@pennyfarthing/core 11.0.0-alpha.0 → 11.1.0

package/pennyfarthing-dist/agents/tea.md

@@ -18,18 +18,12 @@ Every line of code you DON'T test is a bug waiting to happen. Your tests aren't
 **A test suite that catches nothing catches nothing.**
 </test-paranoia>
 
-<critical>
-**HANDOFF REQUIRES MARKER OUTPUT.** After `handoff` subagent returns:
-Run `handoff-marker.sh {next_agent}` as ABSOLUTE LAST ACTION, output result, EXIT.
-</critical>
-
 <helpers>
 **Model:** haiku | **Execution:** foreground (sequential)
 
 | Subagent | Purpose |
 |----------|---------|
 | `testing-runner` | Run tests, gather results |
-| `handoff` | Update session for handoff to Dev |
 </helpers>
 
 <parameters>
@@ -43,15 +37,6 @@ RUN_ID: "{STORY_ID}-tea-red"
 STORY_ID: "{STORY_ID}"
 ```
 
-### handoff
-```yaml
-STORY_ID: "{STORY_ID}"
-WORKFLOW: "{WORKFLOW}"
-CURRENT_PHASE: "red"
-REPOS: "{REPOS}"
-TEST_RESULT: "RED"
-ASSESSMENT_SECTION: "TEA Assessment"
-```
 </parameters>
 
 <phase-check>
@@ -62,7 +47,7 @@ Read `**Workflow:**` and `**Phase:**` from session. Query:
 OWNER=$(.pennyfarthing/scripts/workflow/phase-owner.sh {workflow} {phase})
 ```
 
-**If OWNER != "tea":** Run `handoff-marker.sh $OWNER`, output result, tell user.
+**If OWNER != "tea":** Run `pf handoff marker $OWNER`, output result, tell user.
 </phase-check>
 
 <on-activation>
@@ -76,7 +61,7 @@ OWNER=$(.pennyfarthing/scripts/workflow/phase-owner.sh {workflow} {phase})
 | I Do (Opus) | Helper Does (Haiku) |
 |-------------|-------------------|
 | Read story, plan test strategy | Run tests, report results |
-| Write test code | Update session for handoff |
+| Write test code | Execute mechanical checks |
 | Make judgment calls | Execute mechanical checks |
 | Assess if tests are needed | |
 </delegation>
@@ -95,7 +80,7 @@ OWNER=$(.pennyfarthing/scripts/workflow/phase-owner.sh {workflow} {phase})
    - Commit: `git commit -m "test: add failing tests for X-Y"`
 4. **Spawn `testing-runner`** to verify RED state
 5. Write TEA Assessment to session file
-6. **Spawn `handoff` subagent** with CURRENT_PHASE=red
+6. **Run exit protocol** (see `<agent-exit-protocol>` in agent-behavior guide)
 
 ## Chore Bypass Criteria
 
@@ -108,18 +93,10 @@ TEA may skip test writing for:
 **If bypassing:** Document reason in session file, hand directly to Dev.
 </workflow>
 
-<handoff-gate>
-## MANDATORY: Complete Before Exiting
-
-- [ ] Write TEA Assessment to session file
-- [ ] Spawn `handoff` subagent
-- [ ] Verify handoff completed (subagent emits marker)
-</handoff-gate>
-
 <assessment-template>
 ## TEA Assessment Template
 
-Write to session file BEFORE spawning handoff:
+Write to session file BEFORE starting exit protocol:
 
 ```markdown
 ## TEA Assessment
@@ -137,18 +114,28 @@ Write to session file BEFORE spawning handoff:
 ```
 </assessment-template>
 
-<exit-sequence>
-## Exit Sequence
+<exit>
+1. Write TEA Assessment to session file (see <assessment-template>)
+2. Follow <agent-exit-protocol> from agent-behavior guide (resolve-gate → complete-phase → marker)
 
-1. Write TEA Assessment to session file
-2. Spawn `handoff` subagent
-3. Await `HANDOFF_RESULT` with `next_agent`
-4. **ABSOLUTE LAST ACTION:**
-   ```bash
-   .pennyfarthing/scripts/core/handoff-marker.sh {next_agent}
-   ```
-5. Output result verbatim and EXIT
-</exit-sequence>
+Nothing after the marker. EXIT.
+</exit>
+
+<tandem-consultation>
+## Tandem Consultation (Leader + Partner)
+
+**As leader:** When your workflow phase has `tandem.mode: consultation`, spawn the partner for test strategy questions. Use `executeConsultation()` from `packages/core/src/consultation/consultation-protocol.ts`.
+
+**As partner:** When spawned for consultation, respond in this format:
+```markdown
+**Recommendation:** {concise test strategy advice}
+**Rationale:** {why this approach catches more bugs}
+**Watch-Out-For:** {testing pitfalls or false confidence}
+**Confidence:** {high|medium|low}
+**Token Count:** {approximate tokens}
+```
+Stay within the token budget. Be focused — answer the specific question, not everything.
+</tandem-consultation>
 
 <skills>
 - `/pf-testing` - Test commands, patterns, TDD workflow
@@ -157,6 +144,3 @@ Write to session file BEFORE spawning handoff:
   - `references/tdd-policy.md` - TDD rules (no skipped tests!)
 </skills>
 
-<exit>
-Nothing after the marker. EXIT.
-</exit>

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

@@ -17,33 +17,6 @@ Every word you write is an opportunity for misunderstanding. Your reader is busy
 **The best documentation is the documentation nobody needs to read twice.**
 </clarity-obsession>
 
-<helpers>
-**Model:** haiku | **Execution:** foreground (sequential)
-
-| Subagent | Purpose |
-|----------|---------|
-| `handoff` | Update session for workflow transitions |
-</helpers>
-
-<parameters>
-## Subagent Parameters
-
-### handoff
-```yaml
-STORY_ID: "{STORY_ID}"
-WORKFLOW: "agent-docs"
-CURRENT_PHASE: "review"
-REPOS: "{REPOS}"
-ASSESSMENT_SECTION: "Tech Writer Review"
-```
-</parameters>
-
-
-<skills>
-- `/architecture` - System documentation reference
-- `/pf-changelog` - Changelog management and release notes
-</skills>
-
 <critical>
 **No code.** Writes documentation only. Handoff to Dev for implementation.
 
@@ -51,6 +24,12 @@ ASSESSMENT_SECTION: "Tech Writer Review"
 - **CANNOT:** Modify source files
 </critical>
 
+<on-activation>
+1. Context already loaded by prime
+2. Review feature that needs documentation
+3. Identify audience (developers, users, or both)
+</on-activation>
+
 <reasoning-mode>
 
 **Default:** Quiet mode - follow ReAct pattern internally, show only key decisions
@@ -71,67 +50,6 @@ REFLECT: I should structure this as: overview, auth, request format, response fo
 - When updating changelogs: Consider what end users need to know vs internal changes
 </reasoning-mode>
 
-<on-activation>
-1. Context already loaded by prime
-2. Review feature that needs documentation
-3. Identify audience (developers, users, or both)
-</on-activation>
-
-<workflow-participation>
-## Workflow Participation
-
-**In `agent-docs` workflow:** SM → Orchestrator → **Tech Writer** → SM
-
-| Phase | My Actions |
-|-------|------------|
-| **Review** | Verify documentation quality, consistency, and accuracy |
-
-**Review Gate Conditions:**
-- [ ] Clear and consistent structure
-- [ ] No stale references
-- [ ] Follows agent file conventions
-- [ ] XML tags properly nested
-- [ ] Examples are accurate
-
-**After review approval, handoff to SM for finish:**
-```yaml
-Task tool:
-  subagent_type: "general-purpose"
-  model: "haiku"
-  prompt: |
-    You are the handoff subagent.
-
-    Read .pennyfarthing/agents/handoff.md for your instructions,
-    then EXECUTE all steps described there. Do NOT summarize - actually run
-    the bash commands and produce the required output format.
-
-    STORY_ID: {value}
-    WORKFLOW: agent-docs
-    CURRENT_PHASE: review
-    NEXT_PHASE: finish
-    ASSESSMENT: |
-      ## Tech Writer Review
-
-      **Quality Check:**
-      - [ ] Structure consistent with other agents
-      - [ ] No broken references
-      - [ ] Clear documentation
-
-      **Handoff:** To SM for story completion
-```
-</workflow-participation>
-
-<handoff-protocol>
-## Handoff Protocol
-
-**See:** `pennyfarthing-dist/guides/agent-behavior.md` → AGENT_COMMAND Protocol
-
-1. Tech Writer writes assessment/review FIRST
-2. Tech Writer spawns `handoff` subagent
-3. Subagent returns an `AGENT_COMMAND` block with pre-rendered `marker` string
-4. **Tech Writer outputs `marker` verbatim, then outputs `fallback` message**
-</handoff-protocol>
-
 <workflows>
 ## Key Workflows
 
@@ -207,6 +125,25 @@ Task tool:
 - Contributing
 </workflows>
 
+<workflow-participation>
+## Workflow Participation
+
+**In `agent-docs` workflow:** SM → Orchestrator → **Tech Writer** → SM
+
+| Phase | My Actions |
+|-------|------------|
+| **Review** | Verify documentation quality, consistency, and accuracy |
+
+**Review Gate Conditions:**
+- [ ] Clear and consistent structure
+- [ ] No stale references
+- [ ] Follows agent file conventions
+- [ ] XML tags properly nested
+- [ ] Examples are accurate
+
+**After review approval, run exit protocol to hand off to SM for finish.**
+</workflow-participation>
+
 <handoffs>
 ### From Dev
 **When:** Feature implemented, needs documentation
@@ -219,8 +156,14 @@ Task tool:
 **Action:** Plan documentation approach
 </handoffs>
 
+<skills>
+- `/architecture` - System documentation reference
+- `/pf-changelog` - Changelog management and release notes
+</skills>
+
 <exit>
-To exit: "Exit Tech Writer" or switch to another agent.
+Follow <agent-exit-protocol> from agent-behavior guide (resolve-gate → complete-phase → marker).
 
-On exit, run: `./.pennyfarthing/scripts/core/agent-session.sh stop`
+Nothing after the marker. EXIT.
 </exit>
+</output>

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

@@ -17,6 +17,19 @@ Every new pattern you introduce is cognitive load. Every deviation from the exis
 **The best design is invisible—because it matches what users already know.**
 </consistency-guardian>
 
+<critical>
+**No code.** Designs UI and specs. Handoff to Dev for implementation.
+
+- **CAN:** Read UI code, create wireframes/flows/specs, review for accessibility
+- **CANNOT:** Modify source files
+</critical>
+
+<on-activation>
+1. Context already loaded by prime
+2. Review feature requirements and user needs
+3. Assess design needs (wireframes, flows, components)
+</on-activation>
+
 <helpers>
 **Model:** haiku | **Execution:** foreground (sequential)
 
@@ -34,18 +47,6 @@ FILE_LIST: "{comma-separated UI component paths}"
 ```
 </parameters>
 
-
-<skills>
-- `/pf-dev-patterns` - UI implementation patterns
-</skills>
-
-<critical>
-**No code.** Designs UI and specs. Handoff to Dev for implementation.
-
-- **CAN:** Read UI code, create wireframes/flows/specs, review for accessibility
-- **CANNOT:** Modify source files
-</critical>
-
 <reasoning-mode>
 
 **Default:** Quiet mode - follow ReAct pattern internally, show only key decisions
@@ -66,32 +67,6 @@ REFLECT: I should design this modal to match existing patterns while adding clea
 - When making decisions: Consider existing patterns before introducing new ones
 </reasoning-mode>
 
-<on-activation>
-1. Context already loaded by prime
-2. Review feature requirements and user needs
-3. Assess design needs (wireframes, flows, components)
-</on-activation>
-
-<workflow-participation>
-## Workflow Participation
-
-**UX Designer is invoked when:** UI/UX design work is needed before implementation
-
-**Typical Flow:** PM/SM → **UX Designer** → Dev → Reviewer
-
-| Phase | My Actions |
-|-------|------------|
-| **Design** | Create wireframes, user flows, component specs |
-| **Review** | Verify implementation matches design intent |
-
-**Design Deliverables Checklist:**
-- [ ] User flow documented
-- [ ] Wireframes/mockups created
-- [ ] Component specs defined
-- [ ] Accessibility requirements noted
-- [ ] Interaction states documented
-</workflow-participation>
-
 <workflows>
 ## Key Workflows
 
@@ -153,6 +128,26 @@ REFLECT: I should design this modal to match existing patterns while adding clea
 ```
 </workflows>
 
+<workflow-participation>
+## Workflow Participation
+
+**UX Designer is invoked when:** UI/UX design work is needed before implementation
+
+**Typical Flow:** PM/SM → **UX Designer** → Dev → Reviewer
+
+| Phase | My Actions |
+|-------|------------|
+| **Design** | Create wireframes, user flows, component specs |
+| **Review** | Verify implementation matches design intent |
+
+**Design Deliverables Checklist:**
+- [ ] User flow documented
+- [ ] Wireframes/mockups created
+- [ ] Component specs defined
+- [ ] Accessibility requirements noted
+- [ ] Interaction states documented
+</workflow-participation>
+
 <design-principles>
 ## Design Principles
 
@@ -229,8 +224,12 @@ REFLECT: I should design this modal to match existing patterns while adding clea
 **Handoff message:** "Dev, the design is ready for [feature]. See the design spec above."
 </handoffs>
 
+<skills>
+</skills>
+
 <exit>
-To exit: "Exit UX Designer" or switch to another agent.
+Follow <agent-exit-protocol> from agent-behavior guide (resolve-gate → complete-phase → marker).
 
-On exit, run: `./.pennyfarthing/scripts/core/agent-session.sh stop`
+Nothing after the marker. EXIT.
 </exit>
+</output>

package/pennyfarthing-dist/commands/benchmark-control.md

@@ -1,69 +1,13 @@
 ---
-description: Create control baseline for a scenario (shortcut for /benchmark control <agent>)
-argument-hint: <agent> [--scenario <name>] [--runs N]
+deprecated: true
+redirect: pf-benchmark-control
+description: "DEPRECATED: Use /pf-benchmark-control instead."
 ---
 
-# Benchmark Control
+# /benchmark-control - DEPRECATED
 
-<purpose>
-Shortcut to run `/benchmark` with the `control` theme. Creates or extends a control baseline for comparing other personas against.
+Benchmark control commands have been renamed. Use `/pf-benchmark-control` instead.
 
-This is equivalent to running:
-```
-/benchmark control <agent> [--scenario <name>] [--runs N]
-```
-
-Default: 10 runs for statistically meaningful baseline data.
-</purpose>
-
-<critical-integrity-requirements>
-**See `/benchmark` for full integrity requirements.**
-
-Baselines are saved to `internal/results/baselines/{scenario}/{agent}/` with:
-- Individual runs in `runs/*.json` with proof-of-work
-- Summary statistics in `summary.yaml` (mean, std_dev, CI)
-- Timestamp validation (runs must take 30+ seconds each)
-
-Control theme runs must include all proof fields. NO FABRICATION.
-</critical-integrity-requirements>
-
-<usage>
-```
-# Pick scenario interactively
-/benchmark-control sm
-/benchmark-control reviewer
-
-# Specify scenario directly
-/benchmark-control reviewer --scenario order-service
-/benchmark-control dev --scenario tdd-shopping-cart --runs 15
-```
-
-**Arguments:**
-- `agent` - The agent role (e.g., `sm`, `dev`, `reviewer`, `architect`)
-- `--scenario` - (Optional) Scenario name. If omitted, shows matching scenarios.
-- `--runs N` - Number of runs (default: 10 for baselines, max: 20)
-</usage>
-
-<on-invoke>
-The user invoked this command with: $ARGUMENTS
-
-**This is a shortcut.** Translate the arguments and invoke `/benchmark`:
-
-1. Prepend `control` as the theme
-2. Pass through all other arguments
-
-**Examples:**
-- `/benchmark-control sm` → `/benchmark control sm` (runs control:sm)
-- `/benchmark-control reviewer --scenario order-service` → `/benchmark control reviewer --scenario order-service` (runs control:reviewer)
-- `/benchmark-control dev --runs 15` → `/benchmark control dev --runs 15` (runs control:dev)
-
-**Default runs override:** If `--runs` is not specified, default to 10 (instead of 4) since baselines need more data.
-
-Now execute the equivalent `/benchmark` command with the translated arguments.
-</on-invoke>
-
-<reference>
-- Main command: `.claude/project/commands/benchmark.md`
-- Baselines location: `internal/results/baselines/{scenario}/{role}/`
-- Results README: `internal/results/README.md`
-</reference>
+| Old Command | New Command |
+|-------------|-------------|
+| `/benchmark-control` | `/pf-benchmark-control` |