VeryGoodOpenSource / VeryGoodOpenSource/vgv-wingspan
feat(plan): /plan-options multi-angle best-of-N planning
Nobody has claimed this yet.
- Dominant language
- Shell
- Stars
- 105
- Forks
- 15
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 2
Description
Problem. /plan produces a single plan from one pre-chosen approach; there's no best-of-N.
Proposal. Fan out lens planners (simplicity, risk, speed, maintainability) in parallel → judge against the success criteria → AskUserQuestion to pick or merge. Larger build; do once the success-criteria gate is stable.
Acceptance criteria.
- N competing plans written to
docs/plan/options/. - Judge ranks against success criteria + NON-GOALS.
- Winner handed to
/build.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by tracing the /plan workflow and its success-criteria gate, then inspect how plans are handed to /build. Use docs/plan/options/ as the specified output location and verify the acceptance criteria: competing options are written, ranked against success criteria and NON-GOALS, and the selected or merged winner reaches /build.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- shell
- Domain
- cli, documentation, tooling
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100