strategy
- Before proof: <what proves the start state>
- Step -> GOAL.md criterion: <step n -> criterion #>
- Trusted commands: `<cmd>` (frozen_repo | evaluator_owned)
## Grounding ledger
<compact: question -> answer/source -> decision (reference/plan-grounding.md, reference/interview.md)>
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: 472k | 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 |