Windsurf rules

1---
2name: audit-plan
3model: sonnet
4description: "Evaluate an incoming project plan against bigpowers principles and conventions, surface gaps, and produce a READY/NOT READY verdict before engagement begins. Use when a new project arrives, when adapting a foreign plan, or before running seed-conventions on an unfamiliar codebase."
5---
6 
7# Audit Plan
8 
9> **HARD GATE** — Do NOT start build skills (kickoff-branch, develop-tdd) until audit-plan returns a READY verdict. A plan missing test commands, scope boundaries, or success criteria will produce drift and rework downstream.
10 
11Assess an incoming project plan for alignment with bigpowers principles, identify what's missing, and produce a structured readiness report before any skill execution begins.
12 
13## Three lenses
14 
15### 1. Principles alignment
16- Are stories vertical slices (not horizontal layers)?
17- Is scope bounded — explicit in_scope + out_of_scope?
18- Are success criteria defined (how do we know we're done)?
19- Are HARD GATE candidates identifiable (critical decision points)?
20- Is there a domain language / ubiquitous terminology?
21 
22### 2. Conventions completeness
23- Does `CLAUDE.md` or `AGENTS.md` exist?
24- Does `CONVENTIONS.md` exist?
25- Is the `specs/` directory layout in place?
26- Are commit conventions documented (Conventional Commits)?
27- Is the git workflow mode identified (`solo-git` | `team-pr`)?
28 
29### 3. Bigpowers pre-flight (must all be answered before build)
30| Question | Why |
31|----------|-----|
32| What is the **test command**? | `develop-tdd` verify steps require it |
33| What is the **build command**? | `verify-work` mechanical gate |
34| What is the **lint command**? | `audit-code` lint gate |
35| What is the **typecheck command**? | `verify-work` typecheck gate |
36| What **CI platform** is in use? | `wire-ci` configuration |
37| **Solo or team**? | `release-branch` integration mode |
38| Primary **language + framework**? | model routing + conventions |
39| **Greenfield or existing** codebase? | determines whether to run `seed-conventions` or `migrate-spec` first |
40 
41## Process
42 
431. **Ingest the plan** — accept a file path, pasted PRD text, or existing `specs/` artifacts. Read `CLAUDE.md` and `CONVENTIONS.md` if present.
44 
452. **Score each lens** — for every item above, mark:
46   - ✅ Present and adequate
47   - ⚠️ Present but incomplete — note what's missing
48   - ❌ Absent
49 
503. **Close gaps conversationally** — for each ❌ or ⚠️, ask one question at a time. Record each answer before moving to the next.
51 
524. **Write `specs/PLAN-AUDIT_LATEST.md`**:
53 
54```markdown
55# Plan Audit — <project>
56**Date:** YYYY-MM-DD · **Verdict:** READY | NOT READY
57 
58## Principles Alignment
59| Check | Status | Note |
60| Vertical slices | ✅ | 4 stories, each shippable |
61| Scope bounded | ⚠️ | in_scope present; out_of_scope missing |
62 
63## Conventions Completeness
64| Check | Status | Note |
65 
66## Pre-flight Answers
67| Command | Value |
68| test | `npm test` |
69| build | `npm run build` |
70 
71## Open Gaps
72- [ ] Add out_of_scope to scope definition (run scope-work)
73- [ ] Create CLAUDE.md (run seed-conventions)
74 
75## Verdict
76READY — proceed with survey-context
77NOT READY — N gaps remain; close before proceeding
78```
79 
805. **Recommend next skill**:
81   - READY → `survey-context`
82   - Needs bootstrapping → `seed-conventions`
83   - Needs spec elaboration → `elaborate-spec`
84   - Has foreign spec format → `migrate-spec`
85   - Plan assumptions need challenging → `grill-me`
86 
87## Verify
88 
89→ verify: `test -f specs/PLAN-AUDIT_LATEST.md && grep -q Verdict specs/PLAN-AUDIT_LATEST.md`
90