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 Knuckles-Team/vector-mcp --skill vector-mcp-developmentgit clone --depth 1 https://github.com/Knuckles-Team/vector-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/skills/knuckles-team/vector-mcp/vector-mcp-development)<a href="https://agentmods.dev/skills/knuckles-team/vector-mcp/vector-mcp-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/vector-mcp/vector-mcp-development/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/skills/knuckles-team/vector-mcp/vector-mcp-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/vector-mcp/vector-mcp-development.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 | $0.00032 | $0.00560 |
| Opus 5.5 | $0.00013 | $0.00224 |
| Sonnet 5.5 | $0.00006 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
vector-mcp-development 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vector MCP Development
Use this skill when changing the vector-mcp connector, its documentation, or
its spec-delivery integration. Work from the repository root and read AGENTS.md,
the affected module, and the relevant specs/ status before editing. Keep the
native epistemic-graph backend as the default and route optional vector providers
through the existing provider policy and SDK contracts.
Rapid delivery: the 5-minute contract
For a small, reviewable change:
- Identify one requirement or maintenance slice and name the exact files it touches.
- Reuse the existing action-routed MCP surface, SDK, central pipelines, and package conventions. Do not add another vector transport, planner, publisher, or CI framework.
- Keep spec status generated by the canonical pipeline tools. Run the narrowest
relevant test, then run
pre-commit run --all-filesfrom the repository root. - Review the complete diff, including workflow and package-data changes, and record the source revision plus the commands and results used as evidence.
- Keep credentials, provider endpoints, generated output, caches, and scratch files
outside the checkout. A Pages claim is complete only after the central reusable
workflow has run and the exact published
spec-delivery/source is checked.
Change boundaries
- Preserve the native epistemic-graph default, action-routed tools, provider policy, refusal behavior, and packaged vector ontology and source mappings.
- Keep optional provider imports lazy and resolve credentials through the existing runtime configuration and secret-reference paths.
- Extend an existing retrieval or collection operation before adding a new abstraction.
- Use the central Pages workflow and
.config/spec-dashboard.jsonfor the spec dashboard; keep one documentation publisher for this repository. - Keep the central aggregate hooks in
.pre-commit-config.yaml; do not copy their implementation or create a second CI framework.
Validation evidence
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 · 58 lines · 32 tokens per session scan A f49cb53d1c40
vector-mcp-development is a skill published in the GitHub repository Knuckles-Team/vector-mcp (16 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 560 once invoked, about $0.0001 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 2026-10-27.
Other skills, from other repositories
rag-expert
Design retrieval-augmented generation systems: chunking, embeddings, vector and hybrid search, reranking, grounding and evaluation. Use when the user mentions RAG, retrieval, semantic search, embeddings, vector databases, pgvector, Chroma, Qdrant, Pinecone, chunking or reranking, wants an assistant answering over…
rag-retrieval-audit
Diagnose missing evidence in a RAG pipeline with labeled queries, chunk/trace inspection, Recall@K/MRR/nDCG, and stage-isolated failure taxonomy. Use when retrieval looks fine but answers fail, or when index/chunk/filter/rerank changes need before/after proof.
chromadb
Build and operate Chroma collections for RAG: PersistentClient vs HttpClient, embedding-function contracts, metadata/where filters, and dimension-safe upsert/query paths agents routinely break.
vector-databases
Vector database operations — embed, store, search, and build RAG pipelines.
molecular-rag
Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. Based on MolRAG (Xian 2025, ACL).
mongodb-mcp-v3-migration
Migrates external consumer code from the mongodb-mcp-server v1/v2 single-package API to the v3 scoped-package structure. In v3, mongodb-mcp-server is a binary-only package (npx / MCPB); library embedding uses @mongodb-js/mcp-cli, @mongodb-js/mcp-core, @mongodb-js/mcp-http-runners, @mongodb-js/mcp-tools-, and the other…