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/sbischoff-ai/pygase/agents-mdgit clone --depth 1 https://github.com/sbischoff-ai/pygaseWrote 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/sbischoff-ai/pygase/agents-md)<a href="https://agentmods.dev/instructions/sbischoff-ai/pygase/agents-md"><img src="https://agentmods.dev/badge/instructions/sbischoff-ai/pygase/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 5.1 | $0.01067 | $0.01067 |
| Opus 5 | $0.00534 | $0.00534 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
pygase 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 6d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Architecture map (quick orientation)
pygase/connection.py: protocol and transport core. Defines package/header serialization, sequence/ack tracking, connection status, and client/server connection classes that send and receive UDP datagrams.pygase/backend.py: server-side orchestration layer. Wraps lower-level connection behavior with backend lifecycle management, event dispatch wiring, and game loop integration.pygase/client.py: client-facing API. Manages connecting/disconnecting to a backend, event exchange, and synchronized state consumption for game/application code.pygase/gamestate.py: authoritative state model and update mechanics. Defines game state containers, ordered updates, and merge/apply behavior used by both client and backend flows.
Canonical uv commands
- Setup (dev env + editable install):
uv sync
- Format:
uv run black pygase tests
- Type-check:
uv run mypy pygase
- Lint/docstyle:
uv run pylint --fail-under=9.9 pygaseuv run pydocstyle pygase
- Targeted tests (single file or subset):
uv run pytest -m "not integration" tests/connection_test.pyuv run pytest -m "not integration" tests -k connection
- Quick default test pass (fast feedback):
uv run pytest -m "not integration" tests
- Integration tests only:
uv run pytest -m integration tests
- Full tests (match CI intent):
uv run pytest tests --doctest-modules --cov=pygase --cov-report=term-missing
Fast path vs full validation
- Fast path (small, local edits that do not affect protocol, networking, or cross-module behavior):
uv run black pygase testsuv run pytest -m "not integration" tests/<affected_module>_test.pyuv run mypy pygase(required before finishing any task)
- Full validation (required for protocol/network behavior edits, connection timing/ordering changes, or broad refactors):
uv run black pygase testsuv run pytest tests --doctest-modules --cov=pygase --cov-report=term-missinguv run mypy pygaseuv run pylint --fail-under=9.9 pygaseuv run pydocstyle pygase
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.
- 6d ago First seen · 72 lines · 1,067 tokens per session scan A 353e944f0b1f
pygase AGENTS.md is an instructions file published in the GitHub repository sbischoff-ai/pygase (47 stars, last pushed 3mo ago), licensed MIT. It adds 1,067 tokens to every session, about $0.0053 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
GameDesignOS AGENTS.md
Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.
moorestech AGENTS.md
AGENTS.md instructions for moorestech/moorestech, covering コーディングの指針, qa（必須）, 互換性とパフォーマンス, 既知の制約（設計上の割り切り） and regionの活用.
turn-based-game-mcp shared-library.instructions.md
Shared library development patterns for the turn-based games platform.
turn-based-game-mcp copilot-instructions.md
Copilot instructions for chrisreddington/turn-based-game-mcp, covering turn-based games platform, purpose, repository structure, code standards and required before each commit.
summer-engine-agent AGENTS.md
AGENTS.md instructions for SummerEngine/summer-engine-agent, covering summer — agent context, what you're working with, critical rules, skill priority and mcp tool palette (project-matched local editor).
everything-game-dev-code copilot-instructions.md
Copilot instructions for MRCalderon3D/everything-game-dev-code, covering github copilot repository instructions, repository intent, how to navigate the repository, working rules and repository maintenance.