@pennyfarthing/core 7.8.2 → 7.9.0

package/pennyfarthing-dist/agents/architect.md

@@ -61,12 +61,6 @@ FILE_LIST: "{comma-separated file paths}"
 - `/dev-patterns` - Implementation patterns
 </skills>
 
-<context>
-Context auto-loaded by `/prime --agent architect`:
-- Shared context, shared behavior
-- Agent sidecar: `.pennyfarthing/sidecars/architect/`
-</context>
-
 <reasoning-mode>
 
 **Default:** Quiet mode - follow ReAct pattern internally, show only key decisions
@@ -90,11 +84,9 @@ REFLECT: Recommend REST endpoint following existing patterns. Document in ADR.
 </reasoning-mode>
 
 <on-activation>
-1. Load sprint status from `sprint/current-sprint.yaml`
-2. Check for active work in `.session/*-session.md`
-3. Review architectural context (current patterns and decisions)
-4. Assess design needs
-5. Load additional docs lazily as needed
+1. Context already loaded by prime
+2. Review architectural context (current patterns and decisions)
+3. Assess design needs
 </on-activation>
 
 <delegation>

package/pennyfarthing-dist/agents/dev.md

@@ -59,7 +59,7 @@ PR_NUMBER: "{PR_NUMBER}"
 
 Read `**Workflow:**` and `**Phase:**` from session. Query:
 ```bash
-OWNER=$($CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/run.sh workflow/phase-owner.sh {workflow} {phase})
+OWNER=$(.pennyfarthing/scripts/core/run.sh workflow/phase-owner.sh {workflow} {phase})
 ```
 
 **If OWNER != "dev":** Run `handoff-marker.sh $OWNER`, output result, tell user.
@@ -153,7 +153,7 @@ Write to session file BEFORE spawning handoff:
 3. Await `HANDOFF_RESULT` with `next_agent`
 4. **ABSOLUTE LAST ACTION:**
    ```bash
-   $CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/handoff-marker.sh {next_agent}
+   .pennyfarthing/scripts/core/handoff-marker.sh {next_agent}
    ```
 5. Output result verbatim and EXIT
 </exit-sequence>

package/pennyfarthing-dist/agents/devops.md

@@ -72,12 +72,6 @@ FILE_LIST: "{comma-separated config file paths}"
 - `/release` - Release management workflow
 </skills>
 
-<context>
-Context auto-loaded by `/prime --agent devops`:
-- Shared context, shared behavior
-- Agent sidecar: `.pennyfarthing/sidecars/devops/`
-</context>
-
 <reasoning-mode>
 
 **Default:** Quiet mode - follow ReAct pattern internally, show only key decisions
@@ -101,11 +95,9 @@ REFLECT: Add electron-rebuild step after npm install. Document in gotchas.
 </reasoning-mode>
 
 <on-activation>
-1. Load sprint status from `sprint/current-sprint.yaml`
-2. Check for active work in `.session/*-session.md`
-3. Assess current infrastructure status
-4. Spot potential problems (preventive thinking)
-5. Load additional docs lazily as needed
+1. Context already loaded by prime
+2. Assess current infrastructure status
+3. Spot potential problems (preventive thinking)
 </on-activation>
 
 <delegation>

package/pennyfarthing-dist/agents/handoff.md

@@ -151,7 +151,7 @@ HANDOFF_RESULT:
 
   next_steps:
     - "Handoff complete. Run handoff-marker.sh as ABSOLUTE LAST ACTION."
-    - "Command: $CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/handoff-marker.sh {next_agent}"
+    - "Command: .pennyfarthing/scripts/core/handoff-marker.sh {next_agent}"
     - "Output marker result verbatim, then EXIT. Nothing after."
 ```
 
@@ -166,7 +166,7 @@ HANDOFF_RESULT:
 
   next_steps:
     - "Handoff complete. Run handoff-marker.sh as ABSOLUTE LAST ACTION."
-    - "Command: $CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/handoff-marker.sh dev"
+    - "Command: .pennyfarthing/scripts/core/handoff-marker.sh dev"
     - "Output marker result verbatim, then EXIT. Nothing after."
 ```
 
@@ -181,7 +181,7 @@ HANDOFF_RESULT:
 
   next_steps:
     - "Handoff complete. Run handoff-marker.sh as ABSOLUTE LAST ACTION."
-    - "Command: $CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/handoff-marker.sh reviewer"
+    - "Command: .pennyfarthing/scripts/core/handoff-marker.sh reviewer"
     - "Output marker result verbatim, then EXIT. Nothing after."
 ```
 
@@ -229,7 +229,7 @@ When you receive `HANDOFF_RESULT`:
 **CRITICAL: The calling agent MUST run this as their ABSOLUTE LAST ACTION:**
 
 ```bash
-$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/handoff-marker.sh {next_agent}
+.pennyfarthing/scripts/core/handoff-marker.sh {next_agent}
 ```
 
 Then output the script's result verbatim and EXIT. Nothing else after.

package/pennyfarthing-dist/agents/orchestrator.md

@@ -83,10 +83,8 @@ ASSESSMENT_SECTION: "Orchestrator Assessment"
 </parameters>
 
 <on-activation>
-1. Load sprint status from `sprint/current-sprint.yaml`
-2. Check for active work in `.session/*-session.md`
-3. Present meta-operation options
-4. Load agent/skill files lazily as needed
+1. Context already loaded by prime
+2. Present meta-operation options
 </on-activation>
 
 <delegation>

package/pennyfarthing-dist/agents/pm.md

@@ -54,12 +54,6 @@ FILE_LIST: "{comma-separated file paths}"
 - `/story-management` - Story creation and sizing patterns
 </skills>
 
-<context>
-Context auto-loaded by `/prime --agent pm`:
-- Shared context, shared behavior
-- Agent sidecar: `.pennyfarthing/sidecars/pm/`
-</context>
-
 <reasoning-mode>
 
 **Default:** Quiet mode - follow ReAct pattern internally, show only key decisions
@@ -83,11 +77,10 @@ REFLECT: Recommend completing Epic 38 batch before starting new epics. P1 bugs f
 </reasoning-mode>
 
 <on-activation>
-1. Load sprint status from `sprint/current-sprint.yaml`
-2. Check for active work in `.session/*-session.md`
-3. Assess current progress (completed vs remaining points)
-4. Identify blockers and priorities
-5. Present strategic options to user
+1. Context already loaded by prime
+2. Assess current progress (completed vs remaining points)
+3. Identify blockers and priorities
+4. Present strategic options to user
 </on-activation>
 
 <delegation>

package/pennyfarthing-dist/agents/reviewer-preflight.md

@@ -28,14 +28,15 @@ model: haiku
 ## 1. Checkout and Diff
 
 ```bash
-cd $CLAUDE_PROJECT_DIR/${REPO} && git fetch origin && git checkout {BRANCH} && git diff develop...HEAD --stat
+# If REPO is a path, cd to it; otherwise check packages/
+cd "${REPO}" 2>/dev/null || cd "packages/${REPO}" && git fetch origin && git checkout {BRANCH} && git diff develop...HEAD --stat
 ```
 
 ## 2. Check Test Cache
 
 ```bash
-source $CLAUDE_PROJECT_DIR/scripts/utils/test-cache.sh
-SESSION_FILE="$CLAUDE_PROJECT_DIR/.session/{STORY_ID}-session.md"
+source scripts/utils/test-cache.sh
+SESSION_FILE=".session/{STORY_ID}-session.md"
 
 if test_cache_valid "$SESSION_FILE"; then
     CACHED_RESULT=$(test_cache_get "$SESSION_FILE" "result")

package/pennyfarthing-dist/agents/reviewer.md

@@ -67,18 +67,12 @@ ASSESSMENT_SECTION: "Reviewer Assessment"
 ```
 </parameters>
 
-<context>
-**Load on activation:**
-- `pennyfarthing-dist/sidecars/reviewer-patterns.md` (if exists)
-- `pennyfarthing-dist/sidecars/reviewer-gotchas.md` (if exists)
-</context>
-
 <phase-check>
 ## On Startup: Check Phase
 
 Read `**Workflow:**` and `**Phase:**` from session. Query:
 ```bash
-OWNER=$($CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/run.sh workflow/phase-owner.sh {workflow} {phase})
+OWNER=$(.pennyfarthing/scripts/core/run.sh workflow/phase-owner.sh {workflow} {phase})
 ```
 
 **If OWNER != "reviewer":** Run `handoff-marker.sh $OWNER`, output result, tell user.
@@ -169,7 +163,7 @@ OWNER=$($CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/run.sh workflow/phase-ow
 3. Await `HANDOFF_RESULT` with `next_agent`
 4. **ABSOLUTE LAST ACTION:**
    ```bash
-   $CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/handoff-marker.sh {next_agent}
+   .pennyfarthing/scripts/core/handoff-marker.sh {next_agent}
    ```
 5. Output result verbatim and EXIT
 

package/pennyfarthing-dist/agents/sm-handoff.md

@@ -77,7 +77,7 @@ HANDOFF_RESULT:
 
   next_steps:
     - "Handoff complete. Run handoff-marker.sh as ABSOLUTE LAST ACTION."
-    - "Command: $CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/handoff-marker.sh {next_agent}"
+    - "Command: .pennyfarthing/scripts/core/handoff-marker.sh {next_agent}"
     - "Output marker result verbatim, then EXIT. Nothing after."
 ```
 
@@ -92,7 +92,7 @@ HANDOFF_RESULT:
 
   next_steps:
     - "Handoff complete. Run handoff-marker.sh as ABSOLUTE LAST ACTION."
-    - "Command: $CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/handoff-marker.sh tea"
+    - "Command: .pennyfarthing/scripts/core/handoff-marker.sh tea"
     - "Output marker result verbatim, then EXIT. Nothing after."
 ```
 
@@ -123,7 +123,7 @@ When SM receives `HANDOFF_RESULT`:
 **CRITICAL: SM MUST run this as their ABSOLUTE LAST ACTION:**
 
 ```bash
-$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/handoff-marker.sh {next_agent}
+.pennyfarthing/scripts/core/handoff-marker.sh {next_agent}
 ```
 
 Then output the script's result verbatim and EXIT. Nothing else after.

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

@@ -174,7 +174,7 @@ Use `/jira claim` command:
 ## Step 5: Create Branch
 
 ```bash
-cd $CLAUDE_PROJECT_DIR && git checkout develop && git pull && \
+git checkout develop && git pull && \
 git checkout -b feat/{STORY_ID}-{SLUG}
 ```
 

package/pennyfarthing-dist/agents/sm.md

@@ -17,12 +17,6 @@ The moment you start reading implementation files or planning how code should wo
 **Your job is done when the next agent has context. Not when the problem is solved.**
 </coordination-discipline>
 
-<critical>
-**WORKFLOW STATUS CHECK IS MANDATORY - FIRST ACTION ON EVERY ACTIVATION**
-
-Before doing ANYTHING else, spawn `workflow-status-check` subagent. No exceptions.
-</critical>
-
 <critical>
 **No code.** Coordinates workflow and stories. Handoff to Dev for implementation.
 
@@ -97,28 +91,10 @@ WORKFLOW: "{WORKFLOW}"
 ```
 </parameters>
 
-<context>
-**Load on activation:**
-- `pennyfarthing-dist/sidecars/sm-patterns.md` (if exists)
-- `pennyfarthing-dist/sidecars/sm-gotchas.md` (if exists)
-</context>
-
 <on-activation>
-## MANDATORY FIRST ACTION
-
-**Spawn workflow-status-check FIRST. Always.**
-
-```yaml
-Task tool:
-  subagent_type: "general-purpose"
-  model: "haiku"
-  prompt: |
-    You are the workflow-status-check subagent. CALLING_AGENT: SM
-    Read .pennyfarthing/agents/workflow-status-check.md for instructions.
-    EXECUTE all steps. Do NOT summarize.
-```
+## On Activation
 
-**THEN route based on returned state:**
+Prime script provides workflow state. Route based on state from activation output:
 
 | State | Action |
 |-------|--------|
@@ -255,7 +231,7 @@ SM sets up the story and hands off to the first agent. Agents hand off to each o
 
 ### Stepped Workflows (BikeLane)
 
-SM does NOT hand off to agents. Instead, use `/workflow start <name>` to begin the stepped flow. The workflow itself guides the user through steps with gates.
+SM does NOT hand off to agents. Instead, use `/workflow start {name}` to begin the stepped flow. The workflow itself guides the user through steps with gates.
 
 | Workflow | Type | How to Start |
 |----------|------|--------------|
@@ -278,7 +254,7 @@ SM does NOT hand off to agents. Instead, use `/workflow start <name>` to begin t
 
 Read `**Workflow:**` and `**Phase:**` from session. Query:
 ```bash
-OWNER=$($CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/run.sh workflow/phase-owner.sh {workflow} {phase})
+OWNER=$(.pennyfarthing/scripts/core/run.sh workflow/phase-owner.sh {workflow} {phase})
 ```
 
 **If OWNER != "sm":** Run `handoff-marker.sh $OWNER`, output result, tell user.
@@ -300,7 +276,7 @@ OWNER=$($CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/run.sh workflow/phase-ow
 3. Await `HANDOFF_RESULT` with `next_agent`
 4. **ABSOLUTE LAST ACTION:**
    ```bash
-   $CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/handoff-marker.sh {next_agent}
+   .pennyfarthing/scripts/core/handoff-marker.sh {next_agent}
    ```
 5. Output result verbatim and EXIT
 

package/pennyfarthing-dist/agents/tea.md

@@ -58,7 +58,7 @@ ASSESSMENT_SECTION: "TEA Assessment"
 
 Read `**Workflow:**` and `**Phase:**` from session. Query:
 ```bash
-OWNER=$($CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/run.sh workflow/phase-owner.sh {workflow} {phase})
+OWNER=$(.pennyfarthing/scripts/core/run.sh workflow/phase-owner.sh {workflow} {phase})
 ```
 
 **If OWNER != "tea":** Run `handoff-marker.sh $OWNER`, output result, tell user.
@@ -144,7 +144,7 @@ Write to session file BEFORE spawning handoff:
 3. Await `HANDOFF_RESULT` with `next_agent`
 4. **ABSOLUTE LAST ACTION:**
    ```bash
-   $CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/core/handoff-marker.sh {next_agent}
+   .pennyfarthing/scripts/core/handoff-marker.sh {next_agent}
    ```
 5. Output result verbatim and EXIT
 </exit-sequence>

package/pennyfarthing-dist/agents/tech-writer.md

@@ -51,13 +51,6 @@ ASSESSMENT_SECTION: "Tech Writer Review"
 - **CANNOT:** Modify source files
 </critical>
 
-<context>
-Context auto-loaded by `/prime --agent tech-writer`:
-- Shared context, shared behavior
-- Agent sidecar: `.pennyfarthing/sidecars/tech-writer/`
-- Also see: `API/docs/`, `UI/docs/`
-</context>
-
 <reasoning-mode>
 
 **Default:** Quiet mode - follow ReAct pattern internally, show only key decisions
@@ -79,11 +72,9 @@ REFLECT: I should structure this as: overview, auth, request format, response fo
 </reasoning-mode>
 
 <on-activation>
-1. Load sprint status from `sprint/current-sprint.yaml`
-2. Check for active work in `.session/*-session.md`
-3. Review feature that needs documentation
-4. Identify audience (developers, users, or both)
-5. Load additional docs lazily as needed
+1. Context already loaded by prime
+2. Review feature that needs documentation
+3. Identify audience (developers, users, or both)
 </on-activation>
 
 <workflow-participation>

package/pennyfarthing-dist/agents/testing-runner.md

@@ -19,8 +19,8 @@ model: haiku
 <critical>
 **Use `/check` command for unfiltered runs:**
 ```bash
-$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/run.sh workflow/check.sh
-$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/run.sh workflow/check.sh --repo api
+.pennyfarthing/scripts/core/run.sh workflow/check.sh
+.pennyfarthing/scripts/core/run.sh workflow/check.sh --repo api
 ```
 
 This runs lint + typecheck + tests. Exit 0 = all passed.
@@ -40,8 +40,8 @@ This runs lint + typecheck + tests. Exit 0 = all passed.
 ## Setup
 
 ```bash
-source $CLAUDE_PROJECT_DIR/scripts/repo-utils.sh
-source $CLAUDE_PROJECT_DIR/scripts/utils/test-setup.sh
+source .pennyfarthing/scripts/repo-utils.sh
+source .pennyfarthing/scripts/utils/test-setup.sh
 
 RUN_ID="${RUN_ID:-$(generate_run_id)}"
 ensure_test_containers
@@ -50,8 +50,8 @@ ensure_test_containers
 ## Filtered Runs
 
 ```bash
-$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/run.sh workflow/check.sh --filter "TestUserLogin"
-$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/run.sh workflow/check.sh --repo api --filter "TestUserLogin"
+.pennyfarthing/scripts/core/run.sh workflow/check.sh --filter "TestUserLogin"
+.pennyfarthing/scripts/core/run.sh workflow/check.sh --repo api --filter "TestUserLogin"
 ```
 
 | Language | Filter Flag |
@@ -73,8 +73,8 @@ fi
 
 Write cache after running:
 ```bash
-source $CLAUDE_PROJECT_DIR/scripts/utils/test-cache.sh
-SESSION_FILE="$CLAUDE_PROJECT_DIR/.session/${STORY_ID}-session.md"
+source .pennyfarthing/scripts/utils/test-cache.sh
+SESSION_FILE=".session/${STORY_ID}-session.md"
 test_cache_write "$SESSION_FILE" "$RESULT" "$PASS" "$FAIL" "$SKIP" "${DURATION}s"
 ```
 

package/pennyfarthing-dist/agents/ux-designer.md

@@ -46,13 +46,6 @@ FILE_LIST: "{comma-separated UI component paths}"
 - **CANNOT:** Modify source files
 </critical>
 
-<context>
-Context auto-loaded by `/prime --agent ux-designer`:
-- Shared context, shared behavior
-- Agent sidecar: `.pennyfarthing/sidecars/ux-designer/`
-- Also see: TailwindCSS, shadcn/ui, `UI/` (React 18)
-</context>
-
 <reasoning-mode>
 
 **Default:** Quiet mode - follow ReAct pattern internally, show only key decisions
@@ -74,11 +67,9 @@ REFLECT: I should design this modal to match existing patterns while adding clea
 </reasoning-mode>
 
 <on-activation>
-1. Load sprint status from `sprint/current-sprint.yaml`
-2. Check for active work in `.session/*-session.md`
-3. Review feature requirements and user needs
-4. Assess design needs (wireframes, flows, components)
-5. Load additional docs lazily as needed
+1. Context already loaded by prime
+2. Review feature requirements and user needs
+3. Assess design needs (wireframes, flows, components)
 </on-activation>
 
 <workflow-participation>

package/pennyfarthing-dist/commands/git-cleanup.md

@@ -5,71 +5,47 @@ workflow: git-cleanup
 
 # Git Cleanup Command
 
-Analyze and organize uncommitted changes across all repos into proper commits and branches based on initiative/feature groupings.
+Organize uncommitted changes into proper commits and branches.
 
-## BikeLane Workflow
+## Quick Start
+
+Run `/git-cleanup` to start the stepped workflow.
 
-This command uses the **git-cleanup** stepped workflow:
+## Workflow Steps
 
 | Step | Name | Purpose |
 |------|------|---------|
-| 1 | Analyze | Gather git status across all repos |
-| 2 | Categorize | Group changes by initiative type |
+| 1 | Analyze | Check stash, gather git status |
+| 2 | Categorize | Group changes by initiative |
 | 3 | Execute | Create branches, commit, merge |
-| 4 | Verify | Confirm clean state, optionally push |
-| 5 | Complete | Summary and next steps |
-
-## Quick Start
-
-Run `/git-cleanup` to start the workflow.
-
-## Git Workflow Rules
+| 4 | Verify | Confirm clean state, push |
+| 5 | Complete | Verify stash empty, summary |
 
-**CRITICAL: Never commit directly to develop.** Branch protection hooks will reject direct commits.
+## Critical Rules
 
-All changes follow this pattern:
-1. Create branch from develop
-2. Commit changes to branch
-3. Merge to develop locally
-4. Push develop (branches stay local)
-
-## Categorization Reference
-
-| Prefix | Type | Branch Pattern |
-|--------|------|----------------|
-| `docs:` | Documentation | `docs/description` |
-| `chore:` | Maintenance | `chore/description` |
-| `chore(sprint):` | Sprint tracking | `chore/sprint-update` |
-| `feat:` | New feature | `feat/story-id-desc` |
-| `fix:` | Bug fix | `fix/issue-desc` |
-| `refactor:` | Code improvement | `refactor/description` |
-| `test:` | Test changes | `test/description` |
+- **NEVER** commit directly to develop (use branches)
+- **NEVER** force push
+- **ALWAYS** check stash before starting (`git stash list`)
+- **ALWAYS** clear stash after completing (with user permission)
+- **ALWAYS** check stash before assuming work is lost
 
-## Manual Quick Reference
+## Stash Safety
 
-For quick cleanup without the full workflow:
+Work is rarely lost - it's usually in stash:
 
 ```bash
-# View what needs cleanup
-./scripts/run.sh git/git-status-all.sh
-
-# Standard cleanup sequence
-git stash push -m "cleanup-wip"
-git checkout develop && git pull
-git checkout -b chore/cleanup-$(date +%Y%m%d)
-git stash pop
-git add <files>
-git commit -m "chore: description"
-git checkout develop
-git merge chore/cleanup-$(date +%Y%m%d)
-git branch -d chore/cleanup-$(date +%Y%m%d)
-git push origin develop
+git stash list              # Check for saved work
+git stash show -p stash@{0} # See contents
+git stash pop               # Restore it
 ```
 
-## Safety Rules
+## Commit Types
 
-- **NEVER** commit directly to develop
-- **NEVER** force push
-- **NEVER** commit secrets (.env, credentials)
-- **ALWAYS** show diff before committing
-- **ALWAYS** use branches
+| Prefix | Use For |
+|--------|---------|
+| `feat:` | New features |
+| `fix:` | Bug fixes |
+| `chore:` | Maintenance |
+| `docs:` | Documentation |
+| `refactor:` | Code improvement |
+| `test:` | Test changes |

package/pennyfarthing-dist/commands/party-mode.md

@@ -10,20 +10,30 @@ You are now in **PARTY MODE** - a free-form creative brainstorming session where
 
 This is the "yes, and..." mode. No idea is too wild. We're exploring possibilities, not committing to implementations. The goal is to generate creative solutions and novel approaches.
 
+## Setup
+
+First, get the current theme's agent personas:
+
+```bash
+pennyfarthing theme show
+```
+
+Use the character names from the current theme for all agent perspectives below.
+
 ## How It Works
 
 When a topic or problem is presented:
 
-1. **Each agent perspective contributes** (pick 3-4 relevant ones):
-   - **Vetinari (PM)**: Strategic implications, business value, political angles
-   - **Leonard (Architect)**: Technical possibilities, creative mechanisms, "what if we..."
-   - **Vimes (Manager)**: Practical concerns, team impact, "how would this actually work"
-   - **Carrot (Dev)**: Implementation ideas, "I could build that by..."
-   - **Igor (TEA)**: Quality angles, "we could verify that with..."
-   - **Sybil (UX)**: User experience, "users would love if..."
-   - **Sacharissa (Tech Writer)**: Communication, "we could explain it as..."
-   - **Lu-Tze (DevOps)**: Operational reality, "in production this would..."
-   - **DEATH (Pennyfarthing Master)**: THE LONG VIEW. WHAT MATTERS IN THE END.
+1. **Each agent perspective contributes** (pick 3-4 relevant ones, using current theme characters):
+   - **PM character**: Strategic implications, business value, political angles
+   - **Architect character**: Technical possibilities, creative mechanisms, "what if we..."
+   - **SM character**: Practical concerns, team impact, "how would this actually work"
+   - **Dev character**: Implementation ideas, "I could build that by..."
+   - **TEA character**: Quality angles, "we could verify that with..."
+   - **UX-Designer character**: User experience, "users would love if..."
+   - **Tech-Writer character**: Communication, "we could explain it as..."
+   - **DevOps character**: Operational reality, "in production this would..."
+   - **Orchestrator character**: THE LONG VIEW. WHAT MATTERS IN THE END.
 
 2. **Build on each other's ideas** - "Yes, and what if we also..."