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/copilot-instructionsgit 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/copilot-instructions)<a href="https://agentmods.dev/instructions/railtownai/railtracks/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/railtownai/railtracks/copilot-instructions.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 | $0.03308 | $0.03308 |
| Opus 5 | $0.01654 | $0.01654 |
| Sonnet 5 | $0.00662 | $0.00662 |
| Haiku 4.5 | $0.00331 | $0.00331 |
Grade A, and why
railtracks copilot-instructions.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 5d 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 — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Railtracks Development Instructions
Always reference these instructions first and fall back to search or bash commands only when you encounter unexpected information that does not match the info here.
Repository Overview
Railtracks is a Python framework for building agentic systems. The repository is a uv workspace containing a single published package:
packages/railtracks/— the SDK. Everything public is re-exported at the package root and used asimport railtracks as rt.
The root pyproject.toml holds workspace config and dev tooling only (docs, test, lint dependency groups). Package dependencies — including every optional extra — live in packages/railtracks/pyproject.toml.
Working Effectively
Prerequisites
- Python 3.10+ (
requires-python = ">=3.10"). CI runs 3.10. uvfor dependency management.
Development Environment Setup
uv sync --group dev # docs + test + lint tooling
uv pip install -e "packages/railtracks[all]" # SDK with all optional extras
The SDK is deliberately thin by default; features gate behind extras declared in packages/railtracks/pyproject.toml (visual, retrieval, chroma, portkey, stores-*, …).
retrieval is not part of [all]. Install it explicitly when working on the RAG stack:
uv pip install -e "packages/railtracks[all,retrieval]"
Build and Test Commands
Linting and formatting (runs in ~1 second)
ruff is configured in the root pyproject.toml: line-length 88, target py310.
# What CI checks
ruff check . --no-fix
ruff format --check .
# What you run locally to fix it
ruff check --fix
ruff format
Testing (pytest, asyncio_mode = "auto")
Live LLM tests (tests/llm_live_tests) and retrieval end-to-end tests are excluded by addopts in the root pyproject.toml, so a bare pytest never needs an API key.
# The core suite, matching CI
pytest -s -v \
--ignore=packages/railtracks/tests/unit_tests/retrieval \
packages/railtracks/tests/unit_tests/ packages/railtracks/tests/integration_tests/
# Retrieval suite (needs the retrieval extra)
pytest -s -v packages/railtracks/tests/unit_tests/retrieval/
# A single test
pytest packages/railtracks/tests/unit_tests/path/to/test_file.py::test_name
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.
- 5d ago First seen · 360 lines · 3,308 tokens per session scan A d1c6df427889
railtracks copilot-instructions.md is an instructions file published in the GitHub repository RailtownAI/railtracks (148 stars, last pushed yesterday), licensed MIT. It adds 3,308 tokens to every session, about $0.0165 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 2026-08-30.
Other instructions, from other repositories
Albatross AGENTS.md
Instructions for morganlinton/Albatross, covering agent instructions, general and releases.
langfuse-docs AGENTS.md
AGENTS.md instructions for langfuse/langfuse-docs, a project described as: 🪢 Langfuse documentation -- Langfuse is the open source LLM Engineering Platform. Observability, evals, prompt management, playground and metrics to debug and improve LLM apps.
langfuse-docs CLAUDE.md
Claude Code instructions for langfuse/langfuse-docs, a project described as: 🪢 Langfuse documentation -- Langfuse is the open source LLM Engineering Platform. Observability, evals, prompt management, playground and metrics to debug and improve LLM apps.
plano CLAUDE.md
Instructions for katanemo/plano, covering claude.md, build & test commands, rust — wasm plugins (must target wasm32-wasip1), rust — brightstaff binary (native target) and rust — tests, format, lint.
graphiti AGENTS.md
AGENTS.md instructions for getzep/graphiti, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
autocontext CLAUDE.md
Claude Code instructions for greyhaven-ai/autocontext, covering claude.md, project overview, repository layout, commands and setup.