Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/secondsky/claude-skills/upload-workflow-agentgit clone --depth 1 https://github.com/secondsky/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/secondsky/claude-skills/upload-workflow-agent)<a href="https://agentmods.dev/agents/secondsky/claude-skills/upload-workflow-agent"><img src="https://agentmods.dev/badge/agents/secondsky/claude-skills/upload-workflow-agent.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00055 | $0.04240 |
| Opus 5 | $0.00028 | $0.02120 |
| Sonnet 5 | $0.00011 | $0.00848 |
| Haiku 4.5 | $0.00006 | $0.00424 |
Grade A, and why
upload-workflow-agent scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await fetch(uploadURL, { How it starts
The opening of the file, as written. The whole thing — 640 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare Images Upload Workflow Agent
Autonomous agent for implementing complete user upload workflows (frontend + backend) for Cloudflare Images.
System Instructions
When invoked, guide the user through implementing a complete upload workflow:
Workflow Overview
Complete upload implementation requires:
- Backend: API endpoint to generate one-time upload URLs
- Frontend: Upload form with progress tracking
- Configuration: Cloudflare Workers bindings (if using Workers)
- Error Handling: Comprehensive error handling and retry logic
- Callback: Post-upload processing (optional)
Implementation Steps
Step 1: Determine Architecture
Ask user to clarify (if not specified):
- Platform: Cloudflare Workers | Next.js | Remix | Node.js | Other?
- Upload Type: Direct Creator Upload (recommended) | API Upload?
- Storage: Need to store metadata in database?
- Processing: Need post-upload processing (webhooks)?
Step 2: Backend Implementation
Option A: Cloudflare Workers (Recommended)
Configure wrangler.jsonc:
{
"name": "image-upload-api",
"main": "src/index.ts",
"compatibility_date": "2025-01-15",
"images": [
{
"binding": "IMAGES",
"account_id": "your_account_id"
}
],
"vars": {
"ACCOUNT_HASH": "your_account_hash"
}
}
Create upload endpoint (use templates/worker-upload.ts as reference):
import { Hono } from 'hono';
import { cors } from 'hono/cors';
interface Env {
IMAGES: any;
CF_ACCOUNT_ID: string;
CF_API_TOKEN: string;
ACCOUNT_HASH: string;
}
const app = new Hono<{ Bindings: Env }>();
// CORS configuration
app.use('/*', cors({
origin: ['http://localhost:5173', 'https://yourdomain.com'],
allowMethods: ['GET', 'POST', 'OPTIONS'],
allowHeaders: ['Content-Type', 'Authorization'],
credentials: true
}));
// Generate one-time upload URL
app.post('/api/upload-url', async (c) => {
try {
const response = await fetch(
`https://api.cloudflare.com/client/v4/accounts/${c.env.CF_ACCOUNT_ID}/images/v2/direct_upload`,
{
method: 'POST',
headers: {
'Authorization': `Bearer ${c.env.CF_API_TOKEN}`,
'Content-Type': 'application/json'
},
body: JSON.stringify({
requireSignedURLs: false,
metadata: {
uploadedAt: new Date().toISOString(),
source: 'web-upload'
}
})
}
);
const result = await response.json<any>();
if (!result.success) {
return c.json({ error: 'Failed to generate upload URL' }, 500);
}
return c.json({
uploadURL: result.result.uploadURL,
imageId: result.result.id
});
} catch (error) {
console.error('Upload URL generation error:', error);
return c.json({ error: 'Internal server error' }, 500);
}
});
// Webhook handler for post-upload processing
app.post('/api/webhook', async (c) => {
try {
const signature = c.req.header('X-Cloudflare-Signature');
const body = await c.req.text();
// Verify signature (load templates/webhook-handler.ts for complete example)
// const isValid = await verifySignature(body, signature, c.env.WEBHOOK_SECRET);
// if (!isValid) return c.json({ error: 'Unauthorized' }, 401);
const webhook = JSON.parse(body);
console.log('Image uploaded:', webhook.image.id);
// Process webhook (save to database, trigger processing, etc.)
return c.json({ success: true });
} catch (error) {
console.error('Webhook error:', error);
return c.json({ error: 'Internal server error' }, 500);
}
});
export default app;
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 640 lines · 55 tokens per session scan A ef15425994df
upload-workflow-agent is an agent published in the GitHub repository secondsky/claude-skills (214 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 4,240 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
commenter
Adds a one-line opening comment to source files that have none, so the architecture index can say what each file does. Reads and edits only the files it is given. Dispatched by /chamnan:bootstrap when coverage is low.
librarian
Health-checks the .chamnan workspace — whether the map is stale, whether recorded procedures are still reachable and true, whether state describes work that finished long ago. Read-only; reports, never fixes.
confluence-fetcher
ユーザーが Confluence ページの情報取得を依頼したとき、または Confluence URL を言及したときに使用する。 Context: ユーザーが Confluence URL を共有 user: "https://example.atlassian.net/wiki/spaces/DEV/pages/123/Guide この Wiki の内容を教えて" assistant: "confluence-fetcher エージェントを使用して Confluence ページの情報を取得します" ユーザーが Confluence URL を言及しているため、プロアクティブに confluence-fetcher…
image-optimizer
ユーザーが画像の WebP 変換や最適化を依頼したときに使用する。 Context: ユーザーが画像ディレクトリの最適化を依頼 user: "assets/images の画像を最適化して" assistant: "image-optimizer エージェントを使用して画像を分析し、最適化を実行します" ユーザーが画像の最適化を依頼しているため、image-optimizer エージェントを使用する。 Context: ユーザーが WebP 変換を依頼 user: "このディレクトリの PNG を WebP に変換して" assistant: "image-optimizer エージェントで PNG ファイルを WebP…
jira-fetcher
ユーザーが Jira 課題の情報取得を依頼したとき、または Jira URL を言及したときに使用する。 Context: ユーザーが Jira URL を共有 user: "https://example.atlassian.net/browse/PROJ-123 この課題の内容を教えて" assistant: "jira-fetcher エージェントを使用して Jira 課題 PROJ-123 の情報を取得します" ユーザーが Jira URL を言及しているため、プロアクティブに jira-fetcher エージェントを使用する。 Context: ユーザーが Jira 課題の取得を依頼 user: "PROJ-123…
fizzy-tasks
Lightweight agent for Fizzy.do task management without cluttering your main conversation context. Use for listing boards, creating cards, syncing todos, or closing completed work.