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/nschneir/pet-project/agents-mdgit clone --depth 1 https://github.com/nschneir/PET-ProjectWrote 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/nschneir/pet-project/agents-md)<a href="https://agentmods.dev/instructions/nschneir/pet-project/agents-md"><img src="https://agentmods.dev/badge/instructions/nschneir/pet-project/agents-md.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 | $0.01766 | $0.01766 |
| Opus 5 | $0.00883 | $0.00883 |
| Sonnet 5 | $0.00353 | $0.00353 |
| Haiku 4.5 | $0.00177 | $0.00177 |
Grade A, and why
PET-Project 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 4d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working on this repository's code. (If you
are here to use pet-tools to write PET software, read
skills/pet-development/SKILL.md and docs/cli.md instead.)
What this is
PET Project (package petlib, distributed as pet-tools): an AI-oriented
toolset for developing and debugging Commodore PET software on the VICE
emulator. Two front ends — the pet CLI and the pet-tools-mcp MCP server —
drive the same session machinery.
Where things are documented (don't duplicate them here):
README.md— install, quickstart, supported PET models.docs/agent-setup.md— per-agent setup (CLI and MCP routes), macOS + Linux.docs/cli.md— the full CLI reference (man page), one entry per command.skills/pet-development/+skills/6502-assembly/— PET/6502 domain knowledge: workflows, memory maps, zero page, ROM routines, cookbook.
Commands
pip install -e ".[dev]" # install with pytest + coverage
pytest # full suite (vice-marked tests need xpet/VICE on PATH)
pytest -m "not vice" # unit tests only — no emulator required
pytest tests/test_monitor.py # one file
pytest tests/test_monitor.py::test_name # one test
python -m coverage run -m pytest && python -m coverage combine && python -m coverage report
# coverage (fail_under=90); subprocesses (daemon, MCP stdio) are measured too
ruff check src tests # lint (config in pyproject.toml); must be clean
Tests marked @pytest.mark.vice launch a real VICE emulator (xpet);
everything else runs against tests/fake_vice.py, an in-process fake of the
VICE binary monitor. pet build needs cc65 (ca65/ld65); pet basic
needs petcat; pet disk needs c1541 — all external subprocesses.
Live-test caution: a setup failure inside a vice-marked test can skip
teardown and leak a warp-mode xpet eating a CPU core. Check
pgrep -fl xpet between live runs and kill leftovers. Give live tests
generous timeouts (minutes, not seconds).
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.
- 4d ago First seen · 112 lines · 1,766 tokens per session scan A 91153708b289
PET-Project AGENTS.md is an instructions file published in the GitHub repository nschneir/PET-Project (1 stars, last pushed 11d ago), licensed MIT. It adds 1,766 tokens to every session, about $0.0088 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
Project64 AGENTS.md
AGENTS.md instructions for nschneir/Project64, covering agents.md, what this is, commands, architecture and code quality.
whoop-mcp CLAUDE.md
Claude Code instructions for shashankswe2020-ux/whoop-mcp, covering project: whoop-mcp, tech stack, commands, project structure and code conventions.
whoop-mcp copilot-instructions.md
Copilot instructions for shashankswe2020-ux/whoop-mcp, covering project: whoop-mcp, tech stack, commands, code conventions and testing.
dotbot AGENTS.md
Instructions for andresharpe/dotbot, covering agents.md, project overview, commands, architecture and three core systems.
agent-almanac CLAUDE.md
Claude Code instructions for pjt222/agent-almanac, covering claude.md, project overview, architecture, five content types and registries.
dotbot CLAUDE.md
Instructions for andresharpe/dotbot, a project described as: Structured, auditable AI-assisted development for teams. Zero-dependency MCP server, web dashboard, and multi-provider AI CLI support.