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 instructions/pattssun/handcontrol/agents-mdgit clone --depth 1 https://github.com/pattssun/handcontrolWhat 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 | $0.00563 | $0.00563 |
| Opus 5 | $0.00282 | $0.00282 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
handcontrol AGENTS.md 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 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.
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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents (and humans) working in this repo. Read this before adding code.
What this repo is
handcontrol is a collection of self-contained hand-tracking demos. Each demo lives in projects/<name>/ and uses MediaPipe HandLandmarker + OpenCV. Viewers come from social media with mixed experience — every project must run with pip install -r requirements.txt and a single python -m ... command.
Layout
core/ Shared library — Camera, HandTracker, overlay helpers. Import from here.
models/ MediaPipe .task files. Committed.
projects/ Each subfolder is one demo. Self-contained otherwise.
Rules for adding a new project
- Reuse
core/first. Before writing webcam capture, MediaPipe setup, FPS counters, or skeleton drawing — checkcore/. If something close exists, use it. If something is missing and would be useful to other projects, add it tocore/(with a docstring) instead of duplicating in your project. - One folder per project. Create
projects/<snake_case_name>/with at minimummain.pyandREADME.md. - Run command is
python -m projects.<name>.mainfrom repo root. This is what the project README documents and what gets added to the gallery in the root README. - Per-project
requirements.txtonly if you need extras beyond root deps. If you need it, document it in the project README. - Add a gallery entry to the root README.md when the project is ready to show.
- No new top-level folders without updating this file.
Project README template
# <project_name>
One-sentence description of what this demo does.
## Run
```bash
python -m projects.<project_name>.main
Controls
q/ESC— quit- ...
## Style
- Python 3.11. Pinned deps in root `requirements.txt`.
- Type hints where they help, not everywhere.
- No comments explaining *what* obvious code does. Comments only for *why* a non-obvious choice was made.
- Keep `main.py` readable end-to-end. If it grows past ~150 lines, split into modules inside the project folder.
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 · 57 lines · 563 tokens per session scan A 5e081d5300d9
handcontrol AGENTS.md is an instructions file published in the GitHub repository pattssun/handcontrol (2 stars, last pushed 3mo ago), licensed MIT. It adds 563 tokens to every session, about $0.0028 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.