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/basler/pypylon/agents-mdgit clone --depth 1 https://github.com/basler/pypylonWhat 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 | $0.01195 | $0.01195 |
| Opus 5 | $0.00598 | $0.00598 |
| Sonnet 5 | $0.00239 | $0.00239 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
pypylon 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 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Development guide for contributors and automated assistants working in this repository. pypylon is the official Python wrapper for the Basler pylon Camera Software Suite, built with SWIG on top of the pylon C++ SDK. See README.md for the project overview, installation, and quick-start examples.
Repository map
| Path | Contents |
|---|---|
src/ |
SWIG interface (.i) files — the binding definitions for genicam, pylon, pylondataprocessing. |
pypylon/ |
Generated/packaged Python modules (build output; not edited by hand). |
generated/ |
SWIG-generated C++/Python (build output). |
samples/ |
Example scripts under pylon/ and pylondataprocessing/ (one folder per sample, <name>/<name>.py); shared helper modules in common/; shared image/data assets in images/. See context/sample_style.md for layout and naming. |
samples_reference_pypylon/ |
Reference ports of the C++ pylon samples. |
tests/ |
Unit tests: genicam/, pylon/{emulated,usb,gigE}/, pylondataprocessing/. Entry point: tests/all_tests.py. |
scripts/ |
Build/format helper scripts. |
context/ |
Coding-style reference docs (see below). |
setup.py, pyproject.toml |
Build configuration. |
Environment
Run all project Python commands inside the Python environment where pypylon is built/installed, so they use the correct interpreter and the matching pylon SDK. This file intentionally does not prescribe a specific environment manager (venv, conda, uv, …) — activate whichever one you use before running commands.
Building from source additionally requires an installed pylon SDK, a C++ compiler, Python development headers, and SWIG 4.3 (see README.md).
Common commands
Build and install for local development:
pip install -e .
# or, to (re)build in place after changing bindings:
python setup.py build
Run the tests the way CI does — pytest over the hardware-free
(Camera Emulation) suites:
pip install pytest numpy
pytest tests/genicam tests/pylon/emulated tests/pylondataprocessing
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 · 105 lines · 1,195 tokens per session scan A 18d11dee79ef
pypylon AGENTS.md is an instructions file published in the GitHub repository basler/pypylon (710 stars, last pushed 20d ago), licensed BSD-3-Clause. It adds 1,195 tokens to every session, about $0.0060 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 2026-08-30.
Other instructions, from other repositories
ai-engineering-from-scratch AGENTS.md
Instructions for rohitg00/ai-engineering-from-scratch, covering agents.md, philosophy, repo layout, hard rules and dependencies.
pixeltable AGENTS.md
AGENTS.md instructions for pixeltable/pixeltable, covering agents.md, protected configuration, project overview, repository structure and setup commands.
pixeltable CLAUDE.md
Claude Code instructions for pixeltable/pixeltable, covering claude.md, protected configuration, project overview, repository structure and setup commands.
HomeAssistant-Tapo-Control AGENTS.md
Instructions for JurajNyiri/HomeAssistant-Tapo-Control, covering agent instructions, required user agreement, repository rules and commits and prs.
HomeAssistant-Tapo-Control copilot-instructions.md
Instructions for JurajNyiri/HomeAssistant-Tapo-Control: Follow AGENTS.md and CONTRIBUTING.md for this repository.
watch-skill AGENTS.md
Instructions for oxbshw/watch-skill, covering working on watch skill, what this project is, layout, commands and rules that are not negotiable.