codexkit 1.0.0

package/.codex/skills/cloudflare/references/r2/patterns.md

@@ -0,0 +1,127 @@
+# R2 Patterns & Best Practices
+
+## Streaming Large Files
+
+```typescript
+const object = await env.MY_BUCKET.get(key);
+if (!object) return new Response('Not found', { status: 404 });
+
+const headers = new Headers();
+object.writeHttpMetadata(headers);
+headers.set('etag', object.httpEtag);
+
+return new Response(object.body, { headers });
+```
+
+## Conditional GET (304 Not Modified)
+
+```typescript
+const ifNoneMatch = request.headers.get('if-none-match');
+const object = await env.MY_BUCKET.get(key, {
+  onlyIf: { etagDoesNotMatch: ifNoneMatch?.replace(/"/g, '') || '' }
+});
+
+if (!object) return new Response('Not found', { status: 404 });
+if (!object.body) return new Response(null, { status: 304, headers: { 'etag': object.httpEtag } });
+
+return new Response(object.body, { headers: { 'etag': object.httpEtag } });
+```
+
+## Upload with Validation
+
+```typescript
+const key = url.pathname.slice(1);
+if (!key || key.includes('..')) return new Response('Invalid key', { status: 400 });
+
+const object = await env.MY_BUCKET.put(key, request.body, {
+  httpMetadata: { contentType: request.headers.get('content-type') || 'application/octet-stream' },
+  customMetadata: { uploadedAt: new Date().toISOString(), ip: request.headers.get('cf-connecting-ip') || 'unknown' }
+});
+
+return Response.json({ key: object.key, size: object.size, etag: object.httpEtag });
+```
+
+## Multipart with Progress
+
+```typescript
+const PART_SIZE = 5 * 1024 * 1024; // 5MB
+const partCount = Math.ceil(file.size / PART_SIZE);
+const multipart = await env.MY_BUCKET.createMultipartUpload(key, { httpMetadata: { contentType: file.type } });
+
+const uploadedParts: R2UploadedPart[] = [];
+try {
+  for (let i = 0; i < partCount; i++) {
+    const start = i * PART_SIZE;
+    const part = await multipart.uploadPart(i + 1, file.slice(start, start + PART_SIZE));
+    uploadedParts.push(part);
+    onProgress?.(Math.round(((i + 1) / partCount) * 100));
+  }
+  return await multipart.complete(uploadedParts);
+} catch (error) {
+  await multipart.abort();
+  throw error;
+}
+```
+
+## Batch Delete
+
+```typescript
+async function deletePrefix(prefix: string, env: Env) {
+  let cursor: string | undefined;
+  let truncated = true;
+
+  while (truncated) {
+    const listed = await env.MY_BUCKET.list({ prefix, limit: 1000, cursor });
+    if (listed.objects.length > 0) {
+      await env.MY_BUCKET.delete(listed.objects.map(o => o.key));
+    }
+    truncated = listed.truncated;
+    cursor = listed.cursor;
+  }
+}
+```
+
+## Checksum Validation
+
+```typescript
+const hash = await crypto.subtle.digest('SHA-256', data);
+await env.MY_BUCKET.put(key, data, { sha256: hash });
+
+// Verify on retrieval
+const object = await env.MY_BUCKET.get(key);
+const retrievedHash = await crypto.subtle.digest('SHA-256', await object.arrayBuffer());
+const valid = object.checksums.sha256 && arrayBuffersEqual(retrievedHash, object.checksums.sha256);
+```
+
+## Storage Class Transitions
+
+```typescript
+// Use S3 SDK CopyObject to transition
+const s3 = new S3Client({...});
+await s3.send(new CopyObjectCommand({
+  Bucket: 'my-bucket',
+  Key: key,
+  CopySource: `/my-bucket/${key}`,
+  StorageClass: 'STANDARD_IA'
+}));
+```
+
+## Public Bucket with Custom Domain
+
+```typescript
+export default {
+  async fetch(request: Request, env: Env): Promise<Response> {
+    const key = new URL(request.url).pathname.slice(1);
+    const object = await env.MY_BUCKET.get(key);
+    if (!object) return new Response('Not found', { status: 404 });
+
+    const headers = new Headers();
+    object.writeHttpMetadata(headers);
+    headers.set('etag', object.httpEtag);
+    headers.set('access-control-allow-origin', '*');
+    headers.set('cache-control', 'public, max-age=31536000, immutable');
+
+    return new Response(object.body, { headers });
+  }
+};
+```

package/.codex/skills/cloudflare/references/r2-data-catalog/README.md

@@ -0,0 +1,18 @@
+# Cloudflare R2 Data Catalog Skill Reference
+
+Expert guidance for Cloudflare R2 Data Catalog - Apache Iceberg catalog built into R2 buckets.
+
+## Overview
+
+R2 Data Catalog is a managed Apache Iceberg REST catalog built directly into R2 buckets. It enables analytical workloads like log analytics, BI, and data pipelines with zero egress fees. Curr...
+
+## In This Reference
+
+- **[configuration.md](./configuration.md)** - Setup, deployment, configuration
+- **[api.md](./api.md)** - API endpoints, methods, interfaces
+- **[patterns.md](./patterns.md)** - Common patterns, use cases, examples
+- **[gotchas.md](./gotchas.md)** - Troubleshooting, best practices, limitations
+
+## See Also
+
+- [Cloudflare Docs](https://developers.cloudflare.com/)

package/.codex/skills/cloudflare/references/r2-data-catalog/api.md

@@ -0,0 +1,29 @@
+### API Token Creation
+
+**Dashboard Method (Recommended):**
+1. R2 → Manage API tokens → Create API token
+2. Select **Admin Read & Write** or **Admin Read only**
+   - Includes both R2 Data Catalog + R2 Storage permissions
+3. Copy token value
+
+**API Method (Programmatic):**
+```json
+{
+  "policies": [{
+    "effect": "allow",
+    "resources": {
+      "com.cloudflare.edge.r2.bucket.<account-id>_<jurisdiction>_<bucket-name>": "*"
+    },
+    "permission_groups": [
+      {
+        "id": "d229766a2f7f4d299f20eaa8c9b1fde9",
+        "name": "Workers R2 Data Catalog Write"
+      },
+      {
+        "id": "2efd5506f9c8494dacb1fa10a3e7d5b6",
+        "name": "Workers R2 Storage Bucket Item Write"
+      }
+    ]
+  }]
+}
+```

package/.codex/skills/cloudflare/references/r2-data-catalog/configuration.md

@@ -0,0 +1,39 @@
+## Configuration
+
+### Prerequisites
+- Cloudflare account with R2 subscription
+- R2 bucket created
+- API token with both R2 Storage and R2 Data Catalog permissions
+
+### Enable Catalog on Bucket
+
+**Via Wrangler:**
+```bash
+npx wrangler r2 bucket catalog enable <BUCKET_NAME>
+```
+
+**Via Dashboard:**
+1. Go to R2 → Select bucket → Settings tab
+2. Scroll to "R2 Data Catalog" → Click "Enable"
+3. Note the **Catalog URI** and **Warehouse name**
+
+**Output:**
+- Catalog URI: `https://<account-id>.r2.cloudflarestorage.com/iceberg/<bucket-name>`
+- Warehouse: `<bucket-name>`
+
+### API Token Creation
+
+**Dashboard Method (Recommended):**
+1. R2 → Manage API tokens → Create API token
+2. Select **Admin Read & Write** or **Admin Read only**
+   - Includes both R2 Data Catalog + R2 Storage permissions
+3. Copy token value
+
+**API Method (Programmatic):**
+```json
+{
+  "policies": [{
+    "effect": "allow",
+    "resources": {
+      "com.cloudflare.edge.r2.bucket.<account-id>_<jurisdiction>_<bucket-name>": "*"
+    },

package/.codex/skills/cloudflare/references/r2-data-catalog/gotchas.md

@@ -0,0 +1,20 @@
+## Best Practices
+
+### Authentication & Security
+1. **Use Admin Read & Write tokens** for read/write operations
+2. **Use Admin Read only tokens** for read-only query engines
+3. **Store tokens securely** in environment variables, not code
+4. **Rotate tokens regularly** via dashboard
+5. **Use catalog-level maintenance** with service tokens for automation
+
+### Performance Optimization
+1. **Enable compaction** for all production tables
+2. **Choose appropriate target file sizes**:
+   - Start with 128 MB for most workloads
+   - Tune based on query patterns
+3. **Configure snapshot expiration** to match retention requirements
+4. **Use partitioning** in table schema for large datasets
+5. **Monitor query performance** and adjust compaction settings
+
+### Data Modeling
+1. **Use namespaces** to organiz

package/.codex/skills/cloudflare/references/r2-data-catalog/patterns.md

@@ -0,0 +1,46 @@
+## Common Use Cases
+
+### 1. Log Analytics Pipeline
+
+**Scenario:** Ingest and query application logs
+
+```python
+from pyiceberg.catalog.rest import RestCatalog
+import pyarrow as pa
+import pandas as pd
+
+# Setup catalog
+catalog = RestCatalog(
+    name="logs_catalog",
+    warehouse=WAREHOUSE,
+    uri=CATALOG_URI,
+    token=TOKEN,
+)
+
+catalog.create_namespace_if_not_exists("logs")
+
+# Create schema for logs
+log_schema = pa.schema([
+    ("timestamp", pa.timestamp("ms")),
+    ("level", pa.string()),
+    ("service", pa.string()),
+    ("message", pa.string()),
+    ("user_id", pa.int64()),
+])
+
+# Create table
+logs_table = catalog.create_table(
+    ("logs", "application_logs"),
+    schema=log_schema,
+)
+
+# Append logs incrementally
+log_data = pa.table({
+    "timestamp": [pd.Timestamp.now(), pd.Timestamp.now()],
+    "level": ["ERROR", "INFO"],
+    "service": ["auth-service", "api-gateway"],
+    "message": ["Failed login attempt", "Request processed"],
+    "user_id": [12345, 67890],
+})
+
+logs_table.appen