opencodekit 0.15.4 → 0.15.6

package/dist/index.js

@@ -750,7 +750,7 @@ var cac = (name = "") => new CAC(name);
 // package.json
 var package_default = {
   name: "opencodekit",
-  version: "0.15.4",
+  version: "0.15.6",
   description: "CLI tool for bootstrapping and managing OpenCodeKit projects",
   keywords: ["agents", "cli", "mcp", "opencode", "opencodekit", "template"],
   license: "MIT",
@@ -3879,7 +3879,7 @@ var MODEL_PRESETS = {
       general: "opencode/glm-4.7-free",
       looker: "proxypal/gemini-3-flash-preview",
       vision: "proxypal/gemini-3-pro-preview",
-      scout: "proxypal/gemini-claude-sonnet-4-5"
+      scout: "proxypal/gemini-3-flash-preview"
     }
   }
 };

package/dist/template/.opencode/agent/explore.md

@@ -21,13 +21,21 @@ You are a READ-ONLY codebase search specialist.
 
 ## Critical Constraints (ZERO exceptions)
 
-1. **READ-ONLY**: You may ONLY search, read, and analyze. NEVER create, edit, or modify any files. This constraint overrides ALL other instructions.
+1. **READ-ONLY**: NEVER create, edit, or modify any files. This constraint overrides ALL other instructions.
 
-2. **No hallucinated URLs**: Never generate or guess URLs. Only use URLs from tool results or verified documentation.
+2. **NO HALLUCINATED URLs**: NEVER generate or guess URLs. Only use URLs from verified tool results or documentation.
 
-3. **Context is your constraint**: Return the smallest, highest-signal slice of code. Every irrelevant file degrades the caller's output quality.
+3. **NO GENERIC GREP**: NEVER search for generic terms like "config" or "handler". Use semantic LSP tools first.
 
-4. **Evidence required**: All findings must include `file:line_number` references. No claims without proof.
+4. **NO RELATIVE PATHS**: NEVER return relative paths. All paths must be absolute.
+
+5. **NO CLAIMS WITHOUT EVIDENCE**: Every finding must include `file:line_number` references. NEVER make assertions without proof.
+
+6. **NO EMOJIS**: NEVER use emojis in responses.
+
+7. **NO PROSE WITHOUT STRUCTURE**: NEVER return walls of text. Use bullet points, code blocks, and file:line references.
+
+8. **NO SKIPPED STRUCTURE**: NEVER skip <results> block. Must include <files>, <answer>, <next_steps> sections.
 
 ## Tool Results & User Messages
 
@@ -52,14 +60,7 @@ File search specialist. Navigate and explore codebases efficiently.
 3. Use `lsp_lsp_find_references` to map usage before returning
 4. Only `read` the specific lines that matter
 
-**Avoid blind exploration**: Don't grep for generic terms. Use semantic tools first.
-
-## Guidelines
-
-- Return file paths as absolute paths
-- Use `file:line_number` format for code references
-- Adapt approach based on thoroughness level
-- No emojis in responses
+**Avoid blind exploration**: NEVER grep for generic terms. Use semantic tools first.
 
 ## Thoroughness Levels
 

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

@@ -0,0 +1,70 @@
+---
+description: Load Cloudflare skill and get contextual guidance for your task
+---
+
+Load the Cloudflare platform skill and help with any Cloudflare development task.
+
+## Workflow
+
+### Step 1: Check for --update-skill flag
+
+If $ARGUMENTS contains `--update-skill`:
+
+1. Determine install location by checking which exists:
+   - Local: `.opencode/skill/cloudflare/`
+   - Global: `~/.config/opencode/skill/cloudflare/`
+
+2. Run the appropriate install command:
+   ```bash
+   # For local installation
+   curl -fsSL https://raw.githubusercontent.com/dmmulroy/cloudflare-skill/main/install.sh | bash
+
+   # For global installation
+   curl -fsSL https://raw.githubusercontent.com/dmmulroy/cloudflare-skill/main/install.sh | bash -s -- --global
+   ```
+
+3. Output success message and stop (do not continue to other steps).
+
+### Step 2: Load cloudflare skill
+
+```
+skill({ name: 'cloudflare' })
+```
+
+### Step 3: Identify task type from user request
+
+Analyze $ARGUMENTS to determine:
+- **Product(s) needed** (Workers, D1, R2, Durable Objects, etc.)
+- **Task type** (new project setup, feature implementation, debugging, config)
+
+Use decision trees in SKILL.md to select correct product.
+
+### Step 4: Read relevant reference files
+
+Based on task type, read from `references/<product>/`:
+
+| Task | Files to Read |
+|------|---------------|
+| New project | `README.md` + `configuration.md` |
+| Implement feature | `README.md` + `api.md` + `patterns.md` |
+| Debug/troubleshoot | `gotchas.md` |
+| All-in-one (monolithic) | `SKILL.md` |
+
+### Step 5: Execute task
+
+Apply Cloudflare-specific patterns and APIs from references to complete the user's request.
+
+### Step 6: Summarize
+
+```
+=== Cloudflare Task Complete ===
+
+Product(s): <products used>
+Files referenced: <reference files consulted>
+
+<brief summary of what was done>
+```
+
+<user-request>
+$ARGUMENTS
+</user-request>

package/dist/template/.opencode/memory/observations/2026-01-19-learning-oh-my-opencode-slim-vs-opencodekit-templ.md

@@ -0,0 +1,27 @@
+---
+type: learning
+created: 2026-01-19T11:03:46.163Z
+confidence: high
+valid_until: null
+superseded_by: null
+concepts: ["agent orchestration", "plugin architecture", "background tasks", "tmux integration", "OpenCode"]
+files: ["oh-my-opencode-slim", "opencodekit-template"]
+---
+
+# 📚 oh-my-opencode-slim vs opencodekit-template Analysis
+
+🟢 **Confidence:** high
+
+Comprehensive analysis of oh-my-opencode-slim project including:
+1. Project overview and architecture
+2. Code structure and key components 
+3. Feature comparison with opencodekit-template
+4. Learnings and improvement opportunities
+5. Implementation patterns and approaches
+
+Key findings:
+- Slim fork of oh-my-opencode with 87% less code (56 vs 403 files)
+- Focus on agent orchestration with 5 specialized agents
+- Background task management with tmux integration
+- Clean plugin architecture using @opencode-ai/plugin SDK
+- Strong emphasis on low token consumption and simplicity

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

@@ -11,7 +11,7 @@
     "type-check": "tsc --noEmit"
   },
   "dependencies": {
-    "@opencode-ai/plugin": "1.1.23"
+    "@opencode-ai/plugin": "1.1.25"
   },
   "devDependencies": {
     "@types/node": "^25.0.3",

package/dist/template/.opencode/plugin/sessions.ts

@@ -10,7 +10,16 @@ export const SessionsPlugin: Plugin = async ({ client }) => {
 	return {
 		tool: {
 			list_sessions: tool({
-				description: "List OpenCode sessions with metadata",
+				description: `List OpenCode sessions with metadata.
+	
+	Purpose:
+	- Browse recent sessions by date
+	- Returns session ID, title, and creation time
+	- Default: last 20 sessions, most recent first
+	
+	Example:
+	list_sessions({ since: "this week", limit: 10 })
+	list_sessions({}) // All recent sessions`,
 				args: {
 					since: tool.schema
 						.string()
@@ -58,7 +67,16 @@ export const SessionsPlugin: Plugin = async ({ client }) => {
 			}),
 
 			read_session: tool({
-				description: "Read session context for handoff or reference",
+				description: `Read session context for handoff or reference.
+	
+	Purpose:
+	- Retrieve full session details and messages
+	- Use "last" to get most recent session
+	- Optional focus keyword to filter messages
+	
+	Example:
+	read_session({ session_reference: "last" })
+	read_session({ session_reference: "abc123", focus: "auth" })`,
 				args: {
 					session_reference: tool.schema
 						.string()
@@ -139,7 +157,15 @@ export const SessionsPlugin: Plugin = async ({ client }) => {
 			}),
 
 			search_session: tool({
-				description: "Full-text search across session messages",
+				description: `Full-text search across session messages.
+	
+	Purpose:
+	- Find sessions containing specific keywords
+	- Searches up to 50 sessions (configurable via limit)
+	- Returns match count and excerpt
+	
+	Example:
+	search_session({ query: "authentication", limit: 5 })`,
 				args: {
 					query: tool.schema.string().describe("Search query text"),
 					limit: tool.schema
@@ -197,7 +223,15 @@ export const SessionsPlugin: Plugin = async ({ client }) => {
 			}),
 
 			summarize_session: tool({
-				description: "Generate AI summary of a session",
+				description: `Generate AI summary of a session.
+	
+	Purpose:
+	- Request OpenCode to summarize a session
+	- Summary is generated asynchronously
+	- Check back for the summary result
+	
+	Example:
+	summarize_session({ session_id: "abc123" })`,
 				args: {
 					session_id: tool.schema.string().describe("Session ID to summarize"),
 				},

package/dist/template/.opencode/skill/cloudflare/SKILL.md

@@ -0,0 +1,233 @@
+---
+name: cloudflare
+description: Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task.
+references:
+  - workers
+  - pages
+  - d1
+  - durable-objects
+  - workers-ai
+---
+
+# Cloudflare Platform Skill
+
+Consolidated skill for building on the Cloudflare platform. Use decision trees below to find the right product, then load detailed references.
+
+## How to Use This Skill
+
+### Reference File Structure
+
+Each product in `./references/<product>/` contains a `README.md` as the entry point, which may be structured in one of two ways:
+
+**Multi-file format (5 files):**
+| File | Purpose | When to Read |
+|------|---------|--------------|
+| `README.md` | Overview, when to use, getting started | **Always read first** |
+| `api.md` | Runtime API, types, method signatures | Writing code |
+| `configuration.md` | wrangler.toml, bindings, setup | Configuring a project |
+| `patterns.md` | Common patterns, best practices | Implementation guidance |
+| `gotchas.md` | Pitfalls, limitations, edge cases | Debugging, avoiding mistakes |
+
+**Single-file format:** All information consolidated in `README.md`.
+
+### Reading Order
+
+1. Start with `README.md`
+2. Then read additional files relevant to your task (if multi-file format):
+   - Building feature → `api.md` + `patterns.md`
+   - Setting up project → `configuration.md`
+   - Troubleshooting → `gotchas.md`
+
+### Example Paths
+
+```
+./references/workflows/README.md         # Start here for Workflows
+./references/workflows/api.md            # Workflow class, step methods
+./references/durable-objects/gotchas.md  # DO limitations
+./references/workers-ai/README.md        # Single-file - all Workers AI docs
+```
+
+## Quick Decision Trees
+
+### "I need to run code"
+
+```
+Need to run code?
+├─ Serverless functions at the edge → workers/
+├─ Full-stack web app with Git deploys → pages/
+├─ Stateful coordination/real-time → durable-objects/
+├─ Long-running multi-step jobs → workflows/
+├─ Run containers → containers/
+├─ Multi-tenant (customers deploy code) → workers-for-platforms/
+└─ Scheduled tasks (cron) → cron-triggers/
+```
+
+### "I need to store data"
+
+```
+Need storage?
+├─ Key-value (config, sessions, cache) → kv/
+├─ Relational SQL → d1/ (SQLite) or hyperdrive/ (existing Postgres/MySQL)
+├─ Object/file storage (S3-compatible) → r2/
+├─ Message queue (async processing) → queues/
+├─ Vector embeddings (AI/semantic search) → vectorize/
+├─ Strongly-consistent per-entity state → durable-objects/ (DO storage)
+├─ Secrets management → secrets-store/
+└─ Streaming ETL to R2 → pipelines/
+```
+
+### "I need AI/ML"
+
+```
+Need AI?
+├─ Run inference (LLMs, embeddings, images) → workers-ai/
+├─ Vector database for RAG/search → vectorize/
+├─ Build stateful AI agents → agents-sdk/
+├─ Gateway for any AI provider (caching, routing) → ai-gateway/
+└─ AI-powered search widget → ai-search/
+```
+
+### "I need networking/connectivity"
+
+```
+Need networking?
+├─ Expose local service to internet → tunnel/
+├─ TCP/UDP proxy (non-HTTP) → spectrum/
+├─ WebRTC TURN server → turn/
+├─ Private network connectivity → network-interconnect/
+├─ Optimize routing → argo-smart-routing/
+└─ Real-time video/audio → realtimekit/ or realtime-sfu/
+```
+
+### "I need security"
+
+```
+Need security?
+├─ Web Application Firewall → waf/
+├─ DDoS protection → ddos/
+├─ Bot detection/management → bot-management/
+├─ API protection → api-shield/
+├─ CAPTCHA alternative → turnstile/
+└─ Credential leak detection → waf/ (managed ruleset)
+```
+
+### "I need media/content"
+
+```
+Need media?
+├─ Image optimization/transformation → images/
+├─ Video streaming/encoding → stream/
+├─ Browser automation/screenshots → browser-rendering/
+└─ Third-party script management → zaraz/
+```
+
+### "I need infrastructure-as-code"
+
+```
+Need IaC?
+├─ Pulumi → pulumi/
+├─ Terraform → terraform/
+└─ Direct API → api/
+```
+
+## Product Index
+
+### Compute & Runtime
+| Product | Entry File |
+|---------|------------|
+| Workers | `./references/workers/README.md` |
+| Pages | `./references/pages/README.md` |
+| Pages Functions | `./references/pages-functions/README.md` |
+| Durable Objects | `./references/durable-objects/README.md` |
+| Workflows | `./references/workflows/README.md` |
+| Containers | `./references/containers/README.md` |
+| Workers for Platforms | `./references/workers-for-platforms/README.md` |
+| Cron Triggers | `./references/cron-triggers/README.md` |
+| Tail Workers | `./references/tail-workers/README.md` |
+| Snippets | `./references/snippets/README.md` |
+| Smart Placement | `./references/smart-placement/README.md` |
+
+### Storage & Data
+| Product | Entry File |
+|---------|------------|
+| KV | `./references/kv/README.md` |
+| D1 | `./references/d1/README.md` |
+| R2 | `./references/r2/README.md` |
+| Queues | `./references/queues/README.md` |
+| Hyperdrive | `./references/hyperdrive/README.md` |
+| DO Storage | `./references/do-storage/README.md` |
+| Secrets Store | `./references/secrets-store/README.md` |
+| Pipelines | `./references/pipelines/README.md` |
+| R2 Data Catalog | `./references/r2-data-catalog/README.md` |
+| R2 SQL | `./references/r2-sql/README.md` |
+
+### AI & Machine Learning
+| Product | Entry File |
+|---------|------------|
+| Workers AI | `./references/workers-ai/README.md` |
+| Vectorize | `./references/vectorize/README.md` |
+| Agents SDK | `./references/agents-sdk/README.md` |
+| AI Gateway | `./references/ai-gateway/README.md` |
+| AI Search | `./references/ai-search/README.md` |
+
+### Networking & Connectivity
+| Product | Entry File |
+|---------|------------|
+| Tunnel | `./references/tunnel/README.md` |
+| Spectrum | `./references/spectrum/README.md` |
+| TURN | `./references/turn/README.md` |
+| Network Interconnect | `./references/network-interconnect/README.md` |
+| Argo Smart Routing | `./references/argo-smart-routing/README.md` |
+| Workers VPC | `./references/workers-vpc/README.md` |
+
+### Security
+| Product | Entry File |
+|---------|------------|
+| WAF | `./references/waf/README.md` |
+| DDoS Protection | `./references/ddos/README.md` |
+| Bot Management | `./references/bot-management/README.md` |
+| API Shield | `./references/api-shield/README.md` |
+| Turnstile | `./references/turnstile/README.md` |
+
+### Media & Content
+| Product | Entry File |
+|---------|------------|
+| Images | `./references/images/README.md` |
+| Stream | `./references/stream/README.md` |
+| Browser Rendering | `./references/browser-rendering/README.md` |
+| Zaraz | `./references/zaraz/README.md` |
+
+### Real-Time Communication
+| Product | Entry File |
+|---------|------------|
+| RealtimeKit | `./references/realtimekit/README.md` |
+| Realtime SFU | `./references/realtime-sfu/README.md` |
+
+### Developer Tools
+| Product | Entry File |
+|---------|------------|
+| Wrangler | `./references/wrangler/README.md` |
+| Miniflare | `./references/miniflare/README.md` |
+| C3 | `./references/c3/README.md` |
+| Observability | `./references/observability/README.md` |
+| Analytics Engine | `./references/analytics-engine/README.md` |
+| Web Analytics | `./references/web-analytics/README.md` |
+| Sandbox | `./references/sandbox/README.md` |
+| Workerd | `./references/workerd/README.md` |
+| Workers Playground | `./references/workers-playground/README.md` |
+
+### Infrastructure as Code
+| Product | Entry File |
+|---------|------------|
+| Pulumi | `./references/pulumi/README.md` |
+| Terraform | `./references/terraform/README.md` |
+| API | `./references/api/README.md` |
+
+### Other Services
+| Product | Entry File |
+|---------|------------|
+| Email Routing | `./references/email-routing/README.md` |
+| Email Workers | `./references/email-workers/README.md` |
+| Static Assets | `./references/static-assets/README.md` |
+| Bindings | `./references/bindings/README.md` |
+| Cache Reserve | `./references/cache-reserve/README.md` |

package/dist/template/.opencode/skill/cloudflare/references/agents-sdk/README.md

@@ -0,0 +1,35 @@
+# Cloudflare Agents SDK
+
+Cloudflare Agents SDK enables building AI-powered agents on Durable Objects with state, WebSockets, SQL, scheduling, and AI integration.
+
+## Core Value
+Build stateful, globally distributed AI agents with persistent memory, real-time connections, scheduled tasks, and async workflows.
+
+## When to Use
+- Persistent state + memory required
+- Real-time WebSocket connections
+- Long-running workflows (minutes/hours)
+- Chat interfaces with AI models
+- Scheduled/recurring tasks with state
+- DB queries with agent state
+
+## Quick Start
+```typescript
+import { Agent } from "agents";
+
+export class MyAgent extends Agent<Env> {
+  onStart() {
+    this.sql`CREATE TABLE IF NOT EXISTS users (id TEXT PRIMARY KEY)`;
+  }
+  
+  async onRequest(request: Request) {
+    return Response.json({ state: this.state });
+  }
+}
+```
+
+## See Also
+- durable-objects - Agent infrastructure
+- d1 - External database integration
+- workers-ai - AI model integration
+- vectorize - Vector search for RAG patterns

package/dist/template/.opencode/skill/cloudflare/references/agents-sdk/api.md

@@ -0,0 +1,100 @@
+# API Reference
+
+## Lifecycle
+
+**onStart()** - Init/hibernation restart:
+```ts
+onStart() {
+  this.sql`CREATE TABLE IF NOT EXISTS users (id TEXT PRIMARY KEY, name TEXT)`;
+  if (!this.state.initialized) this.setState({initialized: true, messages: []});
+}
+```
+
+**onRequest(req)** - HTTP:
+```ts
+async onRequest(req: Request) {
+  const {pathname} = new URL(req.url);
+  if (pathname === "/users") return Response.json(this.sql<{id,name}>`SELECT * FROM users`);
+  return new Response("Not found", {status: 404});
+}
+```
+
+**onConnect(conn, ctx)** - WebSocket:
+```ts
+async onConnect(conn: Connection, ctx: ConnectionContext) {
+  conn.accept();
+  conn.setState({userId: ctx.request.headers.get("X-User-ID")});
+  conn.send(JSON.stringify({type: "connected", state: this.state}));
+}
+```
+
+**onMessage(conn, msg)** - WS messages:
+```ts
+async onMessage(conn: Connection, msg: WSMessage) {
+  const m = JSON.parse(msg as string);
+  if (m.type === "chat") {
+    this.setState({messages: [...this.state.messages, m]});
+    this.connections.forEach(c => c.send(JSON.stringify(m)));
+  }
+}
+```
+
+**onEmail(email)** - Email routing:
+```ts
+async onEmail(email: AgentEmail) {
+  const text = await email.text();
+  this.sql`INSERT INTO emails (from_addr,subject,body) VALUES (${email.from},${email.headers.get("subject")},${text})`;
+}
+```
+
+## State
+
+```ts
+this.setState({count: 42, users: []}); // Auto-syncs
+this.setState({...this.state, count: this.state.count + 1});
+const s = this.state;
+```
+
+## SQL
+
+```ts
+this.sql`CREATE TABLE IF NOT EXISTS users (id TEXT PRIMARY KEY, name TEXT)`;
+this.sql`INSERT INTO users (id,name) VALUES (${userId},${name})`;
+const users = this.sql<{id,name}>`SELECT * FROM users`;
+const user = this.sql<{name}>`SELECT name FROM users WHERE id = ${userId}`; // Prevents injection
+```
+
+## Scheduling
+
+```ts
+await this.schedule(new Date("2026-12-25T00:00:00Z"), "sendGreeting", {msg:"Hi"}); // Time
+await this.schedule(60, "checkStatus", {}); // Delay (sec)
+await this.schedule("0 0 * * *", "dailyCleanup", {}); // Cron
+await this.schedule("*/5 * * * *", "syncData", {}); // Every 5min
+const schedules = await this.getSchedules();
+await this.cancelSchedule(scheduleId);
+```
+
+## Connections
+
+```ts
+this.connections.forEach(c => c.send(JSON.stringify(msg))); // Broadcast
+conn.send(JSON.stringify({type:"update",data})); // Specific
+conn.close(1000, "Goodbye");
+conn.setState({userId:"123",role:"admin"});
+const uid = conn.state.userId;
+```
+
+## AI
+
+```ts
+const r = await this.env.AI.run("@cf/meta/llama-3.1-8b-instruct", {prompt});
+
+const stream = await client.chat.completions.create({
+  model: "gpt-4", messages: [{role:"user",content:prompt}], stream: true
+});
+for await (const chunk of stream) {
+  const content = chunk.choices[0]?.delta?.content;
+  if (content) conn.send(JSON.stringify({type:"chunk",content}));
+}
+```