Borrowing it
Nothing to install: this file belongs to thomwebb/gac. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/thomwebb/gac/main/AGENTS.mdgit clone --depth 1 https://github.com/thomwebb/gacWrote 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/thomwebb/gac/agents-md)<a href="https://agentmods.dev/instructions/thomwebb/gac/agents-md"><img src="https://agentmods.dev/badge/instructions/thomwebb/gac/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/thomwebb/gac/agents-md"><img src="https://agentmods.dev/badge/instructions/thomwebb/gac/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00971 | $0.00971 |
| Opus 5.5 | $0.00388 | $0.00388 |
| Sonnet 5.5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
gac 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 2mo 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GAC — Agent Guidelines
Essential rules for AI coding agents. Detailed reference: load skills from .skills/.
uv run (NON-NEGOTIABLE)
Every Python command must go through uv run:
| Always | Never |
|---|---|
uv run pytest |
pytest |
uv run python script.py |
python script.py |
uv run ruff check . |
ruff check . |
uv run mypy src/ |
mypy src/ |
uv run pip install X |
pip install X |
This project has 35+ AI provider integrations — only uv + uv.lock can resolve the dependency matrix reliably across dev, CI, and production. Vanilla tools will silently break.
For subagents: always include uv run in prompts you generate. Verify compliance before accepting output.
User Data Safety (NON-NEGOTIABLE)
NEVER touch ~/.gac* files during development or testing:
~/.gac/stats.json,~/.gac_stats.json(legacy, auto-migrated)~/.gac.env,~/.gac/oauth/*.json
When testing code that touches stats:
# Use tmp_path + mock the file path
with patch("gac.stats.store.STATS_FILE", tmp_path / "test.json"):
save_stats(data) # safe
# NEVER call reset_stats() / save_stats() without mocking
The session-scoped isolate_stats_file fixture (tests/conftest.py) handles this automatically inside pytest only. Outside pytest, back up first: cp ~/.gac/stats.json{,.bak}.
Accidental data loss is unacceptable.
Commands
make setup # uv venv && uv pip install -e ".[dev]"
make test # uv run -- pytest (excludes integration)
make test-integration # real API calls (needs API keys)
make test-cov # coverage report → htmlcov/index.html
make lint # ruff check + ruff format --check + prettier + markdownlint (4 tools!)
make format # auto-fix all four
make type-check # mypy
Run specific tests:
uv run -- pytest tests/test_cli.py # single file
uv run -- pytest tests/providers/test_openai.py -v # verbose
uv run -- pytest -k "test_parse_response" # by name
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.
- 2mo ago First seen · 91 lines · 971 tokens per session scan A e1748c60ea89
gac AGENTS.md is an instructions file published in the GitHub repository thomwebb/gac (318 stars, last pushed 18d ago), licensed MIT. It adds 971 tokens to every session, about $0.0039 per session on Opus 5.5. 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.
gac AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gac AGENTS.mdthomwebb/gac | Instructions file | 318 | 18d ago | MIT | A | 971 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |