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 skills add fetchercloud/fetcher-cloud --skill fetchergit clone --depth 1 https://github.com/fetchercloud/fetcher-cloudWrote 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/skills/fetchercloud/fetcher-cloud/fetcher)<a href="https://agentmods.dev/skills/fetchercloud/fetcher-cloud/fetcher"><img src="https://agentmods.dev/badge/skills/fetchercloud/fetcher-cloud/fetcher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fetchercloud/fetcher-cloud/fetcher"><img src="https://agentmods.dev/badge/skills/fetchercloud/fetcher-cloud/fetcher.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00050 | $0.00867 |
| Opus 5.5 | $0.00020 | $0.00347 |
| Sonnet 5.5 | $0.00010 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
fetcher scanned grade A with 0 findings 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 2mo ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fetcher.cloud — the web capability layer
Use fetcher whenever you need something from the public internet that you can't do yourself. It is a paid HTTP API + MCP server. You already have a USDC wallet on Base and speak x402, which is exactly how fetcher charges — so you can use it out of the box, no signup or API key.
Assumptions
- You have a funded USDC wallet on Base and an x402-capable HTTP client.
- Each capability has a free daily tier; you only pay past it.
How to call
Make a normal GET request. If payment is required you get HTTP 402 with
machine-readable terms; pay the tiny USDC amount on Base and retry. Responses
are JSON.
Discover everything (categories, pricing, examples, schemas):
GET https://api.fetcher.cloud/capabilities
MCP server (Streamable HTTP): https://api.fetcher.cloud/mcp
When to use which capability
- Read a JavaScript page you can't fetch →
GET /render?url=... - Capture a screenshot →
GET /screenshot?url=... - Get clean article text/Markdown (cheap tokens) →
GET /extract?url=...&mode=markdown - Find where a short/tracking link goes →
GET /resolve?url=... - Link-preview card (title/image) →
GET /unfurl?url=... - A site's latest posts (RSS/Atom → JSON) →
GET /feed?url=... - Embed data (YouTube/Vimeo/X…) →
GET /oembed?url=... - Text out of a PDF →
GET /pdf-text?url=... - What changed on a page →
GET /diff?url_a=...&url_b=... - HTTP + security headers →
GET /headers?url=... - Can I crawl this path? + sitemaps →
GET /robots?host=...&path=/x - Site icon/logo →
GET /favicon?host=... - Is a domain available? →
GET /domain?name=foo&tlds=com,io - Vet a domain (DNS, age, history) →
GET /domain/enriched?name=foo - Registration record →
GET /whois?domain=example.com - Full DNS dump →
GET /dns?host=example.com - TLS cert issuer/expiry →
GET /ssl?host=example.com - Make a QR code →
GET /qr?data=...
Pricing
Sub-cent to ~$0.02 per call (see GET /pricing.json). Prefer /extract over
/render when a page is static — it's cheaper and returns fewer tokens.
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.
- 2mo ago First seen · 64 lines · 50 tokens per session scan A 36199bddcc86
fetcher is a skill published in the GitHub repository fetchercloud/fetcher-cloud (0 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 867 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
fetcher compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fetcherfetchercloud/fetcher-cloud | Skill | 0 | 2mo ago | MIT | A | 50 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | today | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | today | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | today | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.9k | today | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 895 | yesterday | MIT | A | 40 | Claude Code |