start-vibing 4.4.11 → 4.4.12

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/package.json +1 -1
  2. package/template/CLAUDE.md +78 -57
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "start-vibing",
3
- "version": "4.4.11",
3
+ "version": "4.4.12",
4
4
  "description": "Setup Claude Code with 9 plugins, 6 community skills, and 8 MCP servers. Parallel install, auto-accept, superpowers + ralph-loop. e2e-audit 0.2.0 refactor (skill-only, no agents): SessionStart hook + slash command make the skill keyword-invokable (\"e2e audit\", \"roda o e2e\", \"integration test\", \"test coverage gaps\"). Source-first discovery via detect-stack, discover-routes (Next app/pages/Remix/SvelteKit/Nuxt/Astro), discover-api-surface (HTTP handlers, tRPC procedures, GraphQL, server actions, middleware auth), inventory-existing-tests (preserve prior corpus + sha256 drift hash), and detect-uncovered (branch-diff vs origin/main finds changes not covered by existing specs). Report-then-ask between mapping and Playwright run; post-run-feedback report before writing findings. SHOT+TRACE+ASSERT+SOURCE evidence quad per non-meta finding; meta rules (coverage-gap-*, uncovered-*, test-drift, stack-detect, post-run-feedback) exempt. verify-audit.sh enforces schema + quad. Generic (no project leakage). super-design 0.7.0 carries over.",
5
5
  "type": "module",
6
6
  "bin": {
package/template/CLAUDE.md CHANGED
@@ -18,6 +18,26 @@ UPDATE THIS WITH YOUR PROJECT DESCRIPTION
18
18
 
19
19
  ---
20
20
 
21
+ ## Language Policy (HARD RULE)
22
+
23
+ > **ENGLISH ONLY — for everything Claude produces — UNLESS the user explicitly asks for another language in the current request.**
24
+
25
+ This applies to **every** output, with **no exceptions** beyond an explicit user override:
26
+
27
+ - Chat replies, status updates, summaries, questions back to the user
28
+ - Code (identifiers, variables, function/class names, type names)
29
+ - Comments, JSDoc, docstrings
30
+ - Commit messages, PR titles, PR descriptions, branch names
31
+ - Documentation (`/docs/**`, README, CLAUDE.md updates, changelogs, ADRs)
32
+ - Test names, error messages, log messages, CLI help strings
33
+ - File and folder names, configuration keys
34
+
35
+ The user may write to Claude in Portuguese, Spanish, or any other language — **Claude still responds and writes in English** unless the user explicitly says e.g. "responda em português", "write this in Spanish", "use PT-BR for the docs". An override applies **only to the current request**; revert to English on the next turn unless re-confirmed. Mixing English + another language in the same output is forbidden.
36
+
37
+ If unsure whether a request is an override, default to English and ask one short clarifying question.
38
+
39
+ ---
40
+
21
41
  ## Stack
22
42
 
23
43
  | Component | Technology |
@@ -87,17 +107,17 @@ project-root/
87
107
 
88
108
  ## Key Plugins (9 installed)
89
109
 
90
- | Plugin | Purpose | Invocation |
91
- |--------|---------|------------|
92
- | **superpowers** | TDD, debugging, brainstorming, planning | Auto + `/brainstorming`, `/execute-plan` |
93
- | **ralph-loop** | Iterative autonomous dev loop | `/ralph-loop "task" --max-iterations 10` |
94
- | **context7** | Auto library docs (replaces MCP) | Auto-invokes on library mentions |
95
- | **code-simplifier** | Refine code quality post-implementation | `/simplify` or ask Claude |
96
- | **typescript-lsp** | Type diagnostics, go-to-def | Auto (LSP server) |
97
- | **security-guidance** | OWASP vulnerability scan | Auto (PreToolUse hook) |
98
- | **code-review** | PR analysis | `/code-review` |
99
- | **commit-commands** | Git commit, push, PR | `/commit` |
100
- | **frontend-design** | Production-grade UI design | `/frontend-design` |
110
+ | Plugin | Purpose | Invocation |
111
+ | --------------------- | --------------------------------------- | ---------------------------------------- |
112
+ | **superpowers** | TDD, debugging, brainstorming, planning | Auto + `/brainstorming`, `/execute-plan` |
113
+ | **ralph-loop** | Iterative autonomous dev loop | `/ralph-loop "task" --max-iterations 10` |
114
+ | **context7** | Auto library docs (replaces MCP) | Auto-invokes on library mentions |
115
+ | **code-simplifier** | Refine code quality post-implementation | `/simplify` or ask Claude |
116
+ | **typescript-lsp** | Type diagnostics, go-to-def | Auto (LSP server) |
117
+ | **security-guidance** | OWASP vulnerability scan | Auto (PreToolUse hook) |
118
+ | **code-review** | PR analysis | `/code-review` |
119
+ | **commit-commands** | Git commit, push, PR | `/commit` |
120
+ | **frontend-design** | Production-grade UI design | `/frontend-design` |
101
121
 
102
122
  ### Superpowers Workflow (USE THIS)
103
123
 
@@ -121,12 +141,12 @@ Claude works autonomously until the task is complete or hits the iteration limit
121
141
 
122
142
  ## Agent System (4 Subagents)
123
143
 
124
- | Agent | Purpose |
125
- |-------|---------|
126
- | **research-web** | Researches best practices before new features |
127
- | **commit-manager** | Manages git commits, conventional format |
128
- | **claude-md-compactor** | Compacts CLAUDE.md when > 40k chars |
129
- | **tester-unit** | Creates unit tests with Vitest |
144
+ | Agent | Purpose |
145
+ | ----------------------- | --------------------------------------------- |
146
+ | **research-web** | Researches best practices before new features |
147
+ | **commit-manager** | Manages git commits, conventional format |
148
+ | **claude-md-compactor** | Compacts CLAUDE.md when > 40k chars |
149
+ | **tester-unit** | Creates unit tests with Vitest |
130
150
 
131
151
  ---
132
152
 
@@ -135,6 +155,7 @@ Claude works autonomously until the task is complete or hits the iteration limit
135
155
  > Documentation lives in `/docs` and is created **only when the user asks**.
136
156
 
137
157
  After completing any task, Claude should ask:
158
+
138
159
  ```
139
160
  Done! Finished [task description]. Want me to:
140
161
  1. Document this in /docs?
@@ -149,12 +170,12 @@ Do NOT auto-document. Do NOT maintain domain docs. Keep it simple.
149
170
 
150
171
  > After ANY implementation, update this file to reflect the current state.
151
172
 
152
- | Change Type | Sections to Update |
153
- |-------------|-------------------|
173
+ | Change Type | Sections to Update |
174
+ | --------------- | ----------------------------------- |
154
175
  | Any file change | Last Change (branch, date, summary) |
155
- | New feature | 30s Overview, Architecture |
156
- | New dependency | Stack |
157
- | Workflow change | Workflow section |
176
+ | New feature | 30s Overview, Architecture |
177
+ | New dependency | Stack |
178
+ | Workflow change | Workflow section |
158
179
 
159
180
  Keep only the LATEST Last Change entry (no stacking).
160
181
 
@@ -164,13 +185,13 @@ Keep only the LATEST Last Change entry (no stacking).
164
185
 
165
186
  ### HTTP Requests (MANDATORY)
166
187
 
167
- | Rule | Implementation |
168
- |------|----------------|
169
- | Use axios ONLY | Never `fetch()` or raw `axios` |
170
- | `withCredentials: true` | ALWAYS for cookies/sessions |
171
- | Extend base instance | Create `lib/api/axios.ts` |
172
- | Type responses | `api.get<User>('/users')` |
173
- | Centralize errors | Use interceptors |
188
+ | Rule | Implementation |
189
+ | ----------------------- | ------------------------------ |
190
+ | Use axios ONLY | Never `fetch()` or raw `axios` |
191
+ | `withCredentials: true` | ALWAYS for cookies/sessions |
192
+ | Extend base instance | Create `lib/api/axios.ts` |
193
+ | Type responses | `api.get<User>('/users')` |
194
+ | Centralize errors | Use interceptors |
174
195
 
175
196
  ### Path Aliases (MANDATORY)
176
197
 
@@ -216,20 +237,20 @@ Types: `feat`, `fix`, `refactor`, `docs`, `chore`
216
237
 
217
238
  ## FORBIDDEN Actions
218
239
 
219
- | Action | Reason |
220
- | ------------------------------ | ---------------------------- |
221
- | Write in non-English | ALL code/docs MUST be in EN |
222
- | Skip typecheck | Catches runtime errors |
223
- | Use `any` type | Defeats strict mode |
224
- | Define types in `src/` | Must be in `types/` |
225
- | Commit directly to main | Create feature/fix branches |
226
- | Use MUI/Chakra | Use shadcn/ui + Radix |
227
- | Wildcard icon imports | Use named imports |
228
- | Files > 400 lines | MUST split into smaller |
229
- | 'use client' at top level | Push to leaf components only |
230
- | Waterfall data fetching | Use Promise.all() for parallel |
231
- | Auto-document without asking | Ask user first |
232
- | Skip superpowers for features | Use brainstorming + TDD |
240
+ | Action | Reason |
241
+ | ----------------------------- | --------------------------------------------------------------------------------------------------------------------- |
242
+ | Speak/write in non-English | EN ONLY (chat, code, docs, commits) — see Language Policy. Override only via explicit user request, current turn only |
243
+ | Skip typecheck | Catches runtime errors |
244
+ | Use `any` type | Defeats strict mode |
245
+ | Define types in `src/` | Must be in `types/` |
246
+ | Commit directly to main | Create feature/fix branches |
247
+ | Use MUI/Chakra | Use shadcn/ui + Radix |
248
+ | Wildcard icon imports | Use named imports |
249
+ | Files > 400 lines | MUST split into smaller |
250
+ | 'use client' at top level | Push to leaf components only |
251
+ | Waterfall data fetching | Use Promise.all() for parallel |
252
+ | Auto-document without asking | Ask user first |
253
+ | Skip superpowers for features | Use brainstorming + TDD |
233
254
 
234
255
  ---
235
256
 
@@ -247,13 +268,13 @@ Types: `feat`, `fix`, `refactor`, `docs`, `chore`
247
268
 
248
269
  ## MCP Servers
249
270
 
250
- | Server | Purpose | When to Use |
251
- | --------------------- | ----------------------- | ------------------------------------ |
252
- | `sequential-thinking` | Complex problem-solving | Multi-step tasks, planning |
253
- | `memory` | Persistent knowledge | Store/recall project patterns |
254
- | `playwright` | Browser automation | UI testing, page verification |
255
- | `nextjs-devtools` | Next.js dev tools | Next.js projects only |
256
- | `mongodb` | Database operations | DB queries, schema inspection |
271
+ | Server | Purpose | When to Use |
272
+ | --------------------- | ----------------------- | ----------------------------- |
273
+ | `sequential-thinking` | Complex problem-solving | Multi-step tasks, planning |
274
+ | `memory` | Persistent knowledge | Store/recall project patterns |
275
+ | `playwright` | Browser automation | UI testing, page verification |
276
+ | `nextjs-devtools` | Next.js dev tools | Next.js projects only |
277
+ | `mongodb` | Database operations | DB queries, schema inspection |
257
278
 
258
279
  > Note: `context7` is now a **plugin** (auto-invokes on library mentions).
259
280
 
@@ -261,13 +282,13 @@ Types: `feat`, `fix`, `refactor`, `docs`, `chore`
261
282
 
262
283
  ## Community Skills (from GitHub)
263
284
 
264
- | Skill | Source | Purpose |
265
- |-------|--------|---------|
266
- | **react-best-practices** | vercel-labs | React/Next.js perf optimization rules |
267
- | **web-design-guidelines** | vercel-labs | 100+ WCAG + UX audit rules |
268
- | **composition-patterns** | vercel-labs | Compound component patterns |
269
- | **webapp-testing** | anthropics | Real browser test execution |
270
- | **mcp-builder** | anthropics | MCP server development guide |
285
+ | Skill | Source | Purpose |
286
+ | ------------------------- | ----------- | ------------------------------------- |
287
+ | **react-best-practices** | vercel-labs | React/Next.js perf optimization rules |
288
+ | **web-design-guidelines** | vercel-labs | 100+ WCAG + UX audit rules |
289
+ | **composition-patterns** | vercel-labs | Compound component patterns |
290
+ | **webapp-testing** | anthropics | Real browser test execution |
291
+ | **mcp-builder** | anthropics | MCP server development guide |
271
292
 
272
293
  ---
273
294