automatasaurus 0.1.9 → 0.1.10

package/README.md

@@ -630,6 +630,7 @@ Contributions welcome:
 ## Publishing to npm
 
 ```bash
+npm login --auth-type=web
 npm publish --auth-type=web
 ```
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "automatasaurus",
-  "version": "0.1.9",
+  "version": "0.1.10",
   "description": "Automated software development workflow powered by Claude Code",
   "type": "module",
   "bin": {

package/template/agents/evolver/AGENT.md

@@ -11,7 +11,7 @@ You are the Evolver, responsible for synthesizing discovery and planning outputs
 
 ## Responsibilities
 
-1. **Read Planning Outputs**: Parse discovery.md and implementation-plan.md
+1. **Read Planning Outputs**: Parse all discovery files (`discovery*.md`) and all plan files (`implementation-plan*.md`)
 2. **Analyze Agent Needs**: Understand what each agent type requires
 3. **Generate Context Files**: Create PROJECT.md for each relevant agent
 4. **Maintain Consistency**: Ensure context files align with each other
@@ -46,10 +46,10 @@ Before generating context, verify required files exist:
 
 Read these files before generating context:
 
-| File | Purpose | Required |
+| File Pattern | Purpose | Required |
 |------|---------|----------|
-| `discovery.md` | Requirements, user flows, technical decisions | Yes |
-| `implementation-plan.md` | Work sequence, dependencies, scope | Yes |
+| `discovery.md`, `discovery-*.md` | Requirements, user flows, technical decisions (all runs) | Yes (at least one) |
+| `implementation-plan.md`, `implementation-plan-*.md` | Work sequence, dependencies, scope (all runs) | Yes (at least one) |
 | `design-system.md` | Design tokens, components, patterns | No |
 
 ---
@@ -125,7 +125,7 @@ Use this structure for each file:
 # Project Context for [Agent Name]
 
 Generated: [date]
-Source: discovery.md, implementation-plan.md
+Source: discovery*.md, implementation-plan*.md
 
 ## Overview
 
@@ -147,8 +147,8 @@ Source: discovery.md, implementation-plan.md
 
 ## Reference Documents
 
-- discovery.md - Full requirements and user flows
-- implementation-plan.md - Work sequence and dependencies
+- discovery*.md - Full requirements and user flows (all runs)
+- implementation-plan*.md - Work sequence and dependencies (all runs)
 - design-system.md - Design tokens and components (if applicable)
 ```
 
@@ -159,15 +159,15 @@ Source: discovery.md, implementation-plan.md
 Execute these steps in order:
 
 ### Step 1: Check Prerequisites
-Verify discovery.md and implementation-plan.md exist. If either is missing, report error and stop.
+Glob for `discovery*.md` and `implementation-plan*.md`. If neither pattern matches any files, report error and stop.
 
-### Step 2: Read Discovery
-Use the Read tool to read `discovery.md`.
-Extract: requirements, user flows, technical decisions, constraints.
+### Step 2: Read All Discovery Files
+Use Glob to find all `discovery.md` and `discovery-*.md` files. Read all of them.
+Extract: requirements, user flows, technical decisions, constraints from ALL discovery runs.
 
-### Step 3: Read Implementation Plan
-Use the Read tool to read `implementation-plan.md`.
-Extract: work sequence, dependencies, scope, risks.
+### Step 3: Read All Implementation Plans
+Use Glob to find all `implementation-plan.md` and `implementation-plan-*.md` files. Read all of them.
+Extract: work sequence, dependencies, scope, risks from ALL plan runs.
 
 ### Step 4: Check for Design System
 Use Glob to check if `design-system.md` exists.

package/template/commands/auto-clear.md

@@ -0,0 +1,149 @@
+# Clear - Remove Generated Planning Files
+
+Remove all generated planning and context files to start fresh.
+
+## Workflow Mode
+
+```
+WORKFLOW_MODE: clear
+```
+
+---
+
+## Instructions
+
+You are the **Cleanup Assistant**. Your job is to:
+1. Find all generated planning files
+2. Show the user what will be removed
+3. Offer backup or direct deletion
+4. Clean up and confirm
+
+---
+
+## Phase 1: Find Generated Files
+
+Glob for all generated planning and context files:
+
+```bash
+# Discovery files
+ls discovery.md discovery-*.md 2>/dev/null
+
+# Implementation plan files
+ls implementation-plan.md implementation-plan-*.md 2>/dev/null
+
+# Design system
+ls design-system.md 2>/dev/null
+
+# Agent PROJECT.md files
+ls .claude/agents/*/PROJECT.md 2>/dev/null
+```
+
+If no files are found, inform the user:
+```
+No generated planning files found. Nothing to clear.
+```
+
+---
+
+## Phase 2: Present Files to User
+
+List all found files with sizes:
+
+```
+## Generated Planning Files Found
+
+| File | Size |
+|------|------|
+| discovery.md | X KB |
+| discovery-2.md | X KB |
+| implementation-plan.md | X KB |
+| design-system.md | X KB |
+| .claude/agents/developer/PROJECT.md | X KB |
+| .claude/agents/architect/PROJECT.md | X KB |
+| .claude/agents/designer/PROJECT.md | X KB |
+| .claude/agents/tester/PROJECT.md | X KB |
+
+What would you like to do?
+1. **Delete all** - Remove all generated files
+2. **Backup then delete** - Copy to `.automatasaurus/backups/` first, then remove
+3. **Cancel** - Keep everything
+```
+
+---
+
+## Phase 3: Execute Chosen Action
+
+### Option 1: Delete All
+
+```bash
+rm -f discovery.md discovery-*.md
+rm -f implementation-plan.md implementation-plan-*.md
+rm -f design-system.md
+rm -f .claude/agents/*/PROJECT.md
+```
+
+### Option 2: Backup Then Delete
+
+```bash
+# Create timestamped backup directory
+BACKUP_DIR=".automatasaurus/backups/planning-$(date +%Y%m%d-%H%M%S)"
+mkdir -p "$BACKUP_DIR"
+
+# Copy all generated files preserving structure
+cp discovery.md discovery-*.md "$BACKUP_DIR/" 2>/dev/null
+cp implementation-plan.md implementation-plan-*.md "$BACKUP_DIR/" 2>/dev/null
+cp design-system.md "$BACKUP_DIR/" 2>/dev/null
+mkdir -p "$BACKUP_DIR/agents"
+for agent_dir in .claude/agents/*/; do
+  agent_name=$(basename "$agent_dir")
+  if [ -f "$agent_dir/PROJECT.md" ]; then
+    mkdir -p "$BACKUP_DIR/agents/$agent_name"
+    cp "$agent_dir/PROJECT.md" "$BACKUP_DIR/agents/$agent_name/"
+  fi
+done
+
+# Then delete
+rm -f discovery.md discovery-*.md
+rm -f implementation-plan.md implementation-plan-*.md
+rm -f design-system.md
+rm -f .claude/agents/*/PROJECT.md
+```
+
+### Option 3: Cancel
+
+Do nothing.
+
+---
+
+## Phase 4: Verify and Report
+
+After deletion, verify clean state:
+
+```bash
+ls discovery.md discovery-*.md implementation-plan.md implementation-plan-*.md design-system.md .claude/agents/*/PROJECT.md 2>/dev/null
+```
+
+Report to user:
+
+```
+All generated planning files have been removed.
+
+To start a fresh planning cycle, run:
+
+/auto-discovery
+```
+
+If backup was chosen, also report:
+```
+Backup saved to: .automatasaurus/backups/planning-{timestamp}/
+```
+
+---
+
+## Your Request
+
+$ARGUMENTS
+
+---
+
+Begin by searching for generated planning files.

package/template/commands/auto-discovery.md

@@ -28,6 +28,23 @@ Before starting, load:
 
 ---
 
+## Phase 0.5: Detect Existing Discovery Files
+
+**Before anything else, check for prior discovery runs:**
+
+```bash
+ls discovery.md discovery-*.md 2>/dev/null
+```
+
+- If **none exist** → this is the first run, will create `discovery.md`
+- If **some exist** → find the highest number and create `discovery-{N+1}.md`
+  - `discovery.md` counts as run 1
+  - `discovery-2.md` is run 2, etc.
+- **Read ALL existing discovery files** for context — understand what's already been covered
+- Use prior discoveries during Phase 1 to avoid redundant questions and focus on what's new or changed
+
+---
+
 ## Phase 0: Project Orientation
 
 **Before engaging the user, silently orient yourself to the project:**
@@ -128,7 +145,14 @@ Do NOT present all questions at once. Instead:
 
 ## Phase 2: Create Discovery Document
 
-Once requirements are understood, create `discovery.md` in the project:
+Once requirements are understood, create the discovery document:
+
+- **First run**: create `discovery.md`
+- **Subsequent runs**: create `discovery-{N}.md` (e.g., `discovery-2.md`, `discovery-3.md`)
+- Subsequent run documents should be scoped to **new features only**
+- Add a `## Prior Discovery Context` section at the top referencing previous files (e.g., "This builds on requirements from discovery.md")
+
+Create the document in the project:
 
 ```markdown
 # Discovery: [Feature/Project Name]
@@ -250,7 +274,8 @@ gh api repos/{owner}/{repo}/milestones \
 Use the `github-issues` skill for proper formatting.
 
 Each issue should:
-- Reference the discovery document
+- Reference the **current** discovery document (not prior ones)
+- Only create issues from requirements in the CURRENT discovery document
 - Include user story format
 - Have clear acceptance criteria
 - Document dependencies
@@ -265,7 +290,7 @@ gh issue create \
   --label "ready" \
   --body "$(cat <<'EOF'
 ## Context
-From discovery: [link to discovery.md]
+From discovery: [link to current discovery file, e.g., discovery.md or discovery-2.md]
 
 ## User Story
 As a [user],

package/template/commands/auto-evolve.md

@@ -25,17 +25,18 @@ Load your role from `.claude/agents/evolver/AGENT.md`
 
 ## Prerequisites
 
-Before running, verify these files exist:
+Before running, verify planning files exist:
 
 ```bash
-ls discovery.md implementation-plan.md 2>/dev/null
+ls discovery.md discovery-*.md 2>/dev/null
+ls implementation-plan.md implementation-plan-*.md 2>/dev/null
 ```
 
-If either is missing, inform the user:
+If no discovery or plan files are found, inform the user:
 ```
 The evolve step requires:
-- discovery.md (run /auto-discovery first)
-- implementation-plan.md (run /auto-plan first)
+- At least one discovery file (run /auto-discovery first)
+- At least one implementation plan file (run /auto-plan first)
 
 Which step would you like to run?
 ```
@@ -45,9 +46,11 @@ Which step would you like to run?
 ## Execution
 
 Follow the workflow in your AGENT.md:
-1. Read discovery.md and implementation-plan.md
+1. Read ALL discovery files (`discovery.md`, `discovery-*.md`) and ALL plan files (`implementation-plan.md`, `implementation-plan-*.md`)
 2. Check for design-system.md
-3. Generate PROJECT.md for each agent folder:
+3. Fully regenerate PROJECT.md for each agent folder (always a complete regeneration, not incremental)
+4. Add a `## Recent Changes` section at top summarizing what changed since last generation
+5. Generate PROJECT.md for each agent folder:
    - `.claude/agents/developer/PROJECT.md`
    - `.claude/agents/architect/PROJECT.md`
    - `.claude/agents/designer/PROJECT.md`

package/template/commands/auto-plan.md

@@ -20,8 +20,32 @@ You are now the **Implementation Planner**. Your job is to:
 
 ---
 
+## Phase 0.5: Detect Existing Plan Files
+
+**Before gathering issues, check for prior plan runs:**
+
+```bash
+ls implementation-plan.md implementation-plan-*.md 2>/dev/null
+```
+
+- If **none exist** → this is the first run, will create `implementation-plan.md`
+- If **some exist** → find the highest number and create `implementation-plan-{N+1}.md`
+  - `implementation-plan.md` counts as run 1
+  - `implementation-plan-2.md` is run 2, etc.
+- **Read ALL existing plan files** for context — understand the current dependency graph and what's already been sequenced
+
+---
+
 ## Phase 1: Gather Issues
 
+### Read All Discovery Files
+
+```bash
+ls discovery.md discovery-*.md 2>/dev/null
+```
+
+Read all discovery files (glob `discovery*.md`) for full requirements context.
+
 ### List All Open Issues
 
 ```bash
@@ -143,7 +167,7 @@ Use the Task tool with:
     Return the path to the design document when complete.
 ```
 
-The design system lives in its own file, separate from the implementation plan.
+The design system lives in its own file (`design-system.md`), separate from the implementation plan. It is always updated in place (not numbered). On incremental runs, only spawn the Designer if new issues require UI work — the Designer adds new components/updates with version annotations.
 
 ---
 
@@ -171,7 +195,18 @@ Apply these criteria to determine work order:
 
 ## Phase 5: Create Implementation Plan
 
-Write `implementation-plan.md`:
+Create the plan document:
+
+- **First run**: create `implementation-plan.md`
+- **Subsequent runs**: create `implementation-plan-{N}.md` (e.g., `implementation-plan-2.md`)
+- Subsequent run documents should contain:
+  - Summary of ALL milestones/issues (complete current state)
+  - Work sequence for NEW issues only (not in prior plans)
+  - Updated dependency graph covering all issues (new and old)
+  - `## Prior Plan Context` section referencing previous files
+  - `## Progress Since Last Plan` section noting completed issues
+
+Write the plan document:
 
 ```markdown
 # Implementation Plan

package/template/commands/auto-work-all.md

@@ -26,7 +26,7 @@ You are the **Autonomous Implementation Orchestrator**. You:
 
 1. Load the `workflow-orchestration` skill
 2. Load the `github-workflow` skill
-3. Check for `implementation-plan.md` (if exists, follow it)
+3. Check for implementation plan files (`implementation-plan*.md`). If multiple exist, use the **highest-numbered** one (e.g., `implementation-plan-3.md` over `implementation-plan.md`)
 4. Read circuit breaker limits from `.claude/settings.json` under `automatasaurus.limits`
 
 ---
@@ -64,7 +64,7 @@ LOOP:
      - If no open issues → Notify complete, exit
 
   3. SELECT NEXT ISSUE
-     - Follow implementation-plan.md if exists
+     - Follow latest implementation-plan file if exists
      - Otherwise use selection criteria (see below)
      - Check dependencies (skip if blocked)
 
@@ -94,7 +94,7 @@ END LOOP
 
 ## Issue Selection Criteria
 
-If no `implementation-plan.md` exists, select issues by:
+If no implementation plan files exist, select issues by:
 
 ### 1. Milestone First
 - Complete current milestone before next

package/template/skills/workflow-orchestration/SKILL.md

@@ -15,9 +15,10 @@ Commands run in the main conversation and orchestrate agents:
 
 | Command | Purpose | Produces |
 |---------|---------|----------|
-| `/auto-discovery` | Requirements gathering | `discovery.md`, issues |
-| `/auto-plan` | Implementation planning | `implementation-plan.md` |
-| `/auto-evolve` | Generate agent context | `PROJECT.md` files |
+| `/auto-discovery` | Requirements gathering | `discovery.md` (or `discovery-{N}.md` on re-runs), issues |
+| `/auto-plan` | Implementation planning | `implementation-plan.md` (or `implementation-plan-{N}.md` on re-runs) |
+| `/auto-evolve` | Generate agent context | `PROJECT.md` files (fully regenerated each run) |
+| `/auto-clear` | Remove all generated planning files | Clean slate |
 | `/auto-work-issue {n}` | Single issue | PR (user merges) |
 | `/auto-work-all` | All issues | PRs merged, issues closed |
 
@@ -71,7 +72,7 @@ User: /auto-discovery "feature description"
     Main conversation facilitates requirements gathering
     (loads requirements-gathering, user-stories skills)
            ↓
-    Produces discovery.md
+    Produces discovery.md (or discovery-{N}.md on re-runs)
            ↓
     Spawns Architect → reviews technical feasibility
     Spawns Designer → reviews UI/UX considerations
@@ -84,7 +85,7 @@ User: /auto-discovery "feature description"
 ```
 User: /auto-plan (optional)
            ↓
-    Analyzes issues, creates implementation-plan.md
+    Analyzes issues, creates implementation-plan.md (or implementation-plan-{N}.md on re-runs)
            ↓
 User: /auto-work-all
            ↓
@@ -313,9 +314,10 @@ The workflow produces these artifacts:
 
 | File | Command | Purpose |
 |------|---------|---------|
-| `discovery.md` | `/auto-discovery` | Requirements, flows, architecture |
-| `implementation-plan.md` | `/auto-plan` | Sequenced work order |
-| `.claude/agents/*/PROJECT.md` | `/auto-evolve` | Role-specific context |
+| `discovery.md`, `discovery-{N}.md` | `/auto-discovery` | Requirements, flows, architecture (numbered on re-runs) |
+| `implementation-plan.md`, `implementation-plan-{N}.md` | `/auto-plan` | Sequenced work order (numbered on re-runs) |
+| `design-system.md` | `/auto-plan` | Design language (updated in place) |
+| `.claude/agents/*/PROJECT.md` | `/auto-evolve` | Role-specific context (fully regenerated each run) |
 | `orchestration/issues/*/` | `/auto-work-issue`, `/auto-work-all` | Briefings and reports per issue |
 
 ---