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 skills/fetchercloud/fetcher-cloud/fetchernpx skills add fetchercloud/fetcher-cloud --skill fetchergit clone --depth 1 https://github.com/fetchercloud/fetcher-cloudWhat 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 | $0.00050 | $0.00867 |
| Opus 5 | $0.00025 | $0.00434 |
| Sonnet 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 2d 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.
- 2d 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 4d ago), licensed MIT. It adds 50 tokens to every session and 867 once invoked, about $0.0003 per session on Opus 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.
Other skills, from other repositories
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.