@slamb2k/mad-skills 2.0.19 → 2.0.20

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "mad-skills",
   "description": "AI-assisted planning, development and governance tools",
-  "version": "2.0.19",
+  "version": "2.0.20",
   "author": {
     "name": "slamb2k",
     "url": "https://github.com/slamb2k"

package/README.md

@@ -9,7 +9,7 @@ A skill framework for Claude Code. Ships 10 skills covering the full development
 | Skill | Command | Description |
 |-------|---------|-------------|
 | **build** | `/build` | Context-isolated feature development pipeline. Takes a design/plan and executes explore, question, architect, implement, review, ship inside subagents. |
-| **brace** | `/brace` | Initialize projects with the GOTCHA/BRACE framework. Creates 6-layer structure, BRACE build methodology, and project CLAUDE.md. |
+| **brace** | `/brace` | Initialize projects with a standard scaffold. Creates specs/, tools/, context/ directories, project CLAUDE.md, and branch protection. |
 | **distil** | `/distil` | Generate multiple unique web design variations. Creates a Vite + React + TypeScript + Tailwind project with N designs at /1, /2, /3. |
 | **dock** | `/dock` | Generate container release pipelines. Builds once, promotes immutable images through dev → staging → prod. Supports Azure Container Apps, AWS Fargate, Cloud Run, Kubernetes, Dokku, Coolify, CapRover. |
 | **keel** | `/keel` | Generate IaC pipelines (Terraform, Bicep, Pulumi, CDK) to provision cloud infrastructure. Plans on PR, applies on merge. Provisions what /dock deploys to. |
@@ -80,7 +80,7 @@ The session guard checks: git status, CLAUDE.md presence and freshness, task lis
 
 ### Step 1: `/brace` — Initialize the Project
 
-Start in an empty folder. `/brace` creates the project skeleton using the GOTCHA/BRACE framework.
+Start in an empty folder. `/brace` creates the project scaffold.
 
 ```
 > /brace my-webapp
@@ -91,12 +91,10 @@ Start in an empty folder. `/brace` creates the project skeleton using the GOTCHA
 ```
 my-webapp/
 ├── CLAUDE.md              # AI-readable project instructions
-├── goals/                 # Project goals and success criteria
-├── orchestration/         # Workflow definitions
-├── tools/                 # Tool configurations
-├── context/               # Domain knowledge
-├── hard_prompts/          # Reusable prompt templates
-└── args/                  # Runtime parameters
+├── .gitignore             # Ignores credentials, data, temp files
+├── specs/                 # Specifications (/speccy → /build)
+├── context/               # Domain knowledge and references
+└── .tmp/                  # Scratch work (gitignored)
 ```
 
 The CLAUDE.md it creates becomes the foundation — every subsequent skill reads it for project context.

package/hooks/session-guard.cjs

@@ -57,7 +57,7 @@ function check() {
       'No CLAUDE.md found. Want me to set up this project for Claude Code?',
       'single_select',
       [
-        '"Set up with BRACE" \u2014 run `/brace` to scaffold CLAUDE.md + GOTCHA framework (goals, tools, context)',
+        '"Set up with /brace" \u2014 scaffold CLAUDE.md + project structure (specs, tools, context)',
         '"Basic init" \u2014 run `/init` to scaffold CLAUDE.md only',
         '"Skip" \u2014 continue without one',
       ],
@@ -68,7 +68,7 @@ function check() {
 
   output.add(`[SESSION GUARD] \u2705 CLAUDE.md found in: ${PROJECT_DIR}`);
 
-  // 1b) BRACE framework check
+  // 1b) Project scaffold check
   checkBrace(PROJECT_DIR, output);
 
   // 1c) Rig (dev tooling) check
@@ -165,19 +165,19 @@ function remind() {
 // ─── brace check ──────────────────────────────────────────────────
 
 function checkBrace(projectDir, output) {
-  const manifest = join(projectDir, 'goals', 'manifest.md');
-  if (existsSync(manifest)) return; // BRACE already set up
+  const specsDir = join(projectDir, 'specs');
+  if (existsSync(specsDir)) return; // scaffold already set up
 
   const prefs = state.loadPrefs(projectDir);
   if (prefs.braceDismissed) return; // User said don't ask again
 
-  output.add('[SESSION GUARD] \u2139\uFE0F  CLAUDE.md exists but no GOTCHA/BRACE framework detected.');
+  output.add('[SESSION GUARD] \u2139\uFE0F  CLAUDE.md exists but no project scaffold detected.');
   output.add('[SESSION GUARD] BRACE_DISMISS: If the user selects "Don\'t ask again", run: node <path-to-session-guard.cjs> dismiss-brace');
   output.addQuestion(
-    'This project has a CLAUDE.md but no GOTCHA/BRACE framework (goals/, tools/, context/). Want to set it up?',
+    'This project has a CLAUDE.md but no project scaffold (specs/, tools/, context/). Want to set it up?',
     'single_select',
     [
-      '"Set up BRACE" \u2014 run `/brace` to add the GOTCHA framework structure',
+      '"Set up with /brace" \u2014 add project scaffold structure',
       '"Not now" \u2014 skip for this session',
       '"Don\'t ask again" \u2014 dismiss permanently for this project',
     ],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@slamb2k/mad-skills",
-  "version": "2.0.19",
+  "version": "2.0.20",
   "description": "Claude Code skills collection — planning, development and governance tools",
   "type": "module",
   "repository": {

package/skills/brace/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: brace
-description: 'Initialize any project directory with the GOTCHA/BRACE framework for agentic AI systems. Creates the 6-layer structure (Goals, Orchestration, Tools, Context, Hard prompts, Args), BRACE build methodology, and a project CLAUDE.md. Recommends claude-mem for persistent memory. Idempotent — safe to run on existing projects. Triggers: "init gotcha", "setup brace", "brace", "initialize framework", "bootstrap gotcha".'
-argument-hint: "[--no-brace] [--force]"
+description: 'Initialize any project directory with a standard scaffold for AI-assisted development. Creates specs/ and context/ directories, a project CLAUDE.md with development workflow and guardrails, .gitignore, and branch protection. Recommends claude-mem for persistent memory. Idempotent — safe to run on existing projects. Triggers: "init project", "setup brace", "brace", "initialize", "bootstrap", "scaffold".'
+argument-hint: "[--force]"
 allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, AskUserQuestion
 ---
 
-# Brace - GOTCHA/BRACE Framework Bootstrap
+# Brace - Project Scaffold
 
 When this skill is invoked, IMMEDIATELY output the banner below before doing anything else.
 Pick ONE tagline at random — vary your choice each time.
@@ -59,9 +59,9 @@ Status icons: ✅ done · ❌ failed · ⚠️ degraded · ⏳ working · ⏭️
 
 ---
 
-Initialize any project directory with the GOTCHA/BRACE framework. Idempotent —
-safe to re-run on existing projects. Content templates and subagent prompts
-are in `references/`.
+Initialize any project directory with a standard scaffold for AI-assisted
+development. Idempotent — safe to re-run on existing projects. Content
+templates and subagent prompts are in `references/`.
 
 **Key principle:** Scan first, present plan, get approval, then act.
 
@@ -74,7 +74,6 @@ Report format: `references/report-template.md`
 ## Flags
 
 Parse optional flags from the request:
-- `--no-brace` — Skip BRACE build methodology (goals/build_app.md)
 - `--force` — Overwrite existing files without prompting
 
 ---
@@ -99,7 +98,6 @@ For each row, in order:
 4. After all checks: summarize what's available and what's degraded
 
 1. Capture **FLAGS** from the user's request
-2. Create a task list tracking all 5 phases
 
 ---
 
@@ -111,7 +109,7 @@ Launch **Bash** subagent (**haiku**):
 Task(
   subagent_type: "Bash",
   model: "haiku",
-  description: "Scan directory for existing GOTCHA structure",
+  description: "Scan directory for existing scaffold structure",
   prompt: <read from references/phase-prompts.md#phase-1>
 )
 ```
@@ -123,24 +121,26 @@ Parse SCAN_REPORT. Extract:
 - `has_claude_md` / `has_gitignore`
 - `has_atlas` (legacy ATLAS naming detected)
 - `has_forge` (legacy FORGE naming detected)
+- `has_legacy_gotcha` (legacy GOTCHA/goals structure detected)
 - `has_legacy_memory` (old tools/memory system detected)
 
 ---
 
 ## Phase 1b: Legacy Upgrade Detection
 
-**Skip if none of `has_atlas`, `has_forge`, or `has_legacy_memory` is true.**
+**Skip if none of `has_atlas`, `has_forge`, `has_legacy_gotcha`, or `has_legacy_memory` is true.**
 
 Build a description of what was found:
 - If `has_atlas` or `has_forge`: "Legacy ATLAS/FORGE naming detected"
+- If `has_legacy_gotcha`: "Legacy GOTCHA/BRACE framework detected (goals/ directory)"
 - If `has_legacy_memory`: "Legacy memory system (tools/memory/, memory/) detected"
 
 Ask the user via AskUserQuestion:
 
    Question: "Legacy components detected: {description}. Upgrade and clean up?"
    Options:
-   - "Yes, upgrade all" — Replace legacy naming with BRACE and remove old memory system
-   - "No, leave as-is" — Keep existing naming and memory system
+   - "Yes, upgrade all" — Replace legacy structure and remove old systems
+   - "No, leave as-is" — Keep existing structure
 
 Store result as `upgrade_legacy: true|false` in USER_CONFIG.
 
@@ -153,10 +153,9 @@ Store result as `upgrade_legacy: true|false` in USER_CONFIG.
 1. Derive default project name from SCAN_REPORT `directory_name`
 2. Present via AskUserQuestion:
 
-   Question: "What to include in GOTCHA setup?"
+   Question: "Set up project scaffold?"
    Options:
-   - "Full GOTCHA + BRACE (Recommended)"
-   - "GOTCHA structure only (no BRACE methodology)"
+   - "Full scaffold (Recommended)" — CLAUDE.md, directories, guardrails
    - "Cancel"
 
 3. If not cancelled, ask for project description (one sentence) via
@@ -173,7 +172,6 @@ Store result as `upgrade_legacy: true|false` in USER_CONFIG.
 5. Store as USER_CONFIG:
    - project_name: from directory name or user override
    - description: from user input
-   - include_brace: true/false (based on selection and `--no-brace`)
    - install_level: "both" | "global" | "project"
 
 **If cancelled, stop here.**
@@ -188,34 +186,33 @@ For each item in `references/scaffold-manifest.md`:
 - If component not selected in USER_CONFIG → status: "not selected"
 - If item already exists (from SCAN_REPORT) and no `--force` → status: "skip"
 - If item exists and `--force` → status: "overwrite"
-- If CLAUDE.md exists → status: "merge" (append GOTCHA section)
+- If CLAUDE.md exists → status: "merge" (append scaffold sections)
 - If .gitignore exists → status: "merge" (append missing entries)
 - Otherwise → status: "create"
 
 If `upgrade_legacy` is true in USER_CONFIG, set status "upgrade" for:
 - CLAUDE.md (replaces "merge" or "skip" — upgrade takes priority)
-- goals/build_app.md (replaces "skip")
-- goals/manifest.md (replaces "skip")
+
+If `upgrade_legacy` is true AND `has_legacy_gotcha` is true, additionally:
+- `goals/` → status: "remove" (only if contains only manifest.md and build_app.md)
 
 If `upgrade_legacy` is true AND `has_legacy_memory` is true, additionally:
 - `tools/memory/` → status: "remove"
 - `memory/` → status: "remove"
-- CLAUDE.md also gets memory section replacement (handled alongside upgrade)
 - `tools/manifest.md` → status: "cleanup" (remove memory tool rows)
 - `.gitignore` → status: "cleanup" (remove memory/*.npy entry)
 
 Present plan summary to user via AskUserQuestion:
 
 ```
-GOTCHA Framework Setup for: {project_name}
+Project Scaffold for: {project_name}
 
 Will create:  {list of items with status "create"}
 Will merge:   {list of items with status "merge"}
-Will upgrade: {list of items with status "upgrade" — legacy → BRACE}
-Will remove:  {list of items with status "remove" — legacy memory system}
+Will upgrade: {list of items with status "upgrade"}
+Will remove:  {list of items with status "remove" — legacy cleanup}
 Will clean:   {list of items with status "cleanup" — remove legacy references}
 Will skip:    {count} existing items
-Not selected: {count} items
 Global config: {install_level description}
 
 Proceed?
@@ -234,7 +231,7 @@ Launch **general-purpose** subagent:
 ```
 Task(
   subagent_type: "general-purpose",
-  description: "Create GOTCHA framework structure",
+  description: "Create project scaffold structure",
   prompt: <read from references/phase-prompts.md#phase-4>
 )
 ```
@@ -247,12 +244,6 @@ Before sending the prompt, substitute these variables:
 - `{CLAUDE_MD_TEMPLATE}` — read from `references/claude-md-template.md`
   (the section between BEGIN TEMPLATE and END TEMPLATE)
 - `{GITIGNORE_CONTENT}` — read from `assets/gitignore-template`
-- `{GOALS_MANIFEST}` — read from `references/scaffold-manifest.md`
-  (the goals/manifest.md content block)
-- `{TOOLS_MANIFEST}` — read from `references/scaffold-manifest.md`
-  (the tools/manifest.md content block)
-- `{BRACE_WORKFLOW}` — read from `references/brace-workflow.md`
-  (the section after the header, used for goals/build_app.md)
 - `{GLOBAL_PREFERENCES_CONTENT}` — read from `assets/global-preferences-template.md`
   (the section between BEGIN TEMPLATE and END TEMPLATE)
 
@@ -268,7 +259,7 @@ Launch **Bash** subagent (**haiku**):
 Task(
   subagent_type: "Bash",
   model: "haiku",
-  description: "Verify GOTCHA structure",
+  description: "Verify project scaffold",
   prompt: <read from references/phase-prompts.md#phase-5>
 )
 ```
@@ -278,10 +269,44 @@ Parse VERIFY_REPORT. Present the final summary using the format in
 
 ---
 
+## Phase 6: Branch Protection
+
+**Only if the project is a git repo** (from SCAN_REPORT `git_initialized`).
+
+Check if the default branch (main or master) has branch protection:
+
+```bash
+default_branch=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@' || echo "main")
+```
+
+If a GitHub remote is detected (`git remote get-url origin` matches github.com):
+1. Check for existing branch protection via `gh api repos/{owner}/{repo}/branches/{default_branch}/protection` (404 = unprotected)
+2. If unprotected, ask via AskUserQuestion:
+
+   Question: "Default branch `{default_branch}` has no branch protection. Add it?"
+   Options:
+   - "Yes, require PR reviews (Recommended)" — require 1 approval, block force push
+   - "Skip" — leave unprotected
+
+3. If user accepts, apply via:
+   ```bash
+   gh api repos/{owner}/{repo}/branches/{default_branch}/protection \
+     -X PUT -f required_pull_request_reviews='{"required_approving_review_count":1}' \
+     -f enforce_admins=false \
+     -f restrictions=null \
+     -f required_status_checks=null \
+     -F allow_force_pushes=false \
+     -F allow_deletions=false
+   ```
+
+Include result in the final report under a "🔒 Branch protection" section.
+
+---
+
 ## Idempotency Rules
 
 - **Skip** directories and files that already exist (unless `--force`)
-- **Merge** CLAUDE.md: append GOTCHA section if file exists but lacks it
+- **Merge** CLAUDE.md: append scaffold sections if file exists but lacks them
 - **Merge** .gitignore: append missing entries only
 - **Never delete** user content
 - **Never overwrite** without `--force` or explicit user approval

package/skills/brace/references/brace-workflow.md

@@ -1,90 +1,22 @@
-# BRACE Build Methodology
+# Development Workflow
 
-Content for `goals/build_app.md`. Copied during brace Phase 4.
+Reference material for the skills-driven development pipeline.
 
 ---
 
-## Goal
+## Workflow
 
-Build full-stack applications using AI assistance within the GOTCHA framework.
-BRACE is a 5-step process that ensures apps are production-ready.
+```
+/speccy → specs/{name}.md → /build specs/{name}.md → /ship
+```
 
-| Step | Phase | What You Do |
-|------|-------|-------------|
-| **B** | Brief | Define problem, users, success metrics |
-| **R** | Research | Data schema, integrations map, stack proposal |
-| **A** | Architect | Design structure, validate all connections |
-| **C** | Construct | Build with layered architecture |
-| **E** | Evaluate | Test functionality, error handling |
+1. **`/speccy`** interviews the user and writes a structured spec to `specs/{name}.md`
+2. **`/build specs/{name}.md`** reads the spec, explores the codebase, designs
+   architecture, implements, reviews, tests, and ships
+3. **`/ship`** commits, creates PR, waits for CI, and merges
 
----
-
-## B — Brief
-
-**Purpose:** Know exactly what you are building before touching code.
-
-1. **What problem does this solve?** — One sentence.
-2. **Who is this for?** — Specific user, not "everyone".
-3. **What does success look like?** — Measurable outcome.
-4. **What are the constraints?** — Budget, time, technical limits.
-
-**Output:** App Brief (problem, user, success criteria, constraints)
-
----
-
-## R — Research
-
-**Purpose:** Design before building. Define the source of truth.
-
-1. **Data schema** — Tables, fields, relationships
-2. **Integrations map** — External services, auth types, API availability
-3. **Technology stack proposal** — Database, backend, frontend (user approves)
-4. **Edge cases** — Rate limits, auth expiry, timeouts, invalid input
-
-**Output:** Schema, approved stack, integrations checklist, edge cases
-
----
-
-## A — Architect
-
-**Purpose:** Design structure and validate all connections BEFORE building.
-
-Checklist:
-- [ ] Database connection tested
-- [ ] All API keys verified
-- [ ] OAuth flows working
-- [ ] Environment variables set
-- [ ] Rate limits understood
-
-**Output:** All green. Fix anything that fails before proceeding.
-
----
-
-## C — Construct
-
-**Purpose:** Build with proper architecture.
-
-Build order:
-1. Database schema first
-2. Backend API routes second
-3. Frontend UI last
-
-Follow GOTCHA separation: frontend (display), backend (logic), database (truth).
-
-**Output:** Working application with functional DB, API, and UI.
-
----
-
-## E — Evaluate
-
-**Purpose:** Test before shipping.
-
-- **Functional:** All buttons work, data saves/retrieves, navigation works
-- **Integration:** API calls succeed, auth persists, rate limits respected
-- **Edge cases:** Invalid input handled, empty states display, errors show feedback
-- **User acceptance:** Solves the original problem, no major friction
-
-**Output:** Test report (passed, failed, needs fixing)
+The `specs/` directory is the handoff point — `/prime` and `/build` both scan
+it automatically.
 
 ---
 
@@ -92,18 +24,6 @@ Follow GOTCHA separation: frontend (display), backend (logic), database (truth).
 
 1. Building before designing — rewrites everything
 2. Skipping connection validation — hours wasted on broken integrations
-3. No data modeling — schema changes cascade into UI rewrites
+3. No data modelling — schema changes cascade into UI rewrites
 4. No testing — ship broken code, lose trust
 5. Hardcoding everything — no flexibility for changes
-
----
-
-## GOTCHA Layer Mapping
-
-| BRACE Step | GOTCHA Layer |
-|------------|--------------|
-| Brief | Goals (define the process) |
-| Research | Context (reference patterns) |
-| Architect | Args (environment setup) |
-| Construct | Tools (execution) |
-| Evaluate | Orchestration (AI validates) |

package/skills/brace/references/claude-md-template.md

@@ -16,46 +16,27 @@ BEGIN TEMPLATE
 
 {PROJECT_DESCRIPTION}
 
-## Operating Framework: GOTCHA
-
-This project uses the **GOTCHA Framework** — a 6-layer architecture for
-agentic AI systems. LLMs handle reasoning; deterministic tools handle execution.
-
-**GOT** (The Engine):
-- **Goals** (`goals/`) — Process definitions. Check `goals/manifest.md` first.
-- **Orchestration** — You (the AI). Read goals, delegate to tools, handle errors.
-- **Tools** (`tools/`) — Python scripts. Check `tools/manifest.md` first.
-
-**CHA** (The Context):
-- **Context** (`context/`) — Domain knowledge, reference material
-- **Hard Prompts** (`hardprompts/`) — Reusable instruction templates
-- **Args** (`args/`) — Behaviour settings (YAML/JSON)
-
-### Operating Rules
-
-1. **Check goals first** — Before any task, read `goals/manifest.md`
-2. **Check tools first** — Before writing code, read `tools/manifest.md`
-3. **Fix and document** — When tools fail, fix them and update the goal
-4. **Never modify goals without permission** — Goals are living documentation
-5. **Communicate when stuck** — Explain what is missing, do not guess
-
-## Directory Structure
+## Project Structure
 
 ```
 {PROJECT_NAME}/
 ├── CLAUDE.md           This file
 ├── .gitignore          Ignores credentials, data, temp files
-├── goals/              Process definitions
-│   ├── manifest.md     Index of all goals
-│   └── build_app.md    BRACE build methodology
-├── tools/              Deterministic scripts
-│   └── manifest.md     Index of all tools
+├── specs/              Specifications (/speccy output, /build input)
 ├── context/            Domain knowledge and references
-├── hardprompts/        Reusable LLM instruction templates
-├── args/               Behaviour settings (YAML/JSON)
 └── .tmp/               Scratch work (gitignored)
 ```
 
+## Development Workflow
+
+```
+/speccy → specs/{name}.md → /build specs/{name}.md → /ship
+```
+
+- `/speccy` interviews and writes a structured spec to `specs/`
+- `/build` reads the spec, explores, designs, implements, reviews, tests
+- `/ship` commits, creates PR, waits for CI, merges
+
 ## Memory
 
 For persistent memory across sessions, install the **claude-mem** plugin:
@@ -68,24 +49,17 @@ MCP tools for search, timeline, and observation management. Claude Code's
 built-in auto memory (`~/.claude/projects/<project>/memory/MEMORY.md`)
 handles curated facts.
 
-## Build Methodology: BRACE
-
-See `goals/build_app.md` for the full workflow:
-- **B**rief — Define problem, users, success metrics
-- **R**esearch — Data schema, integrations, stack proposal
-- **A**rchitect — Design structure, validate all connections
-- **C**onstruct — Build DB first, then API, then UI
-- **E**valuate — Functional, integration, edge case, acceptance testing
-
 {UNIVERSAL_PRINCIPLES}
 
 ## Guardrails
 
-- Always check manifests before creating new goals or tools
 - Verify tool output format before chaining into another tool
 - Do not assume APIs support batch operations — check first
 - Preserve intermediate outputs when workflows fail mid-execution
-- Read the full goal before starting — do not skim
+- Use persistent tasks (`TaskCreate`/`TaskUpdate`) for cross-session tracking
 - Temporary files go in `.tmp/` — never store important data there
+- Don't build before designing — rewrites everything
+- Don't skip connection validation — hours wasted on broken integrations
+- Don't skip data modelling — schema changes cascade into UI rewrites
 
 END TEMPLATE

package/skills/brace/references/phase-prompts.md

@@ -10,18 +10,17 @@ and substitutes `{VARIABLE}` placeholders before sending to the subagent.
 **Agent:** Bash | **Model:** haiku
 
 ```
-Scan the current working directory for existing GOTCHA/BRACE framework structure.
+Scan the current working directory for existing project scaffold structure.
 
 Limit your SCAN_REPORT to 20 lines maximum.
 
 ## Checks
 
-1. Check for each GOTCHA directory:
-   goals/ tools/ context/ hardprompts/ args/ .tmp/
+1. Check for each scaffold directory:
+   specs/ context/ .tmp/
 
 2. Check for each key file:
-   CLAUDE.md .gitignore goals/manifest.md goals/build_app.md
-   tools/manifest.md
+   CLAUDE.md .gitignore
 
 3. Check if directory is a git repo:
    [ -d .git ] && echo "git: true" || echo "git: false"
@@ -31,7 +30,7 @@ Limit your SCAN_REPORT to 20 lines maximum.
 
 5. Check for legacy ATLAS references:
    atlas_found=false
-   for f in CLAUDE.md goals/build_app.md goals/manifest.md; do
+   for f in CLAUDE.md; do
      if [ -f "$f" ] && grep -qi "ATLAS" "$f"; then
        atlas_found=true
        break
@@ -40,14 +39,20 @@ Limit your SCAN_REPORT to 20 lines maximum.
 
 6. Check for legacy FORGE references:
    forge_found=false
-   for f in CLAUDE.md goals/build_app.md goals/manifest.md; do
+   for f in CLAUDE.md; do
      if [ -f "$f" ] && grep -qi "FORGE" "$f"; then
        forge_found=true
        break
      fi
    done
 
-7. Check for legacy memory system:
+7. Check for legacy GOTCHA/goals structure:
+   legacy_gotcha=false
+   if [ -d "goals" ] || ([ -f "CLAUDE.md" ] && grep -q "GOTCHA" CLAUDE.md); then
+     legacy_gotcha=true
+   fi
+
+8. Check for legacy memory system:
    legacy_memory=false
    if [ -d "tools/memory" ] || [ -f "memory/MEMORY.md" ]; then
      legacy_memory=true
@@ -66,6 +71,7 @@ SCAN_REPORT:
   has_gitignore: true|false
   has_atlas: true|false
   has_forge: true|false
+  has_legacy_gotcha: true|false
   has_legacy_memory: true|false
 ```
 
@@ -76,7 +82,7 @@ SCAN_REPORT:
 **Agent:** general-purpose | **Model:** default
 
 ```
-Create the GOTCHA/BRACE framework structure in the current directory.
+Create the project scaffold structure in the current directory.
 
 Limit your SCAFFOLD_REPORT to 15 lines maximum.
 
@@ -95,50 +101,50 @@ Skip items with status "skip" or "not selected".
 ### For "create" items:
 
 1. Create directories with mkdir -p
-2. Create .gitkeep in empty directories (context/, hardprompts/, args/, .tmp/)
+2. Create .gitkeep in empty directories (specs/, context/, .tmp/)
 3. Write CLAUDE.md using the template below, substituting {PROJECT_NAME},
    {PROJECT_DESCRIPTION}, and {UNIVERSAL_PRINCIPLES}
 4. Write .gitignore from the content below
-5. Write goals/manifest.md and tools/manifest.md from content below
-6. Write goals/build_app.md from the BRACE workflow content below
 
 ### For "merge" items:
 
-- CLAUDE.md: Read existing file. If it does not contain "GOTCHA", append
-  the GOTCHA section from the template. If it does, skip.
+- CLAUDE.md: Read existing file. If it does not contain "## Project Structure"
+  or "## Development Workflow", append those sections from the template. If it
+  does, skip.
 - .gitignore: Read existing file. Append any missing entries from the
   template. Do not duplicate existing entries.
 
-### For "upgrade" items (legacy → BRACE migration):
+### For "upgrade" items (legacy migration):
 
-These files already exist but contain legacy ATLAS or FORGE naming. Replace the
-legacy methodology references with BRACE equivalents while preserving all other content.
+These files already exist but contain legacy naming (ATLAS, FORGE, or
+GOTCHA/BRACE). Replace legacy methodology references with the current
+skills-based workflow while preserving all other content.
 
-- **CLAUDE.md:** Replace the "Build Methodology: ATLAS" or "Build Methodology: FORGE"
-  section (from that heading through the bullet list) with the BRACE section from
-  the template. Also replace "ATLAS build methodology" or "FORGE build methodology"
-  with "BRACE build methodology" in the directory tree comment. Preserve all other sections.
-- **goals/build_app.md:** Replace the entire file with the BRACE workflow content below.
-- **goals/manifest.md:** Replace "ATLAS" or "FORGE" with "BRACE" in the description column.
+- **CLAUDE.md:** Replace any "Operating Framework: GOTCHA", "Build Methodology:
+  BRACE/ATLAS/FORGE" sections with the "Project Structure" and "Development
+  Workflow" sections from the template. Remove references to goals/manifest.md
+  and goals/build_app.md. Preserve all other sections.
 
-### For "remove" items (legacy memory cleanup):
+### For "remove" items (legacy cleanup):
 
 1. Before deleting `memory/MEMORY.md`, check if it contains a "## Key Decisions"
    section. If so, extract that section content into `preserved_content` for the
    SCAFFOLD_REPORT so the user can relocate it.
 2. Remove `tools/memory/` — use `git rm -r tools/memory` if tracked, otherwise `rm -rf tools/memory`
 3. Remove `memory/` — use `git rm -r memory` if tracked, otherwise `rm -rf memory`
+4. Remove `goals/` — use `git rm -r goals` if tracked, otherwise `rm -rf goals`
+   (only if empty or contains only manifest.md and build_app.md)
 
-### For "cleanup" items (legacy memory references):
+### For "cleanup" items (legacy references):
 
-- **tools/manifest.md:** Remove any rows referencing `memory/` tools (e.g. search, embed, store scripts)
-- **.gitignore:** Remove the `memory/*.npy` line and its `# Memory embeddings cache` comment if present
-- **CLAUDE.md:** If a `## Memory System` section exists, replace it with:
+- **tools/manifest.md:** Remove any rows referencing `memory/` tools
+- **.gitignore:** Remove the `memory/*.npy` line and its comment if present
+- **CLAUDE.md:** Remove references to goals/, GOTCHA, BRACE. Replace any
+  `## Memory System` section with:
   ```
   ## Memory
   This project uses claude-mem for persistent cross-session memory.
   ```
-  Also remove `tools/memory/` and `memory/` from any directory tree listings in CLAUDE.md.
 
 ### Global preferences (conditional)
 
@@ -164,18 +170,6 @@ empty string (principles are in the global config instead).
 
 {GITIGNORE_CONTENT}
 
-### goals/manifest.md Content
-
-{GOALS_MANIFEST}
-
-### tools/manifest.md Content
-
-{TOOLS_MANIFEST}
-
-### goals/build_app.md Content
-
-{BRACE_WORKFLOW}
-
 ### Global Preferences Content
 
 {GLOBAL_PREFERENCES_CONTENT}
@@ -192,8 +186,8 @@ decision must be explicitly recorded and revisited.
 - When you defer a fix or skip an edge case, document why and what triggers it
 - At the end of each task, review all assumptions and open questions
 - Present unresolved items to the user with context and suggested actions
-- Unresolved items go to `goals/` as follow-ups, to CLAUDE.md as "Known Issues",
-  or to memory for future session awareness
+- Track unresolved items via persistent tasks (`TaskCreate`) or CLAUDE.md
+  "Known Issues" for future session awareness
 - At the start of new work, check for outstanding items from previous sessions
 - Never close a task with unacknowledged open questions
 
@@ -203,7 +197,7 @@ SCAFFOLD_REPORT:
   status: success|partial|failed
   created: [list of files/dirs created]
   merged: [list of files merged]
-  upgraded: [list of files upgraded to BRACE]
+  upgraded: [list of files upgraded]
   removed: [list of legacy items removed]
   cleaned: [list of files cleaned of legacy references]
   preserved_content: [any key decisions extracted from memory/MEMORY.md, or empty]
@@ -219,24 +213,24 @@ SCAFFOLD_REPORT:
 **Agent:** Bash | **Model:** haiku
 
 ```
-Verify the GOTCHA framework was initialised correctly.
+Verify the project scaffold was initialised correctly.
 
 Limit your VERIFY_REPORT to 15 lines maximum.
 
 ## Checks
 
 1. Verify expected directories exist:
-   for d in goals tools context hardprompts args .tmp; do
+   for d in specs context .tmp; do
      [ -d "$d" ] && echo "dir ok: $d" || echo "dir MISSING: $d"
    done
 
 2. Verify key files exist and are non-empty:
-   for f in CLAUDE.md .gitignore goals/manifest.md tools/manifest.md; do
+   for f in CLAUDE.md .gitignore; do
      [ -s "$f" ] && echo "file ok: $f" || echo "file MISSING: $f"
    done
 
-3. Check CLAUDE.md contains GOTCHA reference:
-   grep -q "GOTCHA" CLAUDE.md && echo "claude_md: has GOTCHA" || echo "claude_md: no GOTCHA"
+3. Check CLAUDE.md contains project structure:
+   grep -q "Project Structure" CLAUDE.md && echo "claude_md: has structure" || echo "claude_md: no structure"
 
 4. Check .gitignore has key entries:
    entries=0
@@ -245,12 +239,9 @@ Limit your VERIFY_REPORT to 15 lines maximum.
    done
    echo "gitignore entries: $entries/2"
 
-5. If legacy memory cleanup was performed, verify removal:
+5. If legacy cleanup was performed, verify removal:
    if [ -d "tools/memory" ]; then echo "legacy: tools/memory still exists"; fi
    if [ -d "memory" ]; then echo "legacy: memory/ still exists"; fi
-   if [ -f "CLAUDE.md" ] && grep -q "tools/memory" CLAUDE.md; then
-     echo "legacy: CLAUDE.md still references tools/memory"
-   fi
 
 ## Output Format
 
@@ -258,8 +249,8 @@ VERIFY_REPORT:
   status: complete|partial|failed
   dirs_verified: {count}/{expected}
   files_verified: {count}/{expected}
-  claude_md_has_gotcha: true|false
+  claude_md_valid: true|false
   gitignore_entries: {count}/{expected}
-  legacy_memory_cleaned: true|false|not_applicable
+  legacy_cleaned: true|false|not_applicable
   issues: [any problems found]
 ```

package/skills/brace/references/report-template.md

@@ -13,21 +13,16 @@ Present this summary after verification completes.
 │  📍 Directory: {cwd}
 │
 │  📝 Structure
-│     {✅|⏭️} goals/         Goals layer
-│     {✅|⏭️} tools/         Tools layer
-│     {✅|⏭️} context/       Context layer
-│     {✅|⏭️} hardprompts/   Hard prompts layer
-│     {✅|⏭️} args/          Args layer
+│     {✅|⏭️} specs/         Specifications
+│     {✅|⏭️} context/       Domain knowledge
 │     {✅|⏭️} .tmp/          Temp directory
 │
 │  📄 Files
 │     {✅|⏭️} CLAUDE.md
 │     {✅|⏭️} .gitignore
-│     {✅|⏭️} goals/manifest.md
-│     {✅|⏭️} goals/build_app.md
-│     {✅|⏭️} tools/manifest.md
 │
-│  🗑️ Removed (only if legacy memory was cleaned up)
+│  🗑️ Removed (only if legacy items were cleaned up)
+│     {✅} goals/            Legacy goals directory
 │     {✅} tools/memory/     Legacy memory scripts
 │     {✅} memory/           Legacy memory directory
 │
@@ -37,8 +32,7 @@ Present this summary after verification completes.
 │  ⚡ Next steps
 │     1. Review CLAUDE.md and customise for your project
 │     2. Add domain knowledge to context/
-│     3. Define your first goal in goals/
-│     4. Start building with the BRACE methodology
+│     3. Run /speccy to design your first feature
 │
 └─────────────────────────────────────────────────
 ```

package/skills/brace/references/scaffold-manifest.md

@@ -11,58 +11,10 @@ creation checklist. Phase 1 uses it to detect existing structure.
 | `.gitignore` | assets/gitignore-template | Standard ignores |
 | `~/.claude/CLAUDE.md` | assets/global-preferences-template.md | Global preferences (conditional on install_level) |
 
-## Goals Layer
-
-| Path | Source | Description |
-|------|--------|-------------|
-| `goals/` | mkdir | Process definitions directory |
-| `goals/manifest.md` | generated | Index of all goal workflows |
-| `goals/build_app.md` | references/brace-workflow.md | BRACE build methodology |
-
-## Tools Layer
-
-| Path | Source | Description |
-|------|--------|-------------|
-| `tools/` | mkdir | Deterministic scripts directory |
-| `tools/manifest.md` | generated | Index of all tools |
-
-## Context, Hard Prompts, Args Layers
+## Project Directories
 
 | Path | Description |
 |------|-------------|
+| `specs/` | Specifications produced by `/speccy`, consumed by `/build` |
 | `context/` | Reference material and domain knowledge |
-| `hardprompts/` | Reusable instruction templates |
-| `args/` | Behaviour settings (YAML/JSON) |
-
-## Temp
-
-| Path | Description |
-|------|-------------|
 | `.tmp/` | Scratch work (gitignored) |
-
-## Generated Manifest Content
-
-### goals/manifest.md
-```
-# Goals Manifest
-
-Index of all goal workflows in this project.
-
-| Goal | File | Description |
-|------|------|-------------|
-| Build App | build_app.md | BRACE 5-step build methodology |
-
-Add new goals here as they are created.
-```
-
-### tools/manifest.md
-```
-# Tools Manifest
-
-Index of all tools in this project.
-
-| Tool | Path | Description |
-|------|------|-------------|
-
-Add new tools here as they are created.
-```

package/skills/brace/tests/evals.json

@@ -1,7 +1,7 @@
 [
   {
     "name": "banner-and-tagline",
-    "prompt": "Initialize GOTCHA framework for this project",
+    "prompt": "Initialize this project with brace",
     "assertions": [
       { "type": "contains", "value": "██" },
       { "type": "regex", "value": "(Bracing the|Reinforcing before|Locking in the|Preparing for heavy|Cross-bracing|Tightening the load|Structural integrity|Brace for impact)" },
@@ -9,21 +9,20 @@
     ]
   },
   {
-    "name": "gotcha-framework",
-    "prompt": "Set up the GOTCHA structure in my project",
+    "name": "project-scaffold",
+    "prompt": "Set up the project scaffold with specs and context directories",
     "assertions": [
       { "type": "contains", "value": "██" },
-      { "type": "regex", "value": "GOTCHA", "flags": "i" },
-      { "type": "regex", "value": "(Goals|Orchestration|Tools|Context)", "flags": "i" },
-      { "type": "semantic", "value": "Describes the GOTCHA framework with its 6-layer structure: Goals, Orchestration, Tools, Context, Hard prompts, and Args" }
+      { "type": "regex", "value": "(specs|context|CLAUDE\\.md)", "flags": "i" },
+      { "type": "semantic", "value": "Describes creating a project scaffold with specs/, context/, and .tmp/ directories plus CLAUDE.md and .gitignore" }
     ]
   },
   {
     "name": "flag-handling",
-    "prompt": "Brace --no-brace this project directory",
+    "prompt": "Brace --force this project directory",
     "assertions": [
       { "type": "contains", "value": "██" },
-      { "type": "semantic", "value": "Acknowledges the --no-brace flag, indicating it will skip the BRACE build methodology while still creating the GOTCHA directory structure" }
+      { "type": "semantic", "value": "Acknowledges the --force flag, indicating it will overwrite existing files without prompting" }
     ]
   }
 ]

package/skills/build/SKILL.md

@@ -303,13 +303,13 @@ Invoke the `/ship` skill:
    Options:
    - **"Fix now"** → create a task list of resolution activities for
      each item; present for user confirmation, then work through them
-   - **"Create goals for future sessions"** → write goal files to `goals/`
-     (if GOTCHA structure exists) or append to CLAUDE.md as Known Issues
+   - **"Create tasks for future sessions"** → create persistent tasks via
+     `TaskCreate` for each item, or append to CLAUDE.md as Known Issues
    - **"Note and continue"** → acknowledge items without formal tracking;
      log to memory (if exists) or as source file comments. No further action.
    - **"Let me choose per item"** → present each individually with full
      description, evidence, and impact. Options per item:
-     "Fix now" / "Add to goals" / "Explain more" / "Note and continue".
+     "Fix now" / "Create task" / "Explain more" / "Note and continue".
      "Explain more" reads source files cited in evidence, provides
      expanded context, then re-presents the item for decision.
 

package/skills/build/references/stage-prompts.md

@@ -384,10 +384,10 @@ Options:
      a concrete task with the suggested_action. Present the task list
      for user confirmation, then work through them.
 
-- "Create goals for future sessions"
-  → For each item, write a goal file to goals/ (if GOTCHA structure
-     exists) or append to CLAUDE.md as a "Known Issues" section.
-     Format: one goal per category grouping, not one per item.
+- "Create tasks for future sessions"
+  → For each item, create a persistent task via TaskCreate with the
+     suggested_action as the task description, or append to CLAUDE.md
+     as a "Known Issues" section. Group by category, not one per item.
 
 - "Note and continue"
   → Acknowledge items without formal tracking. Log to memory (if memory

package/skills/manifest.json

@@ -1,12 +1,12 @@
 {
-  "generated": "2026-03-09T17:55:20.156Z",
+  "generated": "2026-03-10T03:11:12.089Z",
   "count": 10,
   "skills": [
     {
       "name": "brace",
       "directory": "brace",
-      "description": "'Initialize any project directory with the GOTCHA/BRACE framework for agentic AI systems. Creates the 6-layer structure (Goals, Orchestration, Tools, Context, Hard prompts, Args), BRACE build methodology, and a project CLAUDE.md. Recommends claude-mem for persistent memory. Idempotent — safe to run on existing projects. Triggers: \"init gotcha\", \"setup brace\", \"brace\", \"initialize framework\", \"bootstrap gotcha\".'",
-      "lines": 303,
+      "description": "'Initialize any project directory with a standard scaffold for AI-assisted development. Creates specs/ and context/ directories, a project CLAUDE.md with development workflow and guardrails, .gitignore, and branch protection. Recommends claude-mem for persistent memory. Idempotent — safe to run on existing projects. Triggers: \"init project\", \"setup brace\", \"brace\", \"initialize\", \"bootstrap\", \"scaffold\".'",
+      "lines": 328,
       "hasScripts": false,
       "hasReferences": true,
       "hasAssets": true,

package/skills/speccy/SKILL.md

@@ -94,7 +94,7 @@ Before asking any questions, build a thorough understanding of the project:
    the manual scan below.
 3. **Scan the project** (skip items already loaded by /prime):
    - Read `CLAUDE.md` if present (project conventions, structure, domain)
-   - Read goal/spec manifests: `goals/manifest.md`, `spec/` directory
+   - Read spec directory: `specs/` for existing specifications
    - Scan existing specs and design docs for context
    - Read relevant source code that relates to the GOAL
    - Check memory for prior decisions or open questions related to the GOAL

package/skills/brace/references/gotcha-principles.md

@@ -1,113 +0,0 @@
-# GOTCHA Framework Principles
-
-Embedded into the project CLAUDE.md during brace.
-
----
-
-## The GOTCHA Framework
-
-A 6-layer architecture for agentic systems that separates concerns between
-probabilistic reasoning (LLM) and deterministic execution (tools).
-
-**GOT** (The Engine):
-- **Goals** (`goals/`) — Task-specific instructions. Each goal defines:
-  objective, inputs, which tools to use, expected outputs, edge cases.
-  Only modified with explicit permission.
-- **Orchestration** — The AI manager (you). Reads goals, decides which tools
-  to use, applies args, references context, handles errors, delegates work.
-  Never executes work directly — delegates intelligently.
-- **Tools** (`tools/`) — Python scripts organised by workflow. Each has one
-  job: API calls, data processing, file operations, database work. Fast,
-  documented, testable, deterministic. All tools listed in `tools/manifest.md`.
-
-**CHA** (The Context):
-- **Context** (`context/`) — Static reference material: tone rules, writing
-  samples, ICP descriptions, case studies. Shapes quality/style, not process.
-- **Hard Prompts** (`hardprompts/`) — Reusable text templates for LLM
-  sub-tasks: outline-to-post, rewrite-in-voice, summarize-transcript.
-- **Args** (`args/`) — YAML/JSON files controlling behaviour: themes,
-  frameworks, modes, lengths, schedules, model choices. Changing args changes
-  behaviour without editing goals or tools.
-
-## How to Operate
-
-### 1. Check for existing goals first
-Before starting a task, check `goals/manifest.md`. If a goal exists, follow
-it — goals define the full process for common tasks.
-
-### 2. Check for existing tools
-Before writing new code, read `tools/manifest.md`. If a tool exists, use it.
-If you create a new tool, you **must** add it to the manifest.
-
-### 3. When tools fail, fix and document
-- Read the error and stack trace carefully
-- Update the tool to handle the issue
-- Add what you learned to the goal
-- If a goal gets too long, split into primary goal + technical reference
-
-### 4. Treat goals as living documentation
-- Update only when better approaches or API constraints emerge
-- Never modify/create goals without explicit permission
-
-### 5. Communicate clearly when stuck
-If you cannot complete a task with existing tools and goals:
-- Explain what is missing
-- Explain what you need
-- Do not guess or invent capabilities
-
-### 6. Guardrails
-- Always check `tools/manifest.md` before writing a new script
-- Verify tool output format before chaining into another tool
-- Do not assume APIs support batch operations — check first
-- When a workflow fails mid-execution, preserve intermediate outputs
-- Read the full goal before starting a task — do not skim
-
-## Memory
-
-For persistent memory across sessions, use the **claude-mem** plugin
-(`claude plugin install claude-mem`). It automatically captures context
-via lifecycle hooks and provides MCP tools for search, timeline, and
-observation management. Claude Code's built-in auto memory handles
-curated facts (`~/.claude/projects/<project>/memory/MEMORY.md`).
-
-## Question & Assumption Accountability
-
-Nothing gets silently dropped. Every open question, assumption, and deferred
-decision must be explicitly recorded and revisited.
-
-### During work:
-- When you make an assumption, **state it explicitly** and record it
-- When a question cannot be answered immediately, log it as an open item
-- When you defer a fix or skip an edge case, document why and what triggers it
-
-### At the end of each task:
-- Review all assumptions made — were they validated?
-- Review all open questions — were they answered?
-- Review all deferred items — are they tracked for follow-up?
-- Present unresolved items to the user with context and suggested actions
-
-### Persistence:
-- Unresolved items go to `goals/` as documented follow-ups, to CLAUDE.md
-  as "Known Issues", or to memory for future session awareness
-- Never close a task with unacknowledged open questions
-- At the start of new work, check for outstanding items from previous sessions
-
-### Why this matters:
-90% accuracy per step means ~59% accuracy over 5 steps. Silent assumptions
-compound. Explicit tracking breaks the chain — each assumption is either
-validated or flagged before it can propagate.
-
-## The Continuous Improvement Loop
-
-Every failure strengthens the system:
-1. Identify what broke and why
-2. Fix the tool script
-3. Test until it works reliably
-4. Update the goal with new knowledge
-5. Next time — automatic success
-
-## Deliverables vs Scratch
-
-- **Deliverables**: outputs needed by the user (processed data, reports, etc.)
-- **Scratch work**: temp files (raw scrapes, CSVs, research). Always disposable.
-- Never store important data in `.tmp/`