opencodekit 0.12.7 → 0.13.1

package/dist/template/.opencode/command/start.md

@@ -0,0 +1,227 @@
+---
+description: Start working on a bead - claim it and prepare context
+argument-hint: "<bead-id> [--worktree] [--research]"
+agent: build
+---
+
+# Start: $ARGUMENTS
+
+You're claiming a task and preparing to work on it. This is the entry point before implementation.
+
+## Parse Arguments
+
+| Argument     | Default  | Description                                    |
+| ------------ | -------- | ---------------------------------------------- |
+| `<bead-id>`  | required | The bead to start working on                   |
+| `--worktree` | false    | Create isolated git worktree for this work     |
+| `--research` | false    | Run parallel subagent research before starting |
+
+## Load Skills
+
+```typescript
+skill({ name: "beads" });
+```
+
+## Ensure Git Hooks Installed
+
+First-time setup per repo (prevents stale JSONL issues):
+
+```bash
+bd hooks install 2>/dev/null || echo "Hooks already installed"
+```
+
+## Current State
+
+### Git Status
+
+!`git status --porcelain`
+!`git branch --show-current`
+
+### Active Tasks
+
+!`bd list --status=in_progress`
+
+If you have uncommitted changes, ask the user:
+
+1. Stash them (`git stash`)
+2. Commit them first
+3. Continue anyway (risky)
+
+If you already have tasks in_progress, warn the user before claiming another.
+
+## Task Details
+
+!`bd show $ARGUMENTS`
+
+Identify the task type from the bead:
+
+| Type      | Hierarchy Level | Typical Scope                     |
+| --------- | --------------- | --------------------------------- |
+| `epic`    | Parent          | Multi-session, has subtasks       |
+| `task`    | Middle          | Single session, may have subtasks |
+| `subtask` | Leaf            | Single focused unit of work       |
+
+Check for parent/child relationships:
+
+```bash
+bd dep tree $ARGUMENTS 2>/dev/null || echo "No dependencies"
+```
+
+## Claim The Task
+
+```bash
+bd update $ARGUMENTS --status in_progress
+```
+
+## Workspace Setup
+
+### Option A: Feature Branch (default)
+
+If not already on a feature branch:
+
+```bash
+git checkout -b $ARGUMENTS
+```
+
+### Option B: Git Worktree (if --worktree flag)
+
+For isolated work that won't conflict with main workspace:
+
+```typescript
+skill({ name: "using-git-worktrees" });
+```
+
+**When to use worktrees:**
+
+- Epic-level work spanning multiple sessions
+- Parallel work on different features
+- Need to keep main workspace clean
+- Long-running features with frequent context switches
+
+**Worktree setup:**
+
+```bash
+# Verify .gitignore has worktree directory
+grep -q "^\.worktrees/$" .gitignore || echo ".worktrees/" >> .gitignore
+
+# Create worktree
+git worktree add .worktrees/$ARGUMENTS -b $ARGUMENTS
+
+# Navigate to worktree
+cd .worktrees/$ARGUMENTS
+
+# Install dependencies (auto-detect project type)
+[ -f package.json ] && npm install
+[ -f Cargo.toml ] && cargo build
+[ -f requirements.txt ] && pip install -r requirements.txt
+[ -f go.mod ] && go mod download
+```
+
+**Beads in worktrees:** The `.beads/` database is shared with main repo automatically. No special configuration needed unless using `BEADS_DIR` for external storage.
+
+## Parallel Research (if --research flag or epic-level work)
+
+For complex tasks, gather context before diving in:
+
+```typescript
+// Fire subagents in parallel - don't wait for results
+Task({
+  subagent_type: "explore",
+  prompt: `Research codebase patterns for $ARGUMENTS:
+    - Find similar implementations
+    - Identify affected files
+    - Note testing patterns used
+    Return: File list, patterns found, testing approach`,
+  description: "Explore codebase for task",
+});
+
+Task({
+  subagent_type: "scout",
+  prompt: `Research external docs for $ARGUMENTS:
+    - API documentation for libraries involved
+    - Best practices for the approach
+    - Common pitfalls to avoid
+    Return: Key findings, code examples, warnings`,
+  description: "Scout external resources",
+});
+```
+
+**Subagent delegation rules:**
+
+- Subagents are **read-only** - they don't modify beads state
+- Results return to you (build agent) for integration
+- Use for research, not for implementation
+
+## Existing Artifacts
+
+!`ls .beads/artifacts/$ARGUMENTS/ 2>/dev/null || echo "No artifacts yet"`
+
+Look for:
+
+- `spec.md` - Requirements and constraints
+- `research.md` - Previous research
+- `plan.md` - Implementation plan
+- `handoffs/` - Previous session handoffs
+
+## Check Previous Sessions
+
+```typescript
+search_session({ query: "$ARGUMENTS" });
+list_sessions({ limit: 3 });
+```
+
+Load context from previous work on this bead.
+
+## Determine Next Step
+
+Based on task type and what exists:
+
+### For Epics (parent tasks)
+
+| State              | Next Command                      |
+| ------------------ | --------------------------------- |
+| No subtasks        | `/plan $ARGUMENTS --create-beads` |
+| Has ready subtasks | `/start <first-subtask-id>`       |
+| All subtasks done  | `/finish $ARGUMENTS`              |
+
+### For Tasks/Subtasks (leaf work)
+
+| Artifacts Found       | Next Command            |
+| --------------------- | ----------------------- |
+| Nothing               | `/research $ARGUMENTS`  |
+| Only spec.md          | `/plan $ARGUMENTS`      |
+| spec.md + research.md | `/plan $ARGUMENTS`      |
+| plan.md exists        | `/implement $ARGUMENTS` |
+
+## Output
+
+```
+Started: $ARGUMENTS
+━━━━━━━━━━━━━━━━━━━
+
+Type: [epic/task/subtask]
+Branch: $ARGUMENTS
+Workspace: [main | worktree: .worktrees/$ARGUMENTS]
+Status: in_progress
+
+Hierarchy:
+├── Parent: [parent-id or "none"]
+└── Children: [count or "none"]
+
+Artifacts:
+• spec.md: [exists/missing]
+• research.md: [exists/missing]
+• plan.md: [exists/missing]
+
+Research: [launched/skipped]
+
+Next: [recommended command based on state]
+```
+
+## Quick Start
+
+If `--quick` flag is passed and plan.md exists, skip directly to:
+
+```
+/implement $ARGUMENTS
+```

package/dist/template/.opencode/command/triage.md

@@ -1,6 +1,6 @@
 ---
 description: AI-powered task triage, prioritization, and workload analysis
-argument-hint: "[--auto-assign] [--sla] [--bottleneck]"
+argument-hint: "[--quick] [--auto-assign] [--sla] [--bottleneck]"
 agent: build
 ---
 
@@ -14,11 +14,54 @@ skill({ name: "beads" });
 
 Analyze open tasks and optimize prioritization using dependency graph analysis, SLA tracking, and multi-agent coordination.
 
-## Phase 1: Initialize Beads Connection
+## Quick Mode
+
+If `--quick` flag is passed, skip deep analysis and provide immediate actionable output:
+
+```bash
+bd ready --json
+bd list --status=in_progress --json
+```
+
+**Quick Output:**
+
+```
+Quick Triage
+━━━━━━━━━━━━
+
+Ready to start:
+• bd-abc12: "Task title" (P1)
+• bd-def34: "Task title" (P2)
+
+In progress:
+• bd-ghi56: "Task title" - claimed by [agent]
+
+Next: /start <bead-id>
+```
+
+Then stop. Don't run full analysis phases.
+
+## Full Triage (Default)
+
+## Phase 1: Health Check
+
+Run `bd doctor` to ensure database integrity (recommended weekly):
+
+```bash
+bd doctor --fix 2>/dev/null || bd doctor
+```
+
+This detects and auto-fixes:
+
+- Orphaned issues (work committed but issue not closed)
+- Database/JSONL sync issues
+- Migration updates
+
+## Phase 2: Initialize Beads Connection
 
 !`bd status`
 
-## Phase 2: Gather Workspace State
+## Phase 3: Gather Workspace State
 
 Run in parallel:
 
@@ -27,8 +70,8 @@ Run in parallel:
 
 ```typescript
 // Custom tools (not shell commands)
-bd-release(); // Lists active locks when called with no args
-bd-inbox({ n: 10, unread: true, to: "all" });
+bd - release(); // Lists active locks when called with no args
+bd - inbox({ n: 10, unread: true, to: "all" });
 
 // Search for past discussions on recurring issues
 search_session({ query: "blocked OR regression OR urgent", limit: 10 });
@@ -43,7 +86,7 @@ Capture:
 - Pending messages
 - Past context on recurring issues
 
-## Phase 3: Analyze Dependencies
+## Phase 4: Analyze Dependencies
 
 Use `bd dep tree` to understand blocking relationships:
 
@@ -55,7 +98,7 @@ This provides:
 - **Keystones**: High-impact tasks that unlock multiple paths
 - **Cycles**: Circular dependencies (must break)
 
-## Phase 4: Priority Classification
+## Phase 5: Priority Classification
 
 ### Priority Matrix
 
@@ -112,7 +155,7 @@ const slaStatus =
       : "OK";
 ```
 
-## Phase 5: Bottleneck Analysis
+## Phase 6: Bottleneck Analysis
 
 Identify blocking patterns:
 
@@ -154,7 +197,7 @@ Resolution Options:
 Run: bd update <id> --remove-dep <dep-id>
 ```
 
-## Phase 6: Generate Triage Report
+## Phase 7: Generate Triage Report
 
 ```
 ╔══════════════════════════════════════════════════════════════════════════╗
@@ -210,7 +253,7 @@ RECOMMENDATIONS
 ╚══════════════════════════════════════════════════════════════════════════╝
 ```
 
-## Phase 7: Auto-Assignment (Optional)
+## Phase 8: Auto-Assignment (Optional)
 
 If `--auto-assign` flag:
 
@@ -261,7 +304,7 @@ Skipped:
 - bd-old88: No matching role detected (manual assignment needed)
 ```
 
-## Phase 8: Batch Operations
+## Phase 9: Batch Operations
 
 ### Bulk Priority Update
 
@@ -286,7 +329,18 @@ console.log("2. Move to P4 backlog");
 console.log("3. Review individually");
 ```
 
-## Phase 9: Sync and Notify
+### Database Cleanup (Weekly Maintenance)
+
+Keep database small for performance (target: under 200-500 issues):
+
+```bash
+bd cleanup --days 7  # Remove closed issues older than 7 days
+bd list --status=closed --json | wc -l  # Check closed count
+```
+
+**Best Practice (from Steve Yegge):** Run `bd cleanup` every few days to prevent database bloat.
+
+## Phase 10: Sync and Notify
 
 ```typescript