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.
git clone --depth 1 https://github.com/lineage-foundation/mcpWrote 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/rules/lineage-foundation/mcp/documentation-reference)<a href="https://agentmods.dev/rules/lineage-foundation/mcp/documentation-reference"><img src="https://agentmods.dev/badge/rules/lineage-foundation/mcp/documentation-reference/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/lineage-foundation/mcp/documentation-reference"><img src="https://agentmods.dev/badge/rules/lineage-foundation/mcp/documentation-reference.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00379 | $0.00379 |
| Opus 5.5 | $0.00152 | $0.00152 |
| Sonnet 5.5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
documentation-reference 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 1mo 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.
What it actually says
Principle: Documentation-Driven Development
Before writing any code, always consult the relevant official documentation. The goal is to leverage built-in functionalities, established patterns, and best practices provided by the framework or library creators. Avoid "rolling your own" solutions for problems that are likely already solved.
How to Use Documentation
- Identify the Technology: For any given task, identify the core technologies involved (e.g., Python, a specific library, a framework).
- Find the Docs: Use the provided links or search for the official documentation.
- Search for Patterns: Look for examples, tutorials, or API references related to the task.
- Implement the Pattern: Base your implementation on the documented approach.
- Ask if Unsure: If the documentation is unclear, ambiguous, or doesn't seem to cover the use case, ask for clarification rather than making assumptions.
Key Documentation Hubs
Model Context Protocol (MCP)
- Overview & Concepts: https://modelcontextprotocol.io/
- Transports (including Streamable HTTP): https://modelcontextprotocol.io/docs/concepts/transports
- Python SDK (Servers & Clients): https://github.com/modelcontextprotocol/python-sdk
Lineage SDK
- GitHub (Source & API): https://github.com/lineage-foundation/sdk-python
- PyPI: https://pypi.org/project/lineage/
Python
- Official Docs: https://docs.python.org/3/
- Usage: For core Python language features and standard library usage.
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.
- 1mo ago First seen · 38 lines · 379 tokens per session scan A d52b0113867e
documentation-reference is a cursor rule published in the GitHub repository lineage-foundation/mcp (0 stars, last pushed 7d ago), licensed MIT. It adds 379 tokens to every session, about $0.0015 per session on Opus 5.5. 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 cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
shadcn-tailwind-guide
A guide to building new components with shadcn/ui and Tailwind CSS, a utility-based system for styling interfaces.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
testing
Guide for writing pytest unit and integration tests.
development-phase
A development rule that favors clear, well-structured new code and considers compatibility only when it costs nothing.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.