@only1btayy/g2w 1.0.24 → 1.0.26

package/README.md

@@ -75,20 +75,50 @@ Research isn't just a web search. G2W uses Context7 for live library docs, Exa f
 
 ---
 
+### What Ships With G2W
+
+These install automatically — no setup, no API keys, no extra steps:
+
+| Tool | What It Does |
+|---|---|
+| [Context7](https://context7.com) | Live library docs in every research and planning phase — no stale training data |
+| [Shadcn/UI MCP](https://www.shadcn.io/mcp) | Real React component implementations with TypeScript props |
+| [Tailwind CSS MCP](https://github.com/CarbonoDev/tailwindcss-mcp-server) | Utility classes, color palettes, CSS-to-Tailwind conversion |
+| [A11y MCP](https://github.com/priyankark/a11y-mcp) | Accessibility audits and WCAG compliance checks |
+
+Claude reaches for these automatically when they're relevant. You don't have to call them.
+
+---
+
 ### Power-Ups
 
-G2W works out of the box. These optional tools make it stronger:
+Optional tools that make G2W stronger. Run `g2w power-ups` to set these up anytime.
+
+**Free (just needs a key):**
+
+| Tool | What It Adds | Get Your Key |
+|---|---|---|
+| [21st.dev](https://21st.dev) | AI-powered UI component generation — like v0 in your IDE | [21st.dev/magic/console](https://21st.dev/magic/console) |
+| [Motion](https://motion.dev) | Production-grade animations with AI Kit | [plus.motion.dev/personal-token](https://plus.motion.dev/personal-token) |
+| [Figma MCP](https://help.figma.com/hc/en-us/articles/32132100833559) | Design-to-code from Figma frames (free during beta) | [figma.com](https://figma.com) |
+| [Marketing Skills](https://github.com/coreyhaines31/marketingskills) | 40+ skills for copywriting, SEO, conversion, growth | No key needed |
+
+**Research (paid):**
 
 | Tool | What It Adds |
 |---|---|
-| [Repomix](https://github.com/yamadashy/repomix) | Packs entire codebases into one AI-optimized file — `bring2life` and research use this |
-| [Context7](https://context7.com) | Live library docs pulled into research — no stale training data |
 | [Exa](https://exa.ai) | Semantic search for similar projects and best practices |
 | [Firecrawl](https://firecrawl.dev) | Deep crawling of repos and docs sites during research |
+
+**Workflow:**
+
+| Tool | What It Adds |
+|---|---|
+| [Repomix](https://github.com/yamadashy/repomix) | Packs entire codebases into one AI-optimized file — `bring2life` uses this |
 | [MemPalace](https://github.com/milla-jovovich/mempalace) | Persistent memory across sessions — decisions survive context clears |
 | [Superpowers](https://github.com/supermemoryai/superpowers-claude) | Enhanced planning and review capabilities for Claude users |
 
-Install what you want. G2W uses what's available and falls back gracefully when something isn't there.
+G2W uses what's available and falls back gracefully when something isn't there.
 
 ---
 
@@ -118,7 +148,7 @@ Each Foundation agent is also a direct slash command. The normal flow runs throu
 | `/g2w:the-challenger` | You wrote your own plan outside G2W and want it stress-tested before building |
 | `/g2w:the-builder` | Plan is already locked — skip straight to building |
 | `/g2w:the-inspector` | Code is already written — just verify it against a plan |
-| `/g2w:the-leader` | Kick off the full pipeline without the identity, brainstorm, and research phases |
+| `/g2w:the-leader` | Kick off the full pipeline — includes automatic code audit before Challenger reviews |
 
 These are escape hatches for engineers who don't need the ceremony. G2W has no ceiling.
 

package/lib/install.js

@@ -41,7 +41,7 @@ const G2W_HOOKS = {
       ]
     },
     {
-      matcher: 'Edit|Write|Bash',
+      matcher: 'Edit|Write',
       hooks: [
         {
           type: 'prompt',
@@ -83,6 +83,45 @@ function copyHooks(targetBase) {
   return dest;
 }
 
+const MCP_SERVERS = {
+  context7: {
+    command: 'npx',
+    args: ['-y', '@upstash/context7-mcp@latest']
+  },
+  'shadcn-ui': {
+    url: 'https://www.shadcn.io/api/mcp'
+  },
+  'tailwindcss': {
+    command: 'npx',
+    args: ['-y', 'tailwindcss-mcp-server']
+  },
+  'a11y': {
+    command: 'npx',
+    args: ['-y', 'a11y-mcp']
+  }
+};
+
+function mergeMcpServers(targetBase) {
+  const settingsPath = path.join(targetBase, '.claude', 'settings.json');
+  let existing = {};
+  if (fs.existsSync(settingsPath)) {
+    try { existing = JSON.parse(fs.readFileSync(settingsPath, 'utf8')); } catch {}
+  }
+
+  if (!existing.mcpServers) existing.mcpServers = {};
+
+  let added = 0;
+  for (const [name, config] of Object.entries(MCP_SERVERS)) {
+    if (!existing.mcpServers[name]) {
+      existing.mcpServers[name] = config;
+      added++;
+    }
+  }
+
+  fs.writeFileSync(settingsPath, JSON.stringify(existing, null, 2));
+  return added;
+}
+
 function mergeHooks(targetBase) {
   const settingsPath = path.join(targetBase, '.claude', 'settings.json');
   const hooksDir = path.join(targetBase, '.claude', 'hooks');
@@ -131,6 +170,19 @@ function removeSkills(targetBase) {
   return false;
 }
 
+function removeMcpServers(targetBase) {
+  const settingsPath = path.join(targetBase, '.claude', 'settings.json');
+  if (!fs.existsSync(settingsPath)) return;
+  let existing = {};
+  try { existing = JSON.parse(fs.readFileSync(settingsPath, 'utf8')); } catch { return; }
+  if (existing.mcpServers) {
+    for (const name of Object.keys(MCP_SERVERS)) {
+      delete existing.mcpServers[name];
+    }
+  }
+  fs.writeFileSync(settingsPath, JSON.stringify(existing, null, 2));
+}
+
 function removeHooks(targetBase) {
   const settingsPath = path.join(targetBase, '.claude', 'settings.json');
   const hooksDir = path.join(targetBase, '.claude', 'hooks');
@@ -173,6 +225,7 @@ async function run() {
   const { dest, count } = copySkills(base);
   copyHooks(base);
   const settingsPath = mergeHooks(base);
+  const mcpAdded = mergeMcpServers(base);
 
   writeTTY(`${LOGO}
 \x1b[32m✅ G2W installed at ${label}\x1b[0m
@@ -181,6 +234,23 @@ async function run() {
   Hooks    → ${path.join(label, 'hooks/')}
   Config   → ${path.join(label, 'settings.json')}
 
+\x1b[36mIncluded tools:\x1b[0m
+  ✅ Context7     — live library docs in every research phase
+  ✅ Shadcn/UI    — real React component implementations
+  ✅ Tailwind CSS — utility classes and CSS conversion
+  ✅ A11y         — accessibility audits and WCAG checks
+
+\x1b[33mPower-Ups (optional — run g2w power-ups to set up):\x1b[0m
+  → 21st.dev     — AI component generation        https://21st.dev/magic/console
+  → Motion       — production animations           https://plus.motion.dev/personal-token
+  → Figma MCP    — design-to-code from Figma       https://figma.com
+  → Marketing    — 40+ SEO, copy, growth skills    https://github.com/coreyhaines31/marketingskills
+  → Exa          — semantic search (paid)           https://exa.ai
+  → Firecrawl    — deep doc crawling (paid)         https://firecrawl.dev
+  → Repomix      — pack codebases for AI            https://github.com/yamadashy/repomix
+  → MemPalace    — persistent memory                https://github.com/milla-jovovich/mempalace
+  → Superpowers  — enhanced planning + review       https://github.com/supermemoryai/superpowers-claude
+
 Open any project with Claude Code and type:
   /g2w:bring2life    — onboard an existing codebase
   /g2w:back2it       — resume a session
@@ -200,6 +270,7 @@ async function uninstall() {
   const { base, label } = getTarget();
   const removed = removeSkills(base);
   removeHooks(base);
+  removeMcpServers(base);
 
   if (removed) {
     console.log(`\n✅ G2W removed from ${label}\n`);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@only1btayy/g2w",
-  "version": "1.0.24",
+  "version": "1.0.26",
   "description": "G2W — a relationship protocol for building trust with AI",
   "bin": {
     "g2w": "bin/g2w.js"

package/skills/bring2life.md

@@ -99,6 +99,68 @@ Generate all 11:
 - `CURRENT.md`
 - `PLAN.md` (leave empty — written by The Visionary when a task begins)
 
+## Phase 2b — Code Audit
+
+After generating draft docs, run a deep audit of the actual code. Do not wait for the user to ask — this happens automatically. The goal is to show the user the real health of their codebase before they start building on top of it.
+
+Scan for:
+
+**Bugs & crashes:**
+- Race conditions, thread safety issues
+- Null/undefined access paths
+- Logic errors (duplicate checks, unreachable code, off-by-one)
+- State that can get out of sync
+
+**Dead code:**
+- Files with zero references
+- Functions/classes never called
+- Directories that aren't compiled or imported
+- For each: list the file, size, and verdict (delete / flag / verify first)
+
+**Anti-patterns:**
+- Copy-pasted logic that should be shared
+- Hardcoded values that should be configurable
+- Missing error handling at system boundaries
+- Overly complex functions that do too many things
+
+**Security:**
+- Exposed secrets, API keys, credentials
+- Unvalidated user input
+- Unsafe file operations
+
+**Flags worth checking:**
+- Things that work in dev but would break in production
+- Assumptions about paths, environments, or dependencies
+
+Write everything to `ERRORS.md` in the project's G2W doc folder. Use this format:
+
+```
+# Errors & Issues — [project-name]
+Generated by bring2life: [date]
+
+## Critical Bugs
+### ERR-XX — [short title]
+**File:** `path/to/file.ext:line-range`
+**What's wrong:** [explain what the code actually does vs what it should do]
+**The fix:** [specific fix, not vague advice]
+
+## Dead Code
+| File | Size | Verdict |
+|------|------|---------|
+| `file.ext` | XXkb | Delete — [reason] |
+
+## Anti-Patterns
+[list with file references]
+
+## Security
+[list with file references]
+
+## Flags
+[things that need human verification before acting on]
+```
+
+Be specific. File paths, line numbers, what's actually broken and why. No vague "consider improving" — either it's a real issue or don't list it.
+
 ## Phase 3 — Gap Interview
 
 After generating drafts, ask the questions you couldn't answer from the code alone. Ask them conversationally — no more than 3 at a time. Cover:

package/skills/the-challenger.md

@@ -42,7 +42,9 @@ Attack every dimension:
 
 1. **Read `PLAN.md`** from `~/.g2w/projects/[active-project]/`
 
-1b. **Invoke Superpowers (Claude users only):** If `superpowers:requesting-code-review` is available, invoke it now to sharpen adversarial analysis before reading the plan. If not available, proceed with native capabilities.
+1b. **Read `ERRORS.md`** from `~/.g2w/projects/[active-project]/` — this is the code audit generated by The Leader. Use it as context: if the plan touches code with known bugs, flag it. If the plan ignores critical issues that should be addressed first, call it out. If ERRORS.md doesn't exist, note it as a finding ("no code audit was run").
+
+1c. **Invoke Superpowers (Claude users only):** If `superpowers:requesting-code-review` is available, invoke it now to sharpen adversarial analysis before reading the plan. If not available, proceed with native capabilities.
 
 2. **Read the actual codebase** — don't review a plan in a vacuum. Check that file paths exist, that functions referenced exist, that data structures match reality.
 

package/skills/the-inspector.md

@@ -60,10 +60,12 @@ There is no partial pass. The build either passes inspection or it goes back to
 ## Process
 
 1. Read `PLAN.md` — know the contract
-2. Read every file that was modified
-3. Work through the test matrix item by item
-4. Report: PASS (all items verified, user confirmed) or FAIL (specific items failing + fix list)
-5. On PASS → tell The Leader: inspection complete, ready for handoff
+2. Read `ERRORS.md` — know the pre-existing issues
+3. Read every file that was modified
+4. Work through the test matrix item by item
+5. **Update `ERRORS.md`** — mark any issues that were fixed this session as resolved. Add any new issues discovered during verification. Never delete old entries — mark them with `[RESOLVED — date]`.
+6. Report: PASS (all items verified, user confirmed) or FAIL (specific items failing + fix list)
+7. On PASS → tell The Leader: inspection complete, ready for handoff
 
 ## Rules
 

package/skills/the-leader.md

@@ -24,8 +24,16 @@ You are The Leader. You own the pipeline from task definition to handoff. Every
 - Verify PLAN.md exists and has no TBD/TODO/❓ markers before passing to Challenger
 - If markers exist → send back to Visionary. Do not pass incomplete plans.
 
+**Phase 1b — Code Audit (auto):**
+- Check if `ERRORS.md` exists in `~/.g2w/projects/[active-project]/`
+- If it doesn't exist OR is older than 7 days → run a full code audit now
+- Scan the codebase for: bugs, crashes, race conditions, dead code, anti-patterns, security issues
+- Write findings to `ERRORS.md` with file paths, line numbers, and specific descriptions
+- This runs automatically — never ask the user if they want an audit. They always do.
+- If `ERRORS.md` already exists and is current → skip, move on
+
 **Phase 2 — Challenge:**
-- Hand plan to The Challenger
+- Hand plan AND `ERRORS.md` to The Challenger
 - Receive findings
 - If FAIL → return to Visionary with findings. Loop until Challenger gives PASS.
 - On PASS → LOCK the plan. Announce: "Plan is locked. No modifications after this point."