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/cs0lar/treelang/agents-mdgit clone --depth 1 https://github.com/cs0lar/treelangWhat 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 | $0.03898 | $0.03898 |
| Opus 5 | $0.01949 | $0.01949 |
| Sonnet 5 | $0.00780 | $0.00780 |
| Haiku 4.5 | $0.00390 | $0.00390 |
Grade A, and why
treelang 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 2d 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 — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
treelang/ contains the library. AST models and evaluation behavior live under
treelang/trees/, while providers, prompts, selection, and memory integrations
live under treelang/ai/. Unit tests mirror the package beneath tests/; tree
tests are split across tests/trees/test_ast.py, test_nodes.py, and
test_tool.py. Use cookbook/ for runnable examples and notebooks.
evaluation/ contains the regression harness, curated
questions, and evaluation tools. Package metadata and dependencies are declared
in pyproject.toml and locked in uv.lock.
Build, Test, and Development Commands
uv sync --frozen --all-groups: install the exact locked development environment.make check: run linting, type checks, tests with coverage, and package builds.uv run pytest: run the complete test suite.make format: apply Ruff lint fixes and formatting.uv run python evaluation/eval.py: run the deterministic offline benchmark and compare it with the committed baseline; this requires no credentials or network access.
Python 3.12 or newer is required. Run cookbook scripts with uv, for example
uv run python cookbook/calculator.py.
Coding Style & Naming Conventions
Use four-space indentation and Ruff's formatter. Follow standard Python naming:
snake_case for functions, variables, and modules; PascalCase for classes;
and UPPER_CASE for constants. Add type annotations to public interfaces and
async functions where practical. Keep schema changes in treelang/trees/schemas/
and provider-specific behavior in treelang/ai/; avoid mixing those concerns.
Testing Guidelines
Tests run with pytest; existing cases use unittest.IsolatedAsyncioTestCase
and AsyncMock for asynchronous behavior.
Name files test_*.py, classes Test*, and methods test_*. Add focused tests
for success paths, validation failures, and async provider interactions. The
current branch-coverage floor is 60%; raise it only with corresponding tests.
Every behavior change should include a regression test. Run the full suite before
opening a pull request.
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.
- 2d ago First seen · 375 lines · 3,898 tokens per session scan A bedfdc49a629
treelang AGENTS.md is an instructions file published in the GitHub repository cs0lar/treelang (5 stars, last pushed 5d ago), licensed MIT. It adds 3,898 tokens to every session, about $0.0195 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
task-agents-playbook AGENTS.md
AI-Assisted Development Playbook & Task-driven development methodology for AI-agents.
cctop AGENTS.md
Instructions for st0012/cctop, covering agents.md - development guide for cctop, scope and sources, required development rules, driver workflow and github and pr rules.
toh-framework CLAUDE.md
Instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
examples CLAUDE.md
Claude Code instructions for rossoctl/examples, covering claude.md - agent examples, repository structure, key commands, code style and dco sign-off (mandatory).
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
claude-code-templates CLAUDE.md
Instructions for Justdvp/claude-code-templates, covering claude.md, project overview, development commands, package management and application commands.