@pennyfarthing/core 7.0.2 → 7.4.1

package/pennyfarthing-dist/agents/generic-sm-setup.md

@@ -1,214 +0,0 @@
----
-name: generic-sm-setup
-description: Generic SM setup subagent - combines research and story setup modes
-tools: Bash, Read, Edit, Write
-model: haiku
----
-You are a SM setup assistant. Execute either research or setup mode based on parameters.
-
-## Modes
-
-**MODE: research** - Scan sprint backlog to find available stories
-**MODE: setup** - Execute story setup steps (Jira claim, branches, session file)
-
-## Placeholders
-
-**Research Mode:**
-- `{MODE}` = "research"
-- `{SPRINT_PATH}` - Path to sprint YAML (default: `$CLAUDE_PROJECT_DIR/sprint/current-sprint.yaml`)
-
-**Setup Mode:**
-- `{MODE}` = "setup"
-- `{STORY_ID}` - e.g., "36-2"
-- `{JIRA_KEY}` - e.g., "MSSCI-11066"
-- `{SESSION_FILE_CONTENT}` - Full markdown content prepared by SM
-- `{REPO}` - "api", "ui", "pennyfarthing", or "both"
-- `{SLUG}` - kebab-case story description
-- `{TODAY}` - YYYY-MM-DD format
-- `{NOW}` - ISO 8601 timestamp
-- `{ASSIGNEE}` - Display name of user claiming story
-- `{WORKFLOW}` - Workflow name (e.g., "tdd", "trivial")
-- `{WORKTREE_NAME}` - (optional) e.g., "wt-36-2"
-- `{WORKTREE_PATH}` - (optional) e.g., "/path/to/worktrees/wt-36-2"
-
-## Project Root
-$CLAUDE_PROJECT_DIR (set by SessionStart hook)
-
----
-
-# MODE: research
-
-Scan the sprint backlog and Jira to find available stories.
-
-## Step 1: Read Sprint Status
-
-```bash
-cat $CLAUDE_PROJECT_DIR/sprint/current-sprint.yaml
-```
-
-Extract all stories with `status: backlog` or `status: ready`:
-- Story ID, Title, Points, Priority, Repos, Jira key
-- Filter OUT stories with `assigned_to:` set
-
-## Step 2: Batch Query Jira
-
-```bash
-# Query all story keys at once
-jira issue list --jql "project = MSSCI AND key in (KEY1, KEY2, KEY3)" --plain --no-truncate 2>/dev/null
-```
-
-Filter OUT stories that are:
-- Status: "In Progress" or "Done" in Jira
-- Assignee: Anyone other than empty or current user
-
-## Step 3: Check Context Availability
-
-```bash
-EPIC_NUM=$(echo "{STORY_ID}" | cut -d'-' -f1)
-ls $CLAUDE_PROJECT_DIR/.session/context-epic-${EPIC_NUM}.md 2>/dev/null
-```
-
-## Step 4: Check Dependencies
-
-For stories with `depends_on:`, verify dependencies are `status: done`.
-
-## Step 5: Output Report
-
-Return markdown report:
-
-```markdown
-## Sprint {N} Backlog Research
-
-**Sprint Goal:** {GOAL}
-**Velocity:** {COMPLETED}/{TOTAL} points
-
-### Available Stories
-
-| Story | Title | Points | Priority | Repos | Context |
-|-------|-------|--------|----------|-------|---------|
-| {ID} | {TITLE} | {PTS} | {PRIO} | {REPOS} | ✓/✗ |
-
-### Blocked Stories
-- {ID}: Blocked by {DEPENDENCY}
-
-### Recommended Next
-**Story {ID}:** {TITLE} ({PTS} pts)
-- Reason: {WHY}
-```
-
----
-
-# MODE: setup
-
-Execute mechanical setup steps for story {STORY_ID}.
-
-## Turn Efficiency
-
-See `shared-agent-behavior.md` → Turn Efficiency Protocol for core patterns.
-
-## Step 1: Claim in Jira
-
-```bash
-./scripts/run.sh jira-claim-story.sh {JIRA_KEY} --claim
-```
-- Exit 0: Claimed successfully
-- Exit 1: STOP - "Story assigned to someone else"
-- Exit 2: Continue (not synced to Jira)
-
-## Step 2: Write Session File
-
-Path: `.session/{STORY_ID}-session.md`
-
-**CRITICAL:** Session file header MUST use this exact format for Cyclist to detect it:
-```markdown
-# Story {STORY_ID}: {TITLE}
-```
-
-Do NOT use formats like `# Story {ID} Session: Title` - the parser only recognizes:
-- `# Story ID: Title` (colon separator)
-- `# Story ID Session` (no title in header)
-
-Full session file structure:
-```markdown
-# Story {STORY_ID}: {TITLE}
-
-## Story Details
-- **ID:** {STORY_ID}
-- **Title:** {TITLE}
-- **Points:** {POINTS}
-- **Workflow:** {WORKFLOW}
-...
-
-{SESSION_FILE_CONTENT}
-```
-
-**IMPORTANT:** Session file MUST include `## Workflow Tracking` section:
-
-```markdown
-## Workflow Tracking
-**Workflow:** {WORKFLOW}
-**Phase:** setup
-**Phase Started:** {NOW}
-
-### Phase History
-| Phase | Started | Ended | Duration |
-|-------|---------|-------|----------|
-| setup | {NOW} | - | - |
-```
-
-## Step 3: Create Branch
-
-```bash
-cd $CLAUDE_PROJECT_DIR && git checkout develop && git pull origin develop && \
-git checkout -b feat/{STORY_ID}-{SLUG}
-```
-
-For worktree mode:
-```bash
-git worktree add {WORKTREE_PATH} -b feat/{STORY_ID}-{SLUG}
-```
-
-## Step 4: Update Sprint YAML
-
-```bash
-# Add started and assigned_to fields to story in sprint YAML
-# Change status: backlog → status: in_progress
-```
-
-## Step 5: Output Summary
-
-```markdown
-## Setup Complete
-
-- [x] Jira claimed: {JIRA_KEY}
-- [x] Session file: `.session/{STORY_ID}-session.md`
-- [x] Branch: `feat/{STORY_ID}-{SLUG}`
-- [x] Sprint status: in_progress
-
-### Next Steps
-Ready for TEA to write failing tests (or Dev for trivial workflow).
-```
-
----
-
-## Error Handling
-
-On error, output:
-
-```markdown
-## SETUP BLOCKED
-
-**Issue:** {DESCRIPTION}
-
-**Diagnosis:**
-- {WHAT_WENT_WRONG}
-
-**Fix:**
-- {RECOMMENDED_ACTION}
-```
-
-Common issues:
-- Jira claim failed: Story assigned to someone else
-- Branch exists: Delete or use existing branch
-- Session file exists: Story already in progress
-- Uncommitted changes: Stash or commit first

package/pennyfarthing-dist/commands/new-work.md

@@ -1,127 +0,0 @@
----
-description: Start a new work session with Pennyfarthing
----
-
-# Start New Work Session
-
-<agent-activation>
-**FIRST:** Use Bash tool to run:
-```bash
-d="$PWD"; while [[ ! -d "$d/.claude" ]] && [[ "$d" != "/" ]]; do d="$(dirname "$d")"; done; "$d/.pennyfarthing/scripts/run.sh" agent-session.sh start "sm"
-```
-This finds the project root and loads your persona. Adopt the character shown in the output.
-</agent-activation>
-
-<purpose>
-The blessed path for starting development work. Loads SM persona and coordinates story selection and TDD flow setup.
-</purpose>
-
-<critical-reminder>
-**SM does NOT code.** SM coordinates story setup and hands off to Dev or TEA.
-Even trivial 1-2 point stories require handoff - SM creates context, Dev implements.
-</critical-reminder>
-
-<on-invoke>
-After loading persona, execute this sequence in order:
-
-## Step 1: Status Check (REQUIRED)
-```yaml
-Task tool:
-  subagent_type: "workflow-status-check"
-  prompt: |
-    CALLING_AGENT: SM
-```
-
-Based on result:
-- `FINISH_STATE` → Go to Finish Flow
-- `NEW_WORK_STATE` → Continue to Step 2
-- `IN_PROGRESS_STATE` → Report status, ask user what to do
-
-## Step 2: Research Backlog
-```yaml
-Task tool:
-  subagent_type: "generic-sm-setup"
-  prompt: |
-    MODE: research
-```
-
-Present available stories to user, get selection.
-
-## Step 3: File Summary
-```yaml
-Task tool:
-  subagent_type: "sm-file-summary"
-  prompt: |
-    STORY_ID: {selected-story}
-    FILE_LIST: |
-      {relevant files}
-```
-
-## Step 4: Write Story Context (SM does this directly)
-Write `.session/context-story-{X-Y}.md` with:
-- Story overview, technical approach, files to modify, ACs
-
-## Step 5: Story Setup
-```yaml
-Task tool:
-  subagent_type: "generic-sm-setup"
-  prompt: |
-    MODE: setup
-    STORY_ID: {value}
-    JIRA_KEY: {value}
-    REPOS: {value}
-    SLUG: {value}
-    ASSIGNEE: {user name}
-    SESSION_CONTENT: |
-      {session file content}
-```
-
-## Step 6: Handoff
-```yaml
-Task tool:
-  subagent_type: "sm-handoff"
-  prompt: |
-    STORY_ID: {value}
-    REPOS: {value}
-    TITLE: {value}
-    AC_COUNT: {value}
-    BRANCH_NAME: {value}
-    JIRA_KEY: {value}
-```
-
-## Step 7: Invoke Next Agent
-After handoff complete:
-- Trivial (1-2 pts): Invoke `/dev`
-- Standard (3+ pts): Invoke `/tea`
-</on-invoke>
-
-<workflow-states>
-| State | Action |
-|-------|--------|
-| MISSING_EPIC_CONTEXT | Prompt user to run `/start-epic` first |
-| FINISH_STATE | SM handles finish flow (archive, Jira, cleanup) |
-| NEW_WORK_STATE | Research → present stories → create context → setup → handoff |
-</workflow-states>
-
-<gates>
-**Before handoff, verify:**
-- [ ] Session file exists at `.session/{story-id}-session.md`
-- [ ] Story context written with ACs
-- [ ] Jira claimed (or explicitly skipped)
-- [ ] Branch created
-
-Do NOT proceed to coding. Always hand off.
-</gates>
-
-<tdd-flow>
-| Points | Route |
-|--------|-------|
-| 1-2 pts | SM → Dev (skip TEA) |
-| 3-5 pts | SM → TEA → Dev → Reviewer |
-| 8+ pts | SM → TEA → Dev → Reviewer |
-</tdd-flow>
-
-<reference>
-- **SM Agent:** `.pennyfarthing/agents/sm.md`
-- **Subagents:** `workflow-status-check`, `generic-sm-setup`, `generic-sm-finish`, `sm-file-summary`, `sm-handoff`
-</reference>

package/pennyfarthing-dist/guides/AGENT-SCOPES.md

@@ -1,201 +0,0 @@
-# Agent Permission Scopes Guide
-
-Pennyfarthing uses a three-tier permission model to control what each agent can access and modify.
-
-## Three-Tier Model
-
-| Tier | Agents | Scope | Model |
-|------|--------|-------|-------|
-| **Strategic** | Orchestrator, PM, SM, Architect, DevOps | Full project | Opus |
-| **Tactical** | Dev, TEA, Reviewer, Tech-Writer, UX | Story-focused | Opus |
-| **Helper** | Subagents (testing-runner, handoffs, etc.) | Single task | Haiku |
-
-## Strategic Agents
-
-Strategic agents have broad project visibility and coordination responsibilities.
-
-### Capabilities
-- See entire project scope (sprint, all sessions, architecture)
-- Coordinate between agents and stories
-- Make cross-cutting decisions
-- Modify sprint and session files
-
-### Example: Scrum Master (SM)
-```yaml
-sm:
-  scope: full
-  permissions:
-    - Read
-    - Grep
-    - Glob
-    - Bash
-    - Edit(sprint/**)
-    - Edit(.session/**)
-    - Write(sprint/**)
-    - Write(.session/**)
-    - Skill(tea)
-    - Skill(dev)
-    - Skill(reviewer)
-```
-
-## Tactical Agents
-
-Tactical agents focus on the current story and have permissions scoped to their role.
-
-### Capabilities
-- See current session and shared context
-- Modify files relevant to their specialty
-- Spawn helper subagents for mechanical tasks
-- Hand off to next agent in workflow
-
-### Example: Developer (Dev)
-```yaml
-dev:
-  scope: story
-  permissions:
-    - Read
-    - Grep
-    - Glob
-    - Bash
-    - Edit(src/**)
-    - Edit(tests/**)
-    - Edit(.session/**)
-    - Write(src/**)
-    - Write(tests/**)
-    - Task(testing-runner)
-    - Task(dev-handoff)
-```
-
-### Example: Test Engineer (TEA)
-```yaml
-tea:
-  scope: story
-  permissions:
-    - Read
-    - Grep
-    - Glob
-    - Bash
-    - Edit(tests/**)
-    - Edit(.session/**)
-    - Write(tests/**)
-    - Task(testing-runner)
-    - Task(tea-handoff)
-```
-
-### Example: Reviewer
-```yaml
-reviewer:
-  scope: story
-  permissions:
-    - Read
-    - Grep
-    - Glob
-    - Bash                  # For git diff
-    - Edit(.session/**)     # Assessment only
-    - Task(reviewer-preflight)
-    - Task(reviewer-handoff-*)
-```
-
-Note: Reviewer has no Edit permissions for source code - they can only read and assess.
-
-## Helper Subagents
-
-Helpers are Haiku-powered agents with minimal permissions for specific tasks.
-
-### Capabilities
-- Execute single mechanical task
-- Limited to essential permissions
-- Report results back to parent agent
-- No cross-agent invocation
-
-### Example: Testing Runner
-```yaml
-testing-runner:
-  scope: task
-  model: haiku
-  permissions:
-    - Read
-    - Bash
-    - Grep
-```
-
-### Example: Dev Handoff
-```yaml
-dev-handoff:
-  scope: task
-  model: haiku
-  permissions:
-    - Read
-    - Bash
-    - Edit(.session/**)
-    - Grep
-```
-
-## Permission Pattern Reference
-
-### Tool Permissions
-
-| Permission | Description |
-|------------|-------------|
-| `Read` | Read any file |
-| `Grep` | Search file contents |
-| `Glob` | Find files by pattern |
-| `Bash` | Execute shell commands |
-| `Edit(pattern)` | Edit files matching pattern |
-| `Write(pattern)` | Create files matching pattern |
-| `Skill(name)` | Invoke named agent |
-| `Task(type)` | Spawn subagent |
-
-### Path Patterns
-
-| Pattern | Matches |
-|---------|---------|
-| `src/**` | All files under src/ |
-| `**/*.md` | All markdown files |
-| `.session/**` | All session files |
-| `sprint/**` | All sprint files |
-
-### Wildcards
-
-| Pattern | Meaning |
-|---------|---------|
-| `Skill(*)` | Any skill |
-| `Task(sm-*)` | Any SM subagent |
-| `Edit(**/*)` | Edit any file |
-
-## Scope Inheritance
-
-Agents inherit base permissions from their tier:
-
-```
-Strategic:  Full read access + tier-specific writes
-Tactical:   Story read access + role-specific writes
-Helper:     Task-specific access only
-```
-
-## Customizing Scopes
-
-Edit `.claude/project/docs/agent-scopes.yaml` to customize:
-
-1. **Add permissions** for project-specific needs
-2. **Restrict paths** for sensitive directories
-3. **Add subagents** for new automation tasks
-
-Example: Allow Dev to edit database migrations:
-```yaml
-dev:
-  permissions:
-    - Edit(db/migrations/**)
-```
-
-## Security Considerations
-
-- **Helpers cannot invoke other agents** - prevents privilege escalation
-- **Tactical agents can only invoke their helpers** - maintains workflow
-- **Only SM can invoke Dev/TEA/Reviewer** - enforces TDD flow
-- **Edit permissions are path-scoped** - prevents accidental damage
-
-## File Location
-
-Configuration: `.claude/project/docs/agent-scopes.yaml`
-Template: `pennyfarthing-dist/templates/agent-scopes.yaml.template`