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/milkoor/causetrace/agents-mdgit clone --depth 1 https://github.com/milkoor/causetraceWrote 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/milkoor/causetrace/agents-md)<a href="https://agentmods.dev/instructions/milkoor/causetrace/agents-md"><img src="https://agentmods.dev/badge/instructions/milkoor/causetrace/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 | $0.01245 | $0.01245 |
| Opus 5 | $0.00622 | $0.00622 |
| Sonnet 5 | $0.00249 | $0.00249 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
causetrace 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 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
causetrace/ is the Python package. core.py owns events, storage, validation, and replay; analysis.py implements local topology and pattern metrics; annotation.py stores sidecar labels; cli.py exposes commands. Runtime-specific ingestion belongs in causetrace/hooks/. Tests are in tests/, DAG fixtures are in tests/fixtures/dags/, and the runnable example is demo/run_demo.py. Consult docs/runtime-principles.md and docs/schema/ before changing event semantics.
Build, Test, and Development Commands
pip install -e ".[test]" # Editable install plus pytest
python -m pytest tests/ -v # Run the full test suite
python -m pytest tests/test_invariants.py -v # Check runtime invariants
python -m pytest tests/test_dag_fixtures.py -v # Check DAG analysis behavior
causetrace demo # Exercise the installed first-run path
causetrace doctor # Diagnose local runtime data sources
CI runs python -m pytest tests/ -v on Python 3.10, 3.11, and 3.12. Release builds are maintainer work; follow CONTRIBUTING.md before changing versions or publishing.
Coding Style & Naming Conventions
Target Python 3.10+ and use four-space indentation. Follow existing conventions: snake_case for functions, variables, modules, and test names; PascalCase for classes such as ToolEvent. Prefer explicit type hints on new public helpers and short docstrings where behavior is not obvious. No formatter or linter is configured in pyproject.toml; keep edits consistent with nearby code and avoid unrelated formatting churn.
Testing Guidelines
Tests use pytest and follow the tests/test_*.py pattern. Add parser or hook coverage in the matching module; first-run configuration belongs in tests/test_onboarding.py. Topology changes require DAG-fixture regression tests, including external-parent boundaries where relevant. Analysis is session-local: parents absent from the loaded session do not create graph nodes.
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 · 79 lines · 1,245 tokens per session scan A a26e3d97dbe4
causetrace AGENTS.md is an instructions file published in the GitHub repository milkoor/causetrace (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,245 tokens to every session, about $0.0062 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
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).