Cursor rule

1---
2description: "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."
3alwaysApply: false
4---
5 
6# Audit Plan
7 
8> **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.
9 
10Assess an incoming project plan for alignment with bigpowers principles, identify what's missing, and produce a structured readiness report before any skill execution begins.
11 
12## Three lenses
13 
14### 1. Principles alignment
15- Are stories vertical slices (not horizontal layers)?
16- Is scope bounded — explicit in_scope + out_of_scope?
17- Are success criteria defined (how do we know we're done)?
18- Are HARD GATE candidates identifiable (critical decision points)?
19- Is there a domain language / ubiquitous terminology?
20 
21### 2. Conventions completeness
22- Does `CLAUDE.md` or `AGENTS.md` exist?
23- Does `CONVENTIONS.md` exist?
24- Is the `specs/` directory layout in place?
25- Are commit conventions documented (Conventional Commits)?
26- Is the git workflow mode identified (`solo-git` | `team-pr`)?
27 
28### 3. Bigpowers pre-flight (must all be answered before build)
29| Question | Why |
30|----------|-----|
31| What is the **test command**? | `develop-tdd` verify steps require it |
32| What is the **build command**? | `verify-work` mechanical gate |
33| What is the **lint command**? | `audit-code` lint gate |
34| What is the **typecheck command**? | `verify-work` typecheck gate |
35| What **CI platform** is in use? | `wire-ci` configuration |
36| **Solo or team**? | `release-branch` integration mode |
37| Primary **language + framework**? | model routing + conventions |
38| **Greenfield or existing** codebase? | determines whether to run `seed-conventions` or `migrate-spec` first |
39 
40## Process
41 
421. **Ingest the plan** — accept a file path, pasted PRD text, or existing `specs/` artifacts. Read `CLAUDE.md` and `CONVENTIONS.md` if present.
43 
442. **Score each lens** — for every item above, mark:
45   - ✅ Present and adequate
46   - ⚠️ Present but incomplete — note what's missing
47   - ❌ Absent
48 
493. **Close gaps conversationally** — for each ❌ or ⚠️, ask one question at a time. Record each answer before moving to the next.
50 
514. **Write `specs/PLAN-AUDIT_LATEST.md`**:
52 
53```markdown
54# Plan Audit — <project>
55**Date:** YYYY-MM-DD · **Verdict:** READY | NOT READY
56 
57## Principles Alignment
58| Check | Status | Note |
59| Vertical slices | ✅ | 4 stories, each shippable |
60| Scope bounded | ⚠️ | in_scope present; out_of_scope missing |
61 
62## Conventions Completeness
63| Check | Status | Note |
64 
65## Pre-flight Answers
66| Command | Value |
67| test | `npm test` |
68| build | `npm run build` |
69 
70## Open Gaps
71- [ ] Add out_of_scope to scope definition (run scope-work)
72- [ ] Create CLAUDE.md (run seed-conventions)
73 
74## Verdict
75READY — proceed with survey-context
76NOT READY — N gaps remain; close before proceeding
77```
78 
795. **Recommend next skill**:
80   - READY → `survey-context`
81   - Needs bootstrapping → `seed-conventions`
82   - Needs spec elaboration → `elaborate-spec`
83   - Has foreign spec format → `migrate-spec`
84   - Plan assumptions need challenging → `grill-me`
85 
86## Verify
87 
88→ verify: `test -f specs/PLAN-AUDIT_LATEST.md && grep -q Verdict specs/PLAN-AUDIT_LATEST.md`
89