@pennyfarthing/core 11.2.1 → 11.3.1

package/pennyfarthing-dist/commands/pf-help.md

@@ -52,7 +52,7 @@ SM → TEA → Dev → Reviewer → SM (finish)
 
 Commands are organized by resource. Each group is accessible via both slash commands and CLI.
 
-### Sprint — `/pf-sprint` · `pf sprint`
+### Sprint — `/pf-sprint` · `pf.sh sprint`
 
 | Command | Description |
 |---------|-------------|
@@ -65,7 +65,7 @@ Commands are organized by resource. Each group is accessible via both slash comm
 | `/pf-sprint story [show\|add\|update\|size\|finish]` | Story operations |
 | `/pf-sprint epic [show\|add\|promote\|archive]` | Epic operations |
 
-### Git — `/pf-git` · `pf git`
+### Git — `/pf-git` · `pf.sh git`
 
 | Command | Description |
 |---------|-------------|
@@ -74,21 +74,21 @@ Commands are organized by resource. Each group is accessible via both slash comm
 | `/pf-git branches <id>` | Create feature branches from story |
 | `/pf-git release` | Interactive release workflow |
 
-### Session — `/pf-session` · `pf session`
+### Session — `/pf-session` · `pf.sh session`
 
 | Command | Description |
 |---------|-------------|
 | `/pf-session new` | Start next available story |
 | `/pf-session continue` | Resume from checkpoint |
 
-### Epic — `/pf-epic` · `pf epic`
+### Epic — `/pf-epic` · `pf.sh epic`
 
 | Command | Description |
 |---------|-------------|
 | `/pf-epic start <id>` | Start epic for development |
 | `/pf-epic close <id>` | Close completed epic |
 
-### Jira — `/pf-jira` · `pf jira`
+### Jira — `/pf-jira` · `pf.sh jira`
 
 | Command | Description |
 |---------|-------------|
@@ -98,7 +98,7 @@ Commands are organized by resource. Each group is accessible via both slash comm
 | `/pf-jira sync-epic` | Sync epic to Jira |
 | `/pf-jira reconcile` | Report mismatches |
 
-### Theme — `/pf-theme` · `pf theme`
+### Theme — `/pf-theme` · `pf.sh theme`
 
 | Command | Description |
 |---------|-------------|
@@ -108,7 +108,7 @@ Commands are organized by resource. Each group is accessible via both slash comm
 | `/pf-theme create <name>` | Create custom theme |
 | `/pf-theme maker` | Interactive theme wizard |
 
-### Workflow — `/pf-workflow` · `pf workflow`
+### Workflow — `/pf-workflow` · `pf.sh workflow`
 
 | Command | Description |
 |---------|-------------|
@@ -221,11 +221,11 @@ Based on your current state, here's what you might need:
 
 For detailed help on any command group:
 ```bash
-pf help           # Overview of all groups
-pf help sprint    # Sprint commands
-pf help git       # Git commands
-pf help session   # Session commands
-pf help epic      # Epic commands
+pf.sh help           # Overview of all groups
+pf.sh help sprint    # Sprint commands
+pf.sh help git       # Git commands
+pf.sh help session   # Session commands
+pf.sh help epic      # Epic commands
 ```
 
 ## Documentation

package/pennyfarthing-dist/commands/pf-orchestrator.md

@@ -5,7 +5,7 @@ description: Orchestrator - Coordinator of all agents and meta operations
 <agent-activation>
 **FIRST:** Use Bash tool to run:
 ```bash
-pf agent start "orchestrator"
+source .pennyfarthing/scripts/lib/env.sh && source "$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/lib/run-pf.sh" && run_pf agent start "orchestrator"
 ```
 This loads your persona and agent context. Adopt the character shown in the output.
 </agent-activation>

package/pennyfarthing-dist/commands/pf-pm.md

@@ -5,7 +5,7 @@ description: Product Manager - Strategic planning and prioritization
 <agent-activation>
 **FIRST:** Use Bash tool to run:
 ```bash
-pf agent start "pm"
+source .pennyfarthing/scripts/lib/env.sh && source "$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/lib/run-pf.sh" && run_pf agent start "pm"
 ```
 This loads your persona and agent context. Adopt the character shown in the output.
 </agent-activation>

package/pennyfarthing-dist/commands/pf-prime.md

@@ -4,7 +4,7 @@ description: Load essential project context at agent activation
 
 <purpose>
 Quickly load essential context files to reduce agent cold-start overhead.
-Automatically invoked on agent activation via `pf agent start`.
+Automatically invoked on agent activation via `pf.sh agent start`.
 </purpose>
 
 <when-to-use>
@@ -21,19 +21,19 @@ Use the `pf` CLI:
 
 ```bash
 # Load all essential context (default)
-pf agent start "sm"
+pf.sh agent start "sm"
 
 # Minimal mode - fastest startup
-pf agent start "sm" --minimal
+pf.sh agent start "sm" --minimal
 
 # Full mode - include domain docs
-pf agent start "sm" --full
+pf.sh agent start "sm" --full
 
 # Skip persona loading
-pf agent start "sm" --no-persona
+pf.sh agent start "sm" --no-persona
 
 # JSON output (for Cyclist integration)
-pf agent start "sm" --json
+pf.sh agent start "sm" --json
 ```
 
 ## Options
@@ -111,7 +111,7 @@ With `--quiet`, section headers are suppressed.
 The `/prime` command is automatically invoked when agents activate:
 
 1. User invokes `/sm`, `/tea`, `/dev`, or `/reviewer`
-2. `pf agent start <name>` runs
+2. `pf.sh agent start <name>` runs
 3. Context is loaded: workflow state, agent definition, persona, behavior guide, sprint context, session, sidecars
 4. Agent starts with full context AND their learned patterns loaded
 
@@ -129,7 +129,7 @@ If context becomes stale mid-session, run `/prime` manually:
 </integration>
 
 <reference>
-- **CLI:** `pf agent start <name>` or `python3 -m pennyfarthing_scripts.cli agent start <name>`
+- **CLI:** `pf.sh agent start <name>` or `python3 -m pennyfarthing_scripts.cli agent start <name>`
 - **Loads:** Workflow state, agent definition, persona, behavior guide, sprint context, session, sidecars
 - **Sidecar location:** `.pennyfarthing/sidecars/{agent}/*.md`
 - **Behavior guide:** `.pennyfarthing/guides/agent-behavior.md` (all agents)

package/pennyfarthing-dist/commands/pf-reviewer.md

@@ -5,7 +5,7 @@ description: Code Reviewer - Critical code review and quality enforcement
 <agent-activation>
 **FIRST:** Use Bash tool to run:
 ```bash
-pf agent start "reviewer"
+source .pennyfarthing/scripts/lib/env.sh && source "$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/lib/run-pf.sh" && run_pf agent start "reviewer"
 ```
 This loads your persona and agent context. Adopt the character shown in the output.
 </agent-activation>

package/pennyfarthing-dist/commands/pf-session.md

@@ -16,19 +16,19 @@ Manage work session lifecycle. Start new stories from the backlog or resume from
 Start the next available story from the sprint backlog.
 
 ```bash
-pf session new
+pf.sh session new
 ```
 
-Equivalent to `pf sprint work next`. Auto-selects the highest priority story.
+Equivalent to `pf.sh sprint work next`. Auto-selects the highest priority story.
 
 ### `/pf-session continue [--list] [--story-id ID]`
 
 Resume work from a saved checkpoint after context circuit breaker.
 
 ```bash
-pf session continue            # Interactive checkpoint selection
-pf session continue --list     # Show available checkpoints
-pf session continue --story-id MSSCI-12345  # Resume specific story
+pf.sh session continue            # Interactive checkpoint selection
+pf.sh session continue --list     # Show available checkpoints
+pf.sh session continue --story-id MSSCI-12345  # Resume specific story
 ```
 
 ## Quick Reference
@@ -41,8 +41,8 @@ pf session continue --story-id MSSCI-12345  # Resume specific story
 ## CLI Equivalent
 
 ```bash
-pf session new
-pf session continue [--list] [--story-id ID]
+pf.sh session new
+pf.sh session continue [--list] [--story-id ID]
 ```
 
 ## Related

package/pennyfarthing-dist/commands/pf-sm.md

@@ -5,7 +5,7 @@ description: Scrum Master - Story coordination and sprint management
 <agent-activation>
 **FIRST:** Use Bash tool to run:
 ```bash
-pf agent start "sm"
+source .pennyfarthing/scripts/lib/env.sh && source "$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/lib/run-pf.sh" && run_pf agent start "sm"
 ```
 This loads your persona and agent context. Adopt the character shown in the output.
 </agent-activation>

package/pennyfarthing-dist/commands/pf-sprint.md

@@ -20,7 +20,7 @@ Never manually edit `sprint/current-sprint.yaml`. Always use the provided script
 Show current sprint status with story counts and points.
 
 ```bash
-pf sprint status [filter]
+pf.sh sprint status [filter]
 ```
 
 | Filter | Description |
@@ -35,7 +35,7 @@ pf sprint status [filter]
 Show available stories ready for work, grouped by epic.
 
 ```bash
-pf sprint backlog
+pf.sh sprint backlog
 ```
 
 ### `/pf-sprint work [story-id|epic-id|next]`
@@ -59,7 +59,7 @@ if [[ "$OPEN_PRS" -gt 0 ]]; then
 fi
 
 # Check if story is available
-pf sprint check <story-id>
+pf.sh sprint check <story-id>
 
 # Then load SM to begin work
 ```
@@ -78,7 +78,7 @@ When starting work, this command:
 Archive a completed story.
 
 ```bash
-pf sprint archive <story-id> [pr-number] [--apply]
+pf.sh sprint archive <story-id> [pr-number] [--apply]
 ```
 
 | Option | Description |
@@ -90,7 +90,7 @@ pf sprint archive <story-id> [pr-number] [--apply]
 Initialize a new sprint.
 
 ```bash
-pf sprint new 2605 277 2026-02-03 2026-02-16 "Sprint goal"
+pf.sh sprint new 2605 277 2026-02-03 2026-02-16 "Sprint goal"
 ```
 
 ### `/pf-sprint future [--epic EPIC_ID]`
@@ -98,7 +98,7 @@ pf sprint new 2605 277 2026-02-03 2026-02-16 "Sprint goal"
 Show future work available for promotion.
 
 ```bash
-pf sprint future [--epic epic-XX]
+pf.sh sprint future [--epic epic-XX]
 ```
 
 ### `/pf-sprint promote <epic-id>`
@@ -106,7 +106,7 @@ pf sprint future [--epic epic-XX]
 Move an epic from future.yaml to current sprint.
 
 ```bash
-pf sprint epic promote epic-XX
+pf.sh sprint epic promote epic-XX
 ```
 
 ## Quick Reference

package/pennyfarthing-dist/commands/pf-tea.md

@@ -5,7 +5,7 @@ description: Test Engineer/Architect - Test strategy and TDD
 <agent-activation>
 **FIRST:** Use Bash tool to run:
 ```bash
-pf agent start "tea"
+source .pennyfarthing/scripts/lib/env.sh && source "$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/lib/run-pf.sh" && run_pf agent start "tea"
 ```
 This loads your persona and agent context. Adopt the character shown in the output.
 </agent-activation>

package/pennyfarthing-dist/commands/pf-tech-writer.md

@@ -5,7 +5,7 @@ description: Technical Writer - Documentation creation and maintenance
 <agent-activation>
 **FIRST:** Use Bash tool to run:
 ```bash
-pf agent start "tech-writer"
+source .pennyfarthing/scripts/lib/env.sh && source "$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/lib/run-pf.sh" && run_pf agent start "tech-writer"
 ```
 This loads your persona and agent context. Adopt the character shown in the output.
 </agent-activation>

package/pennyfarthing-dist/commands/pf-theme.md

@@ -16,10 +16,10 @@ Manage persona themes: list available themes, view details, switch themes, creat
 Show current theme or specific theme details.
 
 ```bash
-pf theme show [name]
+pf.sh theme show [name]
 
 # Show extended details (OCEAN scores, quirks, catchphrases)
-pf theme show [name] --full
+pf.sh theme show [name] --full
 ```
 
 ### `/theme list`
@@ -27,7 +27,7 @@ pf theme show [name] --full
 List all available themes with current theme highlighted.
 
 ```bash
-pf theme list
+pf.sh theme list
 ```
 
 Output shows current theme marked with `*` and tier brackets: `[S]` elite, `[A]` excellent, `[B]` strong, `[C]` good, `[D]` below average, `[U]` unbenchmarked.
@@ -37,12 +37,12 @@ Output shows current theme marked with `*` and tier brackets: `[S]` elite, `[A]`
 Set the active persona theme.
 
 ```bash
-pf theme set <name>
+pf.sh theme set <name>
 ```
 
 After setting, refresh the current agent's persona:
 ```bash
-pf agent start "sm"
+pf.sh agent start "sm"
 ```
 
 ### `/theme create <name> [--base <theme>] [--user]`
@@ -51,13 +51,13 @@ Create a new custom theme by copying from a base.
 
 ```bash
 # Create from default base (minimalist)
-pf theme create my-theme
+pf.sh theme create my-theme
 
 # Create from specific base
-pf theme create my-theme --base blade-runner
+pf.sh theme create my-theme --base blade-runner
 
 # Create as user-level theme (available across all projects)
-pf theme create my-theme --user
+pf.sh theme create my-theme --user
 ```
 
 ### `/theme maker`
@@ -90,6 +90,6 @@ Interactive wizard for AI-driven theme creation. Supports three modes:
 
 <reference>
 - **Skill:** `.claude/skills/theme/skill.md`
-- **CLI:** `pf theme [list|show|set|create]`
+- **CLI:** `pf.sh theme [list|show|set|create]`
 - **Config:** `.pennyfarthing/config.local.yaml`
 </reference>

package/pennyfarthing-dist/commands/pf-ux-designer.md

@@ -5,7 +5,7 @@ description: UX Designer - User experience design and UI patterns
 <agent-activation>
 **FIRST:** Use Bash tool to run:
 ```bash
-pf agent start "ux-designer"
+source .pennyfarthing/scripts/lib/env.sh && source "$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/lib/run-pf.sh" && run_pf agent start "ux-designer"
 ```
 This loads your persona and agent context. Adopt the character shown in the output.
 </agent-activation>

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

@@ -7,7 +7,7 @@ description: Resume work or start new - smart entry point that picks up where yo
 <agent-activation>
 **FIRST:** Use Bash tool to run:
 ```bash
-pf agent start "sm"
+source .pennyfarthing/scripts/lib/env.sh && source "$CLAUDE_PROJECT_DIR/.pennyfarthing/scripts/lib/run-pf.sh" && run_pf agent start "sm"
 ```
 This loads your persona and agent context. Adopt the character shown in the output.
 </agent-activation>

package/pennyfarthing-dist/gates/{confidence-sm.md → confidence.md}

@@ -1,19 +1,18 @@
-<gate name="confidence-sm" model="haiku">
+<gate name="confidence" model="haiku">
 
 <purpose>
-Check whether the user's instruction to the SM agent is ambiguous or unclear.
-The SM agent handles story management, sprint coordination, and workflow routing.
+Check whether the user's instruction to the current agent is ambiguous or unclear.
 Vague commands like "continue", "next", "start", or "do it" without a clear target
-(story ID, agent name, or specific action) risk the SM taking the wrong action.
-This gate evaluates confidence that the instruction has a single unambiguous interpretation.
+risk the agent taking the wrong action. This gate evaluates confidence that the
+instruction has a single unambiguous interpretation.
 </purpose>
 
 <pass>
-The instruction is clear and unambiguous. The SM agent can proceed confidently.
+The instruction is clear and unambiguous. The agent can proceed confidently.
 
 Evaluate the instruction against these criteria:
-1. **Target identified:** A story ID, agent name, or specific action is stated or obvious from context
-2. **Intent clear:** The desired outcome (start work, finish story, check status, hand off) is unambiguous
+1. **Target identified:** A specific entity (story ID, file, component, action) is stated or obvious from context
+2. **Intent clear:** The desired outcome is unambiguous
 3. **No competing interpretations:** Only one reasonable reading of the instruction exists
 
 If the instruction is confident and clear, return:
@@ -21,28 +20,28 @@ If the instruction is confident and clear, return:
 ```yaml
 GATE_RESULT:
   status: pass
-  gate: confidence-sm
-  message: "Instruction is clear: {summary of what SM will do}"
+  gate: confidence
+  message: "Instruction is clear: {summary of what agent will do}"
   checks:
     - name: target
       status: pass
       detail: "{what the instruction targets}"
     - name: intent
       status: pass
-      detail: "{what action the SM will take}"
+      detail: "{what action the agent will take}"
 ```
 </pass>
 
 <fail>
-The instruction is ambiguous. The SM agent should not guess — ask for clarification instead.
+The instruction is ambiguous. The agent should not guess — ask for clarification instead.
 
 Identify which aspect is unclear and offer specific options the user likely meant:
 
-1. **Missing target:** "continue" / "next" / "start" without specifying a story or action
-   - Did you mean: start a specific story? Continue the current workflow? Check sprint status?
+1. **Missing target:** "continue" / "next" / "start" without specifying what
+   - List the 2-3 most likely targets given current context
 
 2. **Ambiguous scope:** "do the thing" / "handle it" without enough context
-   - Did you mean: finish the current story? Start new work? Run the backlog?
+   - List the 2-3 most likely actions given current workflow state
 
 3. **Multiple interpretations:** The instruction could reasonably mean two or more different actions
    - List each interpretation and ask which one the user intended
@@ -52,7 +51,7 @@ Return with clarifying options so the user can specify their intent:
 ```yaml
 GATE_RESULT:
   status: fail
-  gate: confidence-sm
+  gate: confidence
   message: "Instruction is ambiguous: {what is unclear}"
   checks:
     - name: target
@@ -64,7 +63,7 @@ GATE_RESULT:
   recovery:
     - "Did you mean: {option A}?"
     - "Did you mean: {option B}?"
-    - "Specify a story ID or action to proceed"
+    - "Specify a target or action to proceed"
 ```
 </fail>
 

package/pennyfarthing-dist/gates/dev-exit.md

@@ -0,0 +1,75 @@
+<gate name="dev-exit" model="haiku">
+
+<purpose>
+Composite gate for Dev handoff. Extends tests-pass with a debug code scan.
+Runs after the Dev agent's implementation phase before review.
+</purpose>
+
+<ref gate="gates/tests-pass" />
+
+<check name="no-debug-code">
+No console.log, debugger statements, or .only() in changed files.
+Search changed files (`git diff --name-only develop...HEAD`) for:
+- `console.log` (not in DEV guard)
+- `debugger`
+- `.only(`
+None found = pass.
+</check>
+
+<pass>
+Run all checks from `gates/tests-pass` (test-suite, working-tree, branch-status),
+then run the no-debug-code check.
+
+If ALL pass, return:
+
+```yaml
+GATE_RESULT:
+  status: pass
+  gate: dev-exit
+  message: "All {N} tests passing. Tree clean. No debug code. Branch: {branch}"
+  checks:
+    - name: test-suite
+      status: pass
+      detail: "{passed}/{total} tests passing ({skipped} skipped)"
+    - name: working-tree
+      status: pass
+      detail: "No uncommitted changes"
+    - name: branch-status
+      status: pass
+      detail: "On branch {branch}, HEAD at {short-sha}"
+    - name: no-debug-code
+      status: pass
+      detail: "No debug patterns found in changed files"
+```
+</pass>
+
+<fail>
+If ANY check fails, run all remaining checks (don't short-circuit) and return:
+
+```yaml
+GATE_RESULT:
+  status: fail
+  gate: dev-exit
+  message: "Gate failed: {summary of failures}"
+  checks:
+    - name: test-suite
+      status: pass | fail
+      detail: "{test results or failure list}"
+    - name: working-tree
+      status: pass | fail
+      detail: "{clean or list of uncommitted files}"
+    - name: branch-status
+      status: pass | fail
+      detail: "{branch match or mismatch details}"
+    - name: no-debug-code
+      status: pass | fail
+      detail: "{clean or list of debug code locations}"
+  recovery:
+    - "Fix failing tests in: {file1}, {file2}"
+    - "Commit or stash uncommitted changes"
+    - "Remove debug code: {file:line patterns}"
+    - "Switch to correct branch: git checkout {expected-branch}"
+```
+</fail>
+
+</gate>

package/pennyfarthing-dist/gates/merge-ready.md

@@ -0,0 +1,49 @@
+<gate name="merge-ready" model="haiku">
+
+<purpose>
+Block new work if non-draft pull requests are open. Open non-draft PRs represent
+incomplete review cycles that must be resolved before starting new stories.
+Draft PRs are allowed — they represent in-progress work not yet ready for review.
+Extracted from the sm.md merge-gate.
+</purpose>
+
+<pass>
+Run:
+```bash
+gh pr list --state open --search "draft:false" --json number,title,url
+```
+
+If the result is empty (no non-draft open PRs), return:
+
+```yaml
+GATE_RESULT:
+  status: pass
+  gate: merge-ready
+  message: "No open non-draft PRs. Clear to start new work."
+  checks:
+    - name: no-open-prs
+      status: pass
+      detail: "Zero non-draft PRs found"
+```
+</pass>
+
+<fail>
+If any non-draft PRs exist, list them and block:
+
+```yaml
+GATE_RESULT:
+  status: fail
+  gate: merge-ready
+  message: "Blocked: {N} non-draft PR(s) open"
+  checks:
+    - name: no-open-prs
+      status: fail
+      detail: "Open PRs: {list of PR numbers and titles}"
+  recovery:
+    - "Merge or close open PRs before starting new work"
+    - "Use /reviewer to complete pending reviews"
+    - "Convert to draft if work is not ready: gh pr ready --undo {number}"
+```
+</fail>
+
+</gate>

package/pennyfarthing-dist/gates/release-ready.md

@@ -0,0 +1,95 @@
+<gate name="release-ready" model="haiku">
+
+<purpose>
+Composite gate for pre-deploy verification. Extends tests-pass with build,
+version, and changelog checks. Extracts the pre-deploy checklist from devops.md.
+</purpose>
+
+<ref gate="gates/tests-pass" />
+
+<check name="build-succeeds">
+Build completes without errors.
+Run `cd pennyfarthing && pnpm build`. Exit code 0 = pass.
+</check>
+
+<check name="version-bumped">
+Package version has been incremented.
+Compare current `package.json` version against latest git tag
+(`git describe --tags --abbrev=0`). Current must be strictly greater.
+</check>
+
+<check name="changelog-updated">
+CHANGELOG.md has an entry for the new version.
+Grep `CHANGELOG.md` for the current package.json version string.
+</check>
+
+<pass>
+Run all checks from `gates/tests-pass` (test-suite, working-tree, branch-status),
+then run build-succeeds, version-bumped, and changelog-updated.
+
+If ALL pass, return:
+
+```yaml
+GATE_RESULT:
+  status: pass
+  gate: release-ready
+  message: "Release ready: v{version}. Tests green, build clean, changelog updated."
+  checks:
+    - name: test-suite
+      status: pass
+      detail: "{passed}/{total} tests passing"
+    - name: working-tree
+      status: pass
+      detail: "No uncommitted changes"
+    - name: branch-status
+      status: pass
+      detail: "On branch {branch}"
+    - name: build-succeeds
+      status: pass
+      detail: "Build completed successfully"
+    - name: version-bumped
+      status: pass
+      detail: "v{version} > v{tag}"
+    - name: changelog-updated
+      status: pass
+      detail: "CHANGELOG.md has entry for v{version}"
+```
+</pass>
+
+<fail>
+If ANY check fails, report all results:
+
+```yaml
+GATE_RESULT:
+  status: fail
+  gate: release-ready
+  message: "Not release ready: {summary}"
+  checks:
+    - name: test-suite
+      status: pass | fail
+      detail: "{test results or failure list}"
+    - name: working-tree
+      status: pass | fail
+      detail: "{clean or list of uncommitted files}"
+    - name: branch-status
+      status: pass | fail
+      detail: "{branch info}"
+    - name: build-succeeds
+      status: pass | fail
+      detail: "{build status or error summary}"
+    - name: version-bumped
+      status: pass | fail
+      detail: "{version comparison or same-version warning}"
+    - name: changelog-updated
+      status: pass | fail
+      detail: "{changelog status}"
+  recovery:
+    - "Fix failing tests before release"
+    - "Commit or stash uncommitted changes"
+    - "Resolve build errors"
+    - "Run: npm version patch|minor|major"
+    - "Add changelog entry for v{version}"
+```
+</fail>
+
+</gate>