opencodekit 0.19.1 → 0.19.2

package/dist/index.js

@@ -20,7 +20,7 @@ var __require = /* @__PURE__ */ createRequire(import.meta.url);
 
 //#endregion
 //#region package.json
-var version = "0.19.1";
+var version = "0.19.2";
 
 //#endregion
 //#region src/utils/license.ts

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

@@ -46,6 +46,15 @@ You have access to the TodoWrite tools to help you manage and plan tasks. Use th
 
 When referencing specific functions or pieces of code include the pattern `file_path:line_number` to allow the user to easily navigate to the source code location.
 
+# Web Research Tool Priority
+
+When fetching content from URLs (docs, READMEs, web pages):
+
+1. **`webclaw` MCP tools** (primary) — `scrape`, `crawl`, `batch`, `brand`. Handles 403s, bot protection, 67% fewer tokens.
+2. **`webfetch`** (fallback) — only if webclaw is unavailable or returns an error.
+
+Never use `webfetch` as first choice when webclaw MCP is connected.
+
 # Build Agent
 
 **Purpose**: Primary execution coordinator — you ship working code, not promises.  

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

@@ -81,7 +81,13 @@ If lower-ranked sources conflict with higher-ranked sources, follow higher-ranke
    |------|------|
    | docs/API | `context7`, `codesearch` |
    | production examples | `grepsearch`, `codesearch` |
-   | latest ecosystem/release info | `websearch`, `webfetch` |
+   | latest ecosystem/release info | `websearch` (search), then `webclaw` (`scrape`) for content |
+   | URL content extraction | `webclaw` MCP (`scrape`) — primary; `webfetch` only as fallback |
+   | crawl a doc site | `webclaw` MCP (`crawl`) |
+   | batch multi-URL extraction | `webclaw` MCP (`batch`) |
+   | brand identity from a site | `webclaw` MCP (`brand`) |
+
+   **Web content priority:** Always try `webclaw` tools first for URL extraction. They handle 403s, bot protection, and produce 67% fewer tokens than raw HTML. Fall back to `webfetch` only if webclaw is unavailable.
 
 3. Run independent calls in parallel
 4. Return concise recommendations with sources

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

@@ -72,6 +72,7 @@ Route by need:
 | Distinctive UI direction / anti-slop guidance | `frontend-design`     |
 | Figma design data (read/write via MCP)        | `figma-go`            |
 | Pencil design-as-code workflow                | `pencil`              |
+| Brand identity extraction from URLs           | `webclaw`             |
 
 ### Taste-Skill Variants (installed)
 
@@ -115,6 +116,14 @@ If design must be created or iterated quickly, use Pencil:
 2. Export PNGs for review
 3. Provide audit with node-level critique where possible
 
+## Brand Extraction Workflow (when auditing existing sites)
+
+Use `webclaw` MCP to extract brand identity from live sites:
+
+1. `brand(url)` → get colors, fonts, logos
+2. Cross-reference with visual analysis findings
+3. Flag inconsistencies between declared brand and actual UI
+
 ## Design QA Checklist (strict)
 
 - **Hierarchy**: clear H1/H2/body scale and weight separation

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

@@ -115,6 +115,12 @@
 			"environment": {},
 			"timeout": 120000,
 			"type": "local"
+		},
+		"webclaw": {
+			"command": ["webclaw-mcp"],
+			"enabled": true,
+			"timeout": 120000,
+			"type": "local"
 		}
 	},
 	"model": "opencode/minimax-m2.5-free",
@@ -171,7 +177,7 @@
 				"claude-haiku-4.5": {
 					"attachment": true,
 					"limit": {
-						"context": 144000,
+						"context": 216000,
 						"output": 32000
 					},
 					"options": {
@@ -199,7 +205,7 @@
 				"claude-opus-4.5": {
 					"attachment": true,
 					"limit": {
-						"context": 160000,
+						"context": 216000,
 						"output": 32000
 					},
 					"options": {
@@ -224,7 +230,7 @@
 				"claude-opus-4.6": {
 					"attachment": true,
 					"limit": {
-						"context": 144000,
+						"context": 216000,
 						"output": 64000
 					},
 					"options": {
@@ -294,7 +300,7 @@
 				"claude-sonnet-4.5": {
 					"attachment": true,
 					"limit": {
-						"context": 144000,
+						"context": 216000,
 						"output": 32000
 					},
 					"options": {
@@ -319,7 +325,7 @@
 				"claude-sonnet-4.6": {
 					"attachment": true,
 					"limit": {
-						"context": 200000,
+						"context": 216000,
 						"output": 32000
 					},
 					"options": {

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

@@ -0,0 +1,155 @@
+---
+name: webclaw
+description: Web content extraction, crawling, and scraping via webclaw MCP server. Use when fetching URLs fails (403), when crawling doc sites, batch-extracting pages, tracking content changes, or extracting brand identity from websites.
+---
+
+# Webclaw Skill
+
+Fast, local-first web content extraction for LLMs. Rust-based scraper with TLS fingerprinting, 67% token reduction, and native MCP integration.
+
+## Prerequisites
+
+- `webclaw-mcp` binary installed at `~/.webclaw/webclaw-mcp`
+- Install: `brew tap 0xMassi/webclaw && brew install webclaw`
+- Or: download from https://github.com/0xMassi/webclaw/releases
+- MCP server must be enabled in `.opencode/opencode.json` (`"enabled": true`)
+
+## When to Use
+
+| Scenario               | Tool                   | Why                                        |
+| ---------------------- | ---------------------- | ------------------------------------------ |
+| `webfetch` got 403     | `scrape`               | TLS fingerprinting bypasses bot protection |
+| Research a doc site    | `crawl`                | BFS recursive extraction, same-origin      |
+| Extract multiple URLs  | `batch`                | Parallel multi-URL, faster than sequential |
+| Discover sitemap URLs  | `map`                  | Find all pages without crawling            |
+| Track doc changes      | `diff`                 | Snapshot + compare workflow                |
+| Extract brand identity | `brand`                | Colors, fonts, logos from any site         |
+| LLM-optimized output   | `scrape` with `-f llm` | 67% fewer tokens than raw HTML             |
+
+## MCP Tools (8 local, no API key needed)
+
+### scrape
+
+Extract clean content from a URL. Returns markdown, text, JSON, or LLM-optimized format.
+
+```
+scrape(url: "https://example.com", format: "llm")
+```
+
+Options: `format` (markdown|text|json|llm|html), `include` (CSS selectors), `exclude` (CSS selectors), `only_main_content` (boolean)
+
+### crawl
+
+Recursive BFS crawl of a site. Same-origin only.
+
+```
+crawl(url: "https://docs.example.com", depth: 2, max_pages: 50)
+```
+
+Options: `depth` (1-10), `max_pages`, `sitemap` (seed from sitemap.xml)
+
+### map
+
+Discover URLs from a site's sitemap without fetching content.
+
+```
+map(url: "https://docs.example.com")
+```
+
+### batch
+
+Parallel extraction from multiple URLs.
+
+```
+batch(urls: ["https://a.com", "https://b.com"], format: "llm")
+```
+
+### diff
+
+Compare current page content against a previous snapshot.
+
+```
+diff(url: "https://example.com", snapshot: previous_json)
+```
+
+### brand
+
+Extract visual identity: colors, fonts, logos, OG image.
+
+```
+brand(url: "https://stripe.com")
+```
+
+Returns: `{ name, colors: [{hex, usage}], fonts: [], logos: [{url, kind}] }`
+
+### extract (needs Ollama)
+
+LLM-powered structured extraction. Requires local Ollama instance.
+
+### summarize (needs Ollama)
+
+Page summarization via local LLM.
+
+## Workflow Patterns
+
+### Fallback when webfetch fails
+
+1. Try `webfetch` first (built-in, no setup)
+2. If 403 or empty → use `scrape` via webclaw MCP
+3. If JS-rendered SPA → note limitation (webclaw doesn't execute JS without cloud API)
+
+### Research a documentation site
+
+1. `map(url)` to discover all pages
+2. `crawl(url, depth: 2, max_pages: 50)` to extract content
+3. Feed results to analysis agent
+
+### Brand/design audit
+
+1. `brand(url)` to extract colors, fonts, logos
+2. Pass to vision agent for design system analysis
+
+### Track changes over time
+
+1. `scrape(url, format: "json")` → save as snapshot
+2. Later: `diff(url, snapshot: saved)` → see what changed
+
+## Installation
+
+```bash
+# Homebrew (recommended)
+brew tap 0xMassi/webclaw
+brew install webclaw
+
+# Prebuilt binary
+# Download from https://github.com/0xMassi/webclaw/releases
+# Place webclaw-mcp in ~/.webclaw/
+
+# Verify
+webclaw-mcp --version
+```
+
+## Configuration
+
+After install, enable in `.opencode/opencode.json`:
+
+```json
+{
+  "mcp": {
+    "webclaw": {
+      "enabled": true
+    }
+  }
+}
+```
+
+Optional env vars:
+
+- `WEBCLAW_API_KEY` — cloud API for bot-protected sites (optional)
+- `OLLAMA_HOST` — for extract/summarize tools (default: `http://localhost:11434`)
+
+## Limitations
+
+- **No JS rendering** (local mode) — SPAs that render entirely client-side won't extract fully. Use `--cloud` with API key, or use `playwright` skill instead.
+- **Same-origin crawl only** — won't follow external links during crawl.
+- **Early version** — v0.3.2, MIT license. Report issues to https://github.com/0xMassi/webclaw/issues

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "opencodekit",
-	"version": "0.19.1",
+	"version": "0.19.2",
 	"description": "CLI tool for bootstrapping and managing OpenCodeKit projects",
 	"keywords": [
 		"agents",