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/zilliztech/mfs/claude-mdgit clone --depth 1 https://github.com/zilliztech/mfsWrote 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/zilliztech/mfs/claude-md)<a href="https://agentmods.dev/instructions/zilliztech/mfs/claude-md"><img src="https://agentmods.dev/badge/instructions/zilliztech/mfs/claude-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 | $0.01780 | $0.01780 |
| Opus 5 | $0.00890 | $0.00890 |
| Sonnet 5 | $0.00356 | $0.00356 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade A, and why
mfs CLAUDE.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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
MFS exposes many sources (code, docs, messages, databases, object stores) as one file-like, searchable namespace. It is a monorepo of two cooperating processes:
cli/— a thin Rust CLI (mfs). It is only an HTTP client of the server; it holds no business logic. Don't add behavior here that belongs on the server.server/python/— the Python server (mfs-server, FastAPI). It owns connectors, the ingest pipeline, the vector index, and storage, exposed over an HTTP/v1control plane. This is where almost all work happens.
The SDKs (sdks/python, sdks/typescript) are generated from
protocol/openapi.yaml. server-rs/ is an optional PyO3 acceleration wheel with a
transparent pure-Python fallback (mfs_server.common.accel) — never required.
CONTRIBUTING.md and docs/architecture.md are the long-form references; the
points below are the ones that need several files to piece together.
Commands
All Python commands run from server/python/. dev is an extra, not a
dependency-group — uv run pytest fails (no pytest); always use --extra dev:
uv sync # default deps (local ONNX, Milvus Lite, SQLite)
uv run --extra dev pytest # all unit/smoke tests
uv run --extra dev pytest tests/test_engine_chunkable_e2e.py::test_chunkable_path_drains_through_pipeline # one test
uv run --extra dev ruff format --check src/ tests/ # what CI enforces
uv run --extra dev ruff check src/ tests/ # lint (loose; not gated in CI)
uv run mfs-server run # run server from checkout, binds 127.0.0.1:13619
- A few tests import optional connector SDKs (e.g.
lark_oapi) and fail to collect without them;--ignorethose files oruv sync --extra all-connectors. - CI (
.github/workflows/lint.yml) enforces formatting only —ruff format --checkandcargo fmt --all -- --check. Tests are not gated, so run them yourself.
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 · 130 lines · 1,780 tokens per session scan A 36752ae1b448
mfs CLAUDE.md is an instructions file published in the GitHub repository zilliztech/mfs (134 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,780 tokens to every session, about $0.0089 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
kungfu CLAUDE.md
Claude Code instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before working in this repository. It routes both product use and contribution work to the repository sources of truth, including the requirement that development and build tasks enter through Shifu.
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
beevibe CLAUDE.md
Claude Code instructions for beevibe-ai/beevibe, covering beevibe — claude code guide, monorepo structure, running locally, critical: @beevibe/core compiles to dist/ and restarting cleanly.
llm-wiki-memory AGENTS.md
Instructions for ctxr-dev/llm-wiki-memory, covering agents.md, development discipline (.agents/), layout, tests and conventions.
dense-mem AGENTS.md
AGENTS.md instructions for markhuangai/dense-mem, covering dense-mem repository guidance, project context, architecture decision records, current stack and target architecture.
engram-mcp CLAUDE.md
Claude Code instructions for edg-l/engram-mcp, covering engram mcp, development rules, structure, key types and mcp capabilities.