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 skills add zilliztech/mfs --skill mfs-findgit 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/skills/zilliztech/mfs/mfs-find)<a href="https://agentmods.dev/skills/zilliztech/mfs/mfs-find"><img src="https://agentmods.dev/badge/skills/zilliztech/mfs/mfs-find.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00225 | $0.04352 |
| Opus 5 | $0.00112 | $0.02176 |
| Sonnet 5 | $0.00045 | $0.00870 |
| Haiku 4.5 | $0.00022 | $0.00435 |
Grade A, and why
mfs-find 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 8d 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MFS — find / read across configured sources
1. What MFS is
A retrieval layer that exposes many kinds of content as a unified path tree and makes that tree searchable through one hybrid index:
- One CLI (
mfs), one mental model. Local dir, Postgres, GitHub repo, Slack workspace, S3 bucket, BigQuery dataset — all addressed as paths under their<scheme>://URI. Same verbs everywhere:ls / tree / cat / head / tail / grep / search / export. - One hybrid index. Dense vectors (semantic) + BM25 (keyword) fused per query — covers conceptual recall and exact-token recall in one call.
- POSIX-style locators. Every search hit carries a
locatorthat reopens the exact unit:{"lines":[s,e]}for text/code, a PK dict for rows/issues/threads.
2. When to use MFS — and when NOT to
| Situation | Use MFS? |
|---|---|
| 1000+ files / rows / pages, you don't know where the answer is | ✅ |
| Cross-source question ("any past tickets / commits / RFCs about X") | ✅ --all |
| Concept-style query that won't match literally | ✅ --mode semantic |
| You already know the exact file + roughly where to look | ❌ plain cat/grep |
| Exact identifier / error code in 5 files you can list | ❌ plain grep/rg |
| Real-time tailing of a live log | ❌ index lags ingest |
| The source isn't in MFS yet | wrong skill, use mfs-ingest to register first |
Rule: use the smallest tool that answers the question. MFS pays off
when the scope is too big for rg.
Borderline — ASK the user:
| Ask | Likely answer | Why |
|---|---|---|
| "Summarise these 10 PDFs" | ✅ mfs search + cat --peek per hit |
each PDF gets a converted_md artifact + searchable chunks |
| "Find similar tickets to this one" | ✅ paste the ticket text as the search query | semantic over row_text does similarity matching |
| "Watch for new slack messages" | ❌ no watch capability; use Slack's API |
index lags ingest |
| "Look up user 12345" | ❌ mfs cat <source> --locator '{"id":12345}' directly (skip search) |
one-record-by-id doesn't need ranking |
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/connectors/bigquery.md 1.5 KB
- reference/connectors/discord.md 2.9 KB
- reference/connectors/feishu.md 2.8 KB
- reference/connectors/file.md 2.2 KB
- reference/connectors/gdrive.md 1.7 KB
- reference/connectors/github.md 2.9 KB
- reference/connectors/gmail.md 1.9 KB
- reference/connectors/hubspot.md 1.8 KB
- reference/connectors/jira.md 2.3 KB
- reference/connectors/linear.md 1.2 KB
- reference/connectors/mongo.md 1.9 KB
- reference/connectors/mysql.md 1.2 KB
- reference/connectors/notion.md 1.8 KB
- reference/connectors/postgres.md 2.8 KB
- reference/connectors/s3.md 1.7 KB
- reference/connectors/slack.md 3.6 KB
- reference/connectors/snowflake.md 1.4 KB
- reference/connectors/web.md 1.2 KB
- reference/connectors/zendesk.md 2.3 KB
- reference/error-codes.md 2.2 KB
- reference/json-envelope.md 2.5 KB
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.
- 8d ago First seen · 374 lines · 225 tokens per session scan A 59d9d59cbb41
mfs-find is a skill published in the GitHub repository zilliztech/mfs (137 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 225 tokens to every session and 4,352 once invoked, about $0.0011 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 skills, from other repositories
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
memx
Use when an agent needs to recall, save, inspect, or audit memX memories through the bundled MCP tools.
Vector Databases
Guides retrieval-store design, indexing, and query behavior for embedding-backed systems without confusing storage with application truth.
vector-databases
Vector database operations — embed, store, search, and build RAG pipelines.
crystalline-schema
Use when a Crystalline domain wants structure for one of its engram types - authoring a Picoschema schema engram, running inferschema to bootstrap one from what is already captured, or validateengrams to check conformance.