opencodekit 0.13.2 → 0.14.1

package/dist/template/.opencode/command/skill-optimize.md

@@ -150,7 +150,37 @@ Rules:
 
 ### Clarification Techniques
 
-```
+````
+BEFORE (vague):
+──────────────
+"Check that the configuration is correct."
+
+AFTER (specific):
+────────────────
+"Verify config:
+1. Run: `npm run config:check`
+2. Confirm output shows: 'Configuration valid'
+3. If errors, check [specific file] for [specific issue]"
+
+Rules:
+- Replace "check" with specific verification command
+- Include expected output
+- Add troubleshooting for failures
+
+Use question tool to confirm:
+```typescript
+question({
+  questions: [{
+    header: "Verify",
+    question: "Configuration verified. Ready to continue?",
+    options: [
+      { label: "Yes, continue", description: "Proceed with optimization" },
+      { label: "No, fix issues", description: "Address validation errors first" }
+    ]
+  }]
+});
+````
+
 BEFORE (vague):
 ───────────────
 "Check that the configuration is correct."
@@ -158,19 +188,23 @@ BEFORE (vague):
 AFTER (specific):
 ─────────────────
 "Verify config:
+
 1. Run: `npm run config:check`
 2. Confirm output shows: 'Configuration valid'
 3. If errors, check [specific file] for [specific issue]"
 
 Rules:
+
 - Replace "check" with specific verification command
 - Include expected output
 - Add troubleshooting for failures
+
 ```
 
 ### Hardening Techniques
 
 ```
+
 BEFORE (soft):
 ──────────────
 "You should generally avoid committing directly to main."
@@ -180,20 +214,24 @@ AFTER (hardened):
 "NEVER commit directly to main. ALWAYS use feature branches.
 
 If tempted to commit to main because 'it's just a small fix':
+
 - STOP
 - Create branch anyway: git checkout -b fix/small-fix
 - This is NOT optional"
 
 Rules:
+
 - Add MUST/NEVER to critical rules
 - Anticipate rationalizations
 - Explicitly reject common excuses
 - Name the anti-pattern
+
 ```
 
 ### Expansion Techniques
 
 ```
+
 BEFORE (incomplete):
 ────────────────────
 "Handle errors appropriately."
@@ -203,23 +241,28 @@ AFTER (comprehensive):
 "Error Handling:
 
 Network Errors:
+
 - Retry 2x with exponential backoff
 - If still failing, log and surface to user
 
 Validation Errors:
+
 - Display specific field errors
 - Do NOT proceed with invalid data
 
 Permission Errors:
+
 - Log with full context
 - Display user-friendly message
 - Do NOT expose internal details"
 
 Rules:
+
 - List specific error categories
 - Provide handling for each
 - Include what NOT to do
-```
+
+````
 
 ## Phase 5: Test Optimizations
 
@@ -232,9 +275,9 @@ task({
   description: "Test original skill",
   prompt: `
     Load skill: skill({ name: "$ARGUMENTS" })
-    
+
     Scenario: [test scenario]
-    
+
     Follow the skill and report each step.
   `,
 });
@@ -245,13 +288,13 @@ task({
   description: "Test optimized skill",
   prompt: `
     Load skill: skill({ name: "$ARGUMENTS" })
-    
+
     Scenario: [same test scenario]
-    
+
     Follow the skill and report each step.
   `,
 });
-```
+````
 
 ### Compare Results
 
@@ -367,6 +410,27 @@ write({
 skill({ name: "$ARGUMENTS" });
 ```
 
+```typescript
+question({
+  questions: [
+    {
+      header: "Verify",
+      question: "Skill optimized and saved. Ready to deploy?",
+      options: [
+        {
+          label: "Yes, deploy (Recommended)",
+          description: "All verifications passed",
+        },
+        {
+          label: "No, fix issues",
+          description: "Need to address verification failures",
+        },
+      ],
+    },
+  ],
+});
+```
+
 Confirm:
 
 - [ ] Skill loads without error

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

@@ -75,14 +75,40 @@ bd update $ARGUMENTS --status in_progress
 
 ## Workspace Setup
 
-### Option A: Feature Branch (default)
+### Create Feature Branch
 
-If not already on a feature branch:
+Extract task info and parent branch for a readable branch name:
 
 ```bash
-git checkout -b $ARGUMENTS
+# Get current branch (parent branch)
+PARENT_BRANCH=$(git rev-parse --abbrev-ref HEAD)
+
+# Get task title and type from bead
+BEAD_INFO=$(bd show $ARGUMENTS --json 2>/dev/null)
+BEAD_TITLE=$(echo "$BEAD_INFO" | jq -r '.title // ""' | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/--*/-/g' | cut -c1-40)
+BEAD_TYPE=$(echo "$BEAD_INFO" | jq -r '.type // "task"')
+
+# Map bead type to branch prefix
+case "$BEAD_TYPE" in
+  "bug") PREFIX="fix" ;;
+  "feature"|"epic") PREFIX="feat" ;;
+  "refactor") PREFIX="refactor" ;;
+  "chore") PREFIX="chore" ;;
+  *) PREFIX="feat" ;;
+esac
+
+# Create branch: <parent>/<type>/<bead-id>-<description>
+BRANCH_NAME="${PARENT_BRANCH}/${PREFIX}/$ARGUMENTS-${BEAD_TITLE}"
+git checkout -b "$BRANCH_NAME" 2>/dev/null || echo "Branch already exists or already on it"
 ```
 
+**Branch naming convention:**
+| Parent Branch | Bead Type | Example |
+|---------------|-----------|---------|
+| main | bug | `main/fix/bd-a1b2-login-error` |
+| develop | feature | `develop/feat/bd-c3d4-user-auth` |
+| release-v2 | chore | `release-v2/chore/bd-e5f6-update-deps` |
+
 ### Option B: Git Worktree (if --worktree flag)
 
 For isolated work that won't conflict with main workspace:
@@ -101,11 +127,30 @@ skill({ name: "using-git-worktrees" });
 **Worktree setup:**
 
 ```bash
+# Get current branch (parent branch)
+PARENT_BRANCH=$(git rev-parse --abbrev-ref HEAD)
+
+# Get task title for readable worktree name
+BEAD_INFO=$(bd show $ARGUMENTS --json 2>/dev/null)
+BEAD_TITLE=$(echo "$BEAD_INFO" | jq -r '.title // ""' | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9]/-/g' | sed 's/--*/-/g' | cut -c1-40)
+BEAD_TYPE=$(echo "$BEAD_INFO" | jq -r '.type // "task"')
+
+# Map bead type to branch prefix
+case "$BEAD_TYPE" in
+  "bug") PREFIX="fix" ;;
+  "feature"|"epic") PREFIX="feat" ;;
+  "refactor") PREFIX="refactor" ;;
+  *) PREFIX="feat" ;;
+esac
+
+# Create branch: <parent>/<type>/<bead-id>-<description>
+BRANCH_NAME="${PARENT_BRANCH}/${PREFIX}/$ARGUMENTS-${BEAD_TITLE}"
+
 # Verify .gitignore has worktree directory
 grep -q "^\.worktrees/$" .gitignore || echo ".worktrees/" >> .gitignore
 
-# Create worktree
-git worktree add .worktrees/$ARGUMENTS -b $ARGUMENTS
+# Create worktree with readable branch name
+git worktree add ".worktrees/$ARGUMENTS" -b "$BRANCH_NAME"
 
 # Navigate to worktree
 cd .worktrees/$ARGUMENTS
@@ -172,6 +217,37 @@ list_sessions({ limit: 3 });
 
 Load context from previous work on this bead.
 
+## Load Related Memory (Semantic Search)
+
+Search for relevant past work and learnings before starting:
+
+```typescript
+// Find similar past work (semantic similarity)
+memory -
+  search({
+    query: "[task title/description from bead]",
+    mode: "semantic",
+    limit: 3,
+  });
+
+// Find related observations (gotchas, patterns, learnings)
+memory -
+  search({
+    query: "[task keywords]",
+    mode: "semantic",
+    type: "observation",
+    limit: 3,
+  });
+```
+
+**Review findings before diving in.** Past observations may contain:
+
+- Gotchas to avoid
+- Patterns that worked well
+- Decisions already made
+
+If memory search fails (Ollama not running), continue without it.
+
 ## Determine Next Step
 
 Based on task type and what exists:

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

@@ -340,7 +340,22 @@ 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
+## Phase 10: Check Memory Health
+
+```typescript
+memory - index({ action: "status" });
+```
+
+If documents count is low or index is stale:
+
+```
+⚠️  Vector store may be stale.
+Run: memory-index rebuild
+```
+
+Optionally trigger background reindex if many observations were created recently.
+
+## Phase 11: Sync and Notify
 
 ```typescript
 

package/dist/template/.opencode/dcp.jsonc

@@ -14,28 +14,32 @@
 			// Nudge every 8 tool calls (slightly more aggressive than default 10)
 			"nudgeFrequency": 8,
 			// Protect state-modifying and critical workflow tools
+			// Updated for v1.1.8: Added question tool, removed legacy bd_* (use CLI)
 			"protectedTools": [
 				"write",
 				"edit",
+				"question",
 				"memory-read",
 				"memory-update",
 				"memory-search",
 				"observation",
 				"skill",
 				"skill_mcp",
+				"task",
+				"batch",
+				"todowrite",
+				"todoread",
+				"lsp",
 				"lsp_lsp_rename",
 				"lsp_lsp_find_references",
 				"lsp_lsp_goto_definition",
 				"lsp_lsp_code_actions",
 				"lsp_lsp_code_action_apply",
 				"lsp_lsp_organize_imports",
-				"bd_init",
-				"bd_claim",
-				"bd_done",
-				"bd_show",
-				"bd_reserve",
-				"bd_reservations",
-				"bd_sync"
+				"bd-reserve",
+				"bd-release",
+				"bd-msg",
+				"bd-inbox"
 			]
 		},
 		"discard": {

package/dist/template/.opencode/memory/observations/2026-01-09-pattern-ampcode-mcp-json-includetools-pattern.md

@@ -0,0 +1,42 @@
+---
+type: pattern
+created: 2026-01-09T08:04:40.257Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["mcp", "includeTools", "ampcode", "skill", "token-optimization", "lazy-load", "filtering"]
+---
+
+# 🔄 Ampcode mcp.json includeTools pattern
+
+🟢 **Confidence:** high
+
+Learned from Ampcode's ui-preview skill (https://github.com/ampcode/amp-contrib/tree/main/.agents/skills/ui-preview):
+
+## Pattern: Lazy-load MCP with includeTools filtering
+
+1. **mcp.json file** (separate from SKILL.md):
+```json
+{
+  "chrome-devtools": {
+    "command": "npx",
+    "args": ["-y", "chrome-devtools-mcp@latest"],
+    "includeTools": ["navigate_page", "take_screenshot", "new_page", "list_pages"]
+  }
+}
+```
+
+2. **SKILL.md documents ONLY filtered tools**:
+- "Available Tools" section lists only the filtered tools
+- Workflow examples use only those tools
+- Note at bottom explains how to expand filter if needed
+
+3. **Token savings**: ~90% reduction (4 tools vs 26+ for chrome-devtools)
+
+## Applied to OpenCodeKit:
+- chrome-devtools: 11 tools (from 26+) 
+- playwright: 8 tools (from 17+)
+- Other MCP skills already minimal (2-4 tools), no filtering needed
+
+## Key insight:
+SKILL.md and mcp.json must be synchronized - don't document tools that aren't in includeTools filter, or agents get confused.

package/dist/template/.opencode/memory/project/conventions.md

@@ -85,6 +85,37 @@ Always protect these tools from auto-pruning:
 ]
 ```
 
+### Prompt Injection Pattern (Nudges)
+
+Use `chat.message` hook to inject prompts (nudges) based on user triggers:
+
+```typescript
+"chat.message": async (input, output) => {
+  const { message, parts } = output;
+  if (message.role !== "user") return;
+
+  // 1. Detect trigger keywords
+  const fullText = parts.map(p => p.text).join(" ");
+  if (!fullText.match(/trigger pattern/)) return;
+
+  // 2. Inject synthetic prompt
+  parts.push({
+    type: "text",
+    text: "━━━━━━━━\n[TRIGGER DETECTED]\nAction required: ...\n━━━━━━━━",
+    synthetic: true
+  });
+}
+```
+
+This transforms passive detection into active agent behavior (e.g., Memory plugin triggers).
+
+## Agent Behavior Rules
+
+### Active LSP Nudge
+
+When a tool output displays `[LSP NAVIGATION AVAILABLE]`, it means relevant code files were found.
+**Rule**: You MUST immediately execute the suggested `lsp_lsp_*` tool calls to retrieve code context without waiting for user instruction. This ensures you always have the latest code context for your implementation.
+
 ## Patterns to Avoid
 
 ### Anti-Pattern: Mixing LSP Systems

package/dist/template/.opencode/memory/project/gotchas.md

@@ -1,12 +1,46 @@
 ---
 purpose: Footguns, edge cases, and "don't forget this" warnings
-updated: 2025-01-05
+updated: 2025-01-09
 ---
 
 # Project Gotchas
 
 ## Configuration Quirks
 
+### OpenCode v1.1.7 → v1.1.8 Changes
+
+**v1.1.7 Features:**
+
+- **Question tool**: New interactive tool for gathering user preferences/clarifying instructions
+- **Config precedence fix**: Local `.opencode/opencode.json` now correctly overrides remote/global config
+- **`.claude` loading toggle**: Can disable via `--no-claude-prompts` / `--no-claude-skills` flags
+- **Task tool filtering**: Simplified subagent filtering
+
+**v1.1.8 Features:**
+
+- **Multi-select questions**: Question tool now supports `multiple: true` for multi-select
+- **Performance**: Chunked message loading, lazy diff rendering
+- **Full path fuzzy matching**: Autocomplete uses full file paths
+- **OpenTUI v0.1.70**: UI improvements
+
+**Plugin SDK Update Required:**
+
+```json
+"@opencode-ai/plugin": "^1.1.8"  // Was ^1.1.2
+```
+
+### DCP Protected Tools (v1.1.8)
+
+Legacy `bd_*` tool names don't exist - use actual custom tool names:
+
+| Old (Wrong)       | New (Correct) |
+| ----------------- | ------------- |
+| `bd_init`         | N/A (use CLI) |
+| `bd_claim`        | N/A (use CLI) |
+| `bd_reserve`      | `bd-reserve`  |
+| `bd_reservations` | `bd-release`  |
+| `bd_sync`         | N/A (use CLI) |
+
 ### DCP v1.1.3 Schema Breaking Changes
 
 1. **Legacy `strategies.onIdle` removed**: v1.1.2+ no longer supports this field
@@ -35,10 +69,23 @@ updated: 2025-01-05
 
 ### Protected Tools in DCP
 
-v1.1.3 recognizes more tool variants. Ensure these are protected:
-
-- `lsp_lsp_find_references`, `lsp_lsp_goto_definition` (plugin-specific naming)
-- `memory-search`, `skill_mcp`, `bd_sync` (often forgotten)
+v1.1.8 recognizes more tool variants. Ensure these are protected:
+
+```jsonc
+"protectedTools": [
+  // State-modifying
+  "write", "edit", "question",
+  // Memory/observation
+  "memory-read", "memory-update", "memory-search", "observation",
+  // Skills/tasks
+  "skill", "skill_mcp", "task", "batch", "todowrite", "todoread",
+  // LSP
+  "lsp", "lsp_lsp_rename", "lsp_lsp_find_references", "lsp_lsp_goto_definition",
+  "lsp_lsp_code_actions", "lsp_lsp_code_action_apply", "lsp_lsp_organize_imports",
+  // Beads (custom tools only - CLI uses bash)
+  "bd-reserve", "bd-release", "bd-msg", "bd-inbox"
+]
+```
 
 ## Time Wasters
 

package/dist/template/.opencode/opencode.json

@@ -6,7 +6,8 @@
 			"model": "proxypal/gemini-claude-opus-4-5-thinking"
 		},
 		"compaction": {
-			"description": "Session summarizer for context continuity across compactions"
+			"description": "Session summarizer for context continuity across compactions",
+			"model": "opencode/big-pickle"
 		},
 		"explore": {
 			"description": "Fast codebase search specialist",
@@ -24,7 +25,7 @@
 		},
 		"review": {
 			"description": "Code review, debugging, and security audit specialist",
-			"model": "proxypal/gemini-claude-opus-4-5-thinking"
+			"model": "proxypal/gemini-3-pro-preview"
 		},
 		"rush": {
 			"description": "Fast primary agent for small, well-defined tasks",
@@ -98,7 +99,7 @@
 			"url": "https://mcp.grep.app"
 		}
 	},
-	"model": "github-copilot/claude-haiku-4.5",
+	"model": "opencode/glm-4.7-free",
 	"permission": {
 		"bash": {
 			"*": "allow",
@@ -121,6 +122,7 @@
 		"doom_loop": "ask",
 		"edit": "allow",
 		"external_directory": "ask",
+		"question": "allow",
 		"read": {
 			"*": "allow",
 			"*.env": "deny",

package/dist/template/.opencode/package.json

@@ -11,7 +11,9 @@
 	"author": "",
 	"license": "ISC",
 	"dependencies": {
-		"@opencode-ai/plugin": "1.1.6"
+		"@lancedb/lancedb": "^0.23.0",
+		"@opencode-ai/plugin": "1.1.8",
+		"openai": "^6.15.0"
 	},
 	"devDependencies": {
 		"@types/node": "^25.0.3",