Fasthands — AI skill for Claude Code
Open-source, model-agnostic computer use: diff observations, guarded action batching, and xray — the HTML contract every agent ignores.
How to install Fasthands
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open anzal1/fasthands and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Fasthands does
Open-source, model-agnostic computer use: diff observations, guarded action batching, and xray — the HTML contract every agent ignores. 91% fewer tokens than a screenshot loop, benchmarked and reproducible keyless.
Alternatives in AI
- Vllm Mlx — High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon 1.5k ★
- Claude Skill Aso Appstore Screenshots — A Claude Code skill that generates high-converting App Store screenshots for your iOS app 1.2k ★
- Ppt Agent Skill — 🎨 World-class AI presentation generator · 26 styles · 18 charts · benchmarked against Linear/Anthropic/Stripe 139 ★
README
fasthands
**Open-source, model-agnostic computer use. Same task, fewer tokens, fewer turns, with any model as the brain, including a 4B running on your laptop.**
Computer-use agents today come in two flavors. Anthropic's reference loop sends a screenshot every turn (about 1,366 image tokens at 1280x800) and takes one action per turn. OpenAI's GPT-6 Astra loop is smarter: accessibility trees and code actions, but it resends a fresh full tree every turn, it is closed, and it runs one company's models. Its own write-up admits stale trees and state drift between observing and acting as open failure modes.
fasthands attacks the loop, not the model. Every claim below is measured, reproducible with zero API keys, and reported with its caveats.
The claims, and where each one is proven
| # | Claim | Evidence | Reproduce |
|---|---|---|---|
| 1 | 91.3% fewer observation tokens than a screenshot loop, 61.2% fewer than an Astra-style full-tree loop | Proof 1, 120 runs | npm run bench -- --repeat 5 |
| 2 | Blind batching misclicks catastrophically under DOM drift; guarded batching never does | Proof 2, 40 trials: 0% vs 100% | node --experimental-strip-types src/bench/drift-test.ts |
| 3 | Diff observations stay flat while every other strategy grows with page size | Proof 3, 38 tokens vs 92,732 at N=2000 | node --experimental-strip-types src/bench/scale-test.ts |
| 4 | Reading the HTML contract (xray) removes whole turns of error recovery | Proof 4, signup trap: 2 turns vs 3 to 8 | included in the bench |
| 5 | The harness carries a real 4B local model through real tasks | Proof 5, 46% fewer live tokens, trap flips fail to pass | --provider compat --review |
| 6 | Canvas, WebGL and drawing are first-class: observe below the DOM, act in stro |
Related Skills
Settled Computer
Fast computer use for AI agents: event-driven settling MCP server - replaces time.sleep between clicks, waits
Operance
Local-first AI desktop action layer for controlling your computer with natural language.
Commit Claude Config
Version the Solana AI Kit config in git (un-ignores .claude/, CLAUDE.md, .mcp.json, .gitmodules and commits th
Claude Image
教 Claude Code/Codex 真正用好 gpt-image-2 的 skill 包 · Drop-in skill teaching agents to actually use GPT Image 2 — i
AI Trading MCP
MCP-driven crypto trading rig: Claude (or any MCP client) trades a live portfolio through three guarded tools:
Claude Token Stack
Accuracy-guarded token-efficiency stack for Claude Code on Windows & the Claude desktop app: code graph, conte
Related Agents
Part 19: Repowise — Codebase Intelligence For Coding Agents
60% fewer tokens. 4x faster. Your coding agents stop guessing and start knowing. ---
Lean Reader
Read-only reader, collector, or verifier stage that runs without CLAUDE.md and the memory index (18.8k fewer t
UI Explorer
Drive and explore a native macOS app's GUI (screenshot → click/type → observe) and correlate each action with