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/railtownai/railtracks/agents-mdgit clone --depth 1 https://github.com/RailtownAI/railtracksWrote 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/railtownai/railtracks/agents-md)<a href="https://agentmods.dev/instructions/railtownai/railtracks/agents-md"><img src="https://agentmods.dev/badge/instructions/railtownai/railtracks/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 | $0.02434 | $0.02434 |
| Opus 5 | $0.01217 | $0.01217 |
| Sonnet 5 | $0.00487 | $0.00487 |
| Haiku 4.5 | $0.00243 | $0.00243 |
Grade A, and why
railtracks 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Overview
Railtracks (rt) is a Python framework for building agentic systems: agents, tools, and multi-step flows
defined entirely in standard Python (no YAML/DSLs). This is a uv workspace monorepo:
Root
├── packages/railtracks/ # The actual "railtracks" PyPI package
│ ├── pyproject.toml # Package dependencies (add new deps here, in optional-dependencies for extras)
│ ├── src/railtracks/ # Source (module is railtracks, package dir uses underscore)
│ └── tests/ # unit_tests/, integration_tests/, end_to_end/, llm_live_tests/
├── pyproject.toml # Root workspace: dev-tooling deps only (docs/test/lint groups), NOT package deps
├── docs/ # mkdocs documentation source
├── examples/ # Example scripts
└── scripts/ # CI helper scripts (dependency sorting, license checks, docs validation)
Accessing docs
Full documentation lives at https://docs.railtracks.org/ (works even if this file is read standalone,
without the repo). Locally, the source is under docs/documentation/ and docs/observability/; preview
with mkdocs serve (see Common Commands below). Doc URLs mirror the source path, e.g.
docs/documentation/invocation/flows.md -> https://docs.railtracks.org/documentation/invocation/flows/.
Setup
uv sync --group dev
uv pip install -e "packages/railtracks[all]" # or a specific extra, e.g. [visual], [retrieval]
Common Commands
# Lint / format (must pass before commit, CI enforces this)
ruff check --fix
ruff format
# Unit tests only (fast, ~10s)
pytest packages/railtracks/tests/unit_tests/ -v --timeout=30
# Unit + integration tests (excludes llm_live_tests and end_to_end/retrieval, per root pyproject.toml addopts)
pytest -s -v packages/railtracks/tests/unit_tests/ packages/railtracks/tests/integration_tests/
# Single test file / test
pytest packages/railtracks/tests/unit_tests/nodes/test_x.py -v
pytest packages/railtracks/tests/unit_tests/nodes/test_x.py::test_name -v
# Dependency sort check (CI enforced)
python scripts/check_dependencies_sorted.py
# Docs
mkdocs serve # local preview at localhost:8000
mkdocs build --strict --verbose
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 · 159 lines · 2,434 tokens per session scan A c967bd1509a4
railtracks AGENTS.md is an instructions file published in the GitHub repository RailtownAI/railtracks (148 stars, last pushed yesterday), licensed MIT. It adds 2,434 tokens to every session, about $0.0122 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 2026-09-03.
Other instructions, from other repositories
timbal CLAUDE.md
Claude Code instructions for timbal-ai/timbal, covering claude.md, commands, development and testing, benchmarks and repository layout.
agentinsight-sdk-python AGENTS.md
Instructions for AgentInsight/agentinsight-sdk-python, covering agentinsight python sdk — 智能体执行规则, 1. 项目基本信息, 1.1 技术栈, 1.2 项目关键特征 and 1.3 项目目录结构.
pydantic-ai CLAUDE.md
Claude Code instructions for pydantic/pydantic-ai, a project described as: How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
aidb CLAUDE.md
Instructions for ai-debugger-inc/aidb, covering ai debugger (aidb) - claude code context, project overview, project components, architecture overview and key architectural concepts.
apm python.instructions.md
Python development guidelines.
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.