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/lesleslie/jinja2-async-environment/agents-mdgit clone --depth 1 https://github.com/lesleslie/jinja2-async-environmentWrote 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/lesleslie/jinja2-async-environment/agents-md)<a href="https://agentmods.dev/instructions/lesleslie/jinja2-async-environment/agents-md"><img src="https://agentmods.dev/badge/instructions/lesleslie/jinja2-async-environment/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 | $0.00557 | $0.00557 |
| Opus 5 | $0.00279 | $0.00279 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
jinja2-async-environment 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 yesterday.
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 — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
jinja2_async_environment/ contains the async environment, loaders, compiler modules, and caching utilities; review environment.py first, then dive into loaders/, compiler_modules/, and caching/ when touching specialization. Tests live in tests/, mirroring package layout with test_*.py files and marker-specific suites. Documentation, changelogs, and benchmarking notes sit in docs/ and topical *.md files at the root. Build artifacts land in dist/; avoid editing generated content directly.
Build, Test & Development Commands
Use UV for dependency management: uv sync bootstraps the virtualenv defined by uv.lock. Run the holistic quality gate with python -m crackerjack -t --ai-agent before sharing changes—it executes lint, type-check, and test bundles. Individual tools remain available: ruff format enforces the 88-character formatter, ruff check handles linting, and pyright runs strict type analysis. Execute pytest (or pytest -m unit / pytest -m integration) for targeted runs; append --cov=jinja2_async_environment when asserting coverage locally.
Coding Style & Naming Conventions
Code targets Python 3.13+ with standard four-space indentation and exhaustive type hints. Follow snake_case for functions, async coroutines, and module names; prefer PascalCase for classes and TypedDicts. Keep async APIs truly non-blocking—wrap sync fallbacks in thread pools when necessary. Let ruff autofix trivial issues, and keep imports sorted per the configured isort profile (no blank line before first-party imports).
Testing Guidelines
Pytest discovers files named test_*.py or *_test.py; align helper modules under the same patterns when practical. Mark tests with @pytest.mark.unit, @pytest.mark.integration, or @pytest.mark.benchmark to integrate with existing selection flags. The default run enforces coverage via --cov-fail-under=83; do not regress this threshold. Prefer async fixtures and the asyncio event loop provided by pytest-asyncio instead of manual loop management.
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.
- yesterday First seen · 22 lines · 557 tokens per session scan A 225851392fbb
jinja2-async-environment AGENTS.md is an instructions file published in the GitHub repository lesleslie/jinja2-async-environment (6 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 557 tokens to every session, about $0.0028 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 2026-09-04.
Other instructions, from other repositories
Test Generation
Comprehensive Pytest conventions, mocking strategies, and model usage rules for OpenWebUI plugins.
libthumbor AGENTS.md
AGENTS.md instructions for thumbor/libthumbor, covering agents.md, dev environment setup, running tests, code style and project structure.
ai-agents testing.instructions.md
Instructions for rjmurillo/ai-agents, covering test file rules, must, should, must not and references.
ChainWeaver tests.instructions.md
Instructions for dgenio/ChainWeaver, covering tests, file boundary, framework rules and organization.
fusil CLAUDE.md
Claude Code instructions for devdanzin/fusil, covering claude.md, what this project is, environment & dependencies, commands and tests use unittest, not pytest (pytest is not installed).
python-ai-guardrails-template CLAUDE.md
Instructions for tortastudios/python-ai-guardrails-template, covering claude code — quality contract, how the quality gate works, fixing failures, critical functions and code style rules.