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.
git clone --depth 1 https://github.com/Jott2121/agent-gateWrote 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/rules/jott2121/agent-gate/10-python)<a href="https://agentmods.dev/rules/jott2121/agent-gate/10-python"><img src="https://agentmods.dev/badge/rules/jott2121/agent-gate/10-python/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/rules/jott2121/agent-gate/10-python"><img src="https://agentmods.dev/badge/rules/jott2121/agent-gate/10-python.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 | $0.00000 | $0.00236 |
| Opus 5.5 | $0.00000 | $0.00094 |
| Sonnet 5.5 | $0.00000 | $0.00047 |
| Haiku 4.5 | $0.00000 | $0.00024 |
Grade A, and why
10-python 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.
What it actually says
Python
- Target Python 3.11+ (
requires-pythonin pyproject.toml). CI runs 3.11, 3.12, and 3.13. agent_gate/gate.pyandagent_gate/ledger.pystay stdlib-only. The only runtime dependency ismcp, and it stays inagent_gate/server.py.- A new runtime dependency needs a one-line justification in the PR and a pinned lower bound in pyproject.
- Type hints on all public functions;
from __future__ import annotationswhere useful. - No bare
except:; noexcept Exception: passin any decision path. Raise specific exceptions. - Deterministic by default: seed every RNG, sort dict/set iteration before hashing or printing, freeze timestamps in tests. Ledger hashes include the timestamp, so tests pass a frozen clock.
- Secrets via
os.environonly; never log secret values. - Use
pathlib; no hard-coded absolute paths (no/Users/...).
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 · 16 lines · 0 tokens per session scan A 680a08895724
10-python is a cursor rule published in the GitHub repository Jott2121/agent-gate (3 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 236 tokens. 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 2026-10-12.
Other cursor rules, from other repositories
python-conventions
Python coding conventions for the Dingo SDK.
02-python-standards
Python coding standards, libraries, and concurrency safety.
python-best-practices
Guidelines for professional Python development, including Pydantic v2, Python 3.13 typing, Ruff and testing.
python
You are an AI assistant specialized in Python development. Your approach emphasizes.
backend-python
Cursor rule "backend-python" from coeusyk/inference-x, covering backend python rules, stack assumptions, code style, fastapi conventions and schema conventions.
react-vite-tanstack
You are an expert in TypeScript, Node.js, React, Vite, Yarn ,TanStack Query, TanStack Router, Tanstack table, Tanstack form ,Shadcn elements and Tailwind.