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/josverl/micropython-stubs/copilot-instructionsgit clone --depth 1 https://github.com/Josverl/micropython-stubsWrote 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/instructions/josverl/micropython-stubs/copilot-instructions)<a href="https://agentmods.dev/instructions/josverl/micropython-stubs/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/josverl/micropython-stubs/copilot-instructions.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 | $0.02704 | $0.02704 |
| Opus 5 | $0.01352 | $0.01352 |
| Sonnet 5 | $0.00541 | $0.00541 |
| Haiku 4.5 | $0.00270 | $0.00270 |
Grade A, and why
micropython-stubs copilot-instructions.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 today.
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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MicroPython-Stubs Repository Guide
Project Overview
This repository mostly contains type stubs, not executable code.
It hosts 3,000+ stub files (.pyi) for MicroPython across multiple versions (v1.17-v1.27), ports (esp32, rp2, stm32, etc.), and boards. These stubs enable IDE autocomplete, type checking, and documentation for MicroPython development.
Sister Repository: micropython-stubber - CLI tool (stubber) that generates these stubs.
Repository Structure
stubs/ # Generated stub files (MCU, frozen, doc, merged)
publish/ # Ready-to-install PyPI packages
micropython-v1_XX_X-{port}-{board}-stubs/
micropython-stdlib-stubs/
tools/ # Tooling (board_compare)
scripts/ # Analysis scripts and notebooks
docs/ # Sphinx documentation source
data/ # JSON database files (stub-packages.json)
tests/quality_tests/ # Pytest-based stub quality tests
Key Concepts
Stub Types (Half-Products)
- MCU stubs: Generated on-device, precise but minimal type info (
stubs/micropython-{version}-{port}[-{board}]) - Frozen stubs: From manifest files, includes frozen modules (
stubs/micropython-{version}-Frozen/{port}/{board}) - Doc stubs: Parsed from MicroPython
.rstdocs, rich typing (stubs/micropython-{version}-docstubs) - Merged stubs: MCU + Doc, precise + rich (
stubs/micropython-{version}-{port}-merged) - Core stubs: Manual overrides for problematic modules (
stubs/micropython-core)
Naming Convention
micropython-{flat_version}-{port}-{board}-stubs where flat_version uses underscores (e.g., v1_24_1).
Development Workflows
Platform Notes
- Primary: Windows
- Secondary: Linux
- CI/CD :GitHub Actions workflows use Ubuntu
Database
data/all_packages.db
The project uses a SQLite database (package_data.db) to store metadata about packages
and project hashes to detect if a package has changed since it was last published.
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.
- today First seen · 270 lines · 2,704 tokens per session scan A a10c6ab37143
micropython-stubs copilot-instructions.md is an instructions file published in the GitHub repository Josverl/micropython-stubs (317 stars, last pushed today), licensed MIT. It adds 2,704 tokens to every session, about $0.0135 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 2026-09-04.
Other instructions, from other repositories
pypylon AGENTS.md
Instructions for basler/pypylon, covering agents.md, repository map, environment, common commands and or, to (re)build in place after changing bindings.
robots AGENTS.md
AGENTS.md instructions for strands-labs/robots, covering agents.md - strands-labs/robots, project dashboard, repository structure, development and install with all optional deps.
uiprotect AGENTS.md
AGENTS.md instructions for uilibs/uiprotect, covering notes for llm contributors, what this project is, code style, commit / pr conventions and running tests.
iaqualink-py CLAUDE.md
Claude Code instructions for flz/iaqualink-py, covering claude.md, confidentiality, project overview, development commands and architecture.
pymobiledevice3 CLAUDE.md
Claude Code instructions for doronz88/pymobiledevice3, a project described as: Pure python3 implementation for working with iDevices (iPhone, etc...).
typemux-cc AGENTS.md
AGENTS.md instructions for K-dash/typemux-cc, covering agent instructions, landing the plane (session completion), build & quality, required: run before completing any work and individual commands.