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 etreby/intel-npu-tools --skill intel-npu-local-knowledgegit clone --depth 1 https://github.com/etreby/intel-npu-toolsWrote 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/etreby/intel-npu-tools/intel-npu-local-knowledge)<a href="https://agentmods.dev/skills/etreby/intel-npu-tools/intel-npu-local-knowledge"><img src="https://agentmods.dev/badge/skills/etreby/intel-npu-tools/intel-npu-local-knowledge/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/etreby/intel-npu-tools/intel-npu-local-knowledge"><img src="https://agentmods.dev/badge/skills/etreby/intel-npu-tools/intel-npu-local-knowledge.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 | $0.00067 | $0.00423 |
| Opus 5 | $0.00034 | $0.00211 |
| Sonnet 5 | $0.00013 | $0.00085 |
| Haiku 4.5 | $0.00007 | $0.00042 |
Grade A, and why
intel-npu-local-knowledge 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.
What it actually says
Intel NPU Local Knowledge
Use the intel-npu-tools MCP server to retrieve relevant local passages. Keep indexed scope explicit and cite returned paths and line numbers.
Workflow
- Call
semantic_index_statusto inspect existing roots. - If the requested file or directory is absent or may have changed, ask for its path when unknown, then call
semantic_indexonce. Index only the scope relevant to the task. - Call
semantic_searchwith a specific natural-language query. Passrootwhen results must stay within one indexed tree. Start withlimit=5. - Answer from the returned passages and cite each local path with its starting line. Distinguish retrieved facts from inference.
- Refine the query when results are weak or ambiguous. Do not repeatedly re-index unchanged content; indexing is incremental.
Tool guidance
semantic_index(path): Index one supported text file or recursively index a directory on the Intel NPU.semantic_search(query, limit, root): Return ranked passages with similarity score, path, line range, and text.semantic_index_status(): Return database location, roots, file count, and chunk count.
Treat scores as ranking signals, not calibrated probabilities. Prefer passages that directly address the query and verify critical details against the cited file when a file-reading tool is available.
Privacy and boundaries
- Index only paths the user placed in scope.
- Do not index credential stores, browser profiles, key directories, or unrelated home folders.
- Local text chunks and embeddings persist in the SQLite index until the toolkit data directory is removed.
- The MCP transport is local stdio; no indexed text is uploaded by this toolkit.
What ships with it
1 file 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.
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 · 32 lines · 67 tokens per session scan A 741198516814
intel-npu-local-knowledge is a skill published in the GitHub repository etreby/intel-npu-tools (0 stars, last pushed 26d ago), licensed MIT. It adds 67 tokens to every session and 423 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
pinecone-research
Agent RAG and long-term memory with Pinecone.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
potpie-graph
Use when the task can read or write the project-memory graph through the potpie CLI: discover the contract with graph catalog, read named views with graph read, resolve entity identity with graph search-entities, create validated plans with graph propose, commit plans with graph commit --verify, inspect quality with…
potpie-repo-baseline
Use when establishing, refreshing, or deeply understanding a repository's baseline memory in Potpie: purpose, application type, features, services/modules, environments, deploy shape, dependencies, API contracts, datastores, integrations, ownership, and explicit preferences. The harness reads authored and…
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
create-atomic-context-provider
Build a BaseDynamicContextProvider that injects a named, titled block into an agent's system prompt at every run() — current time, user identity, retrieved RAG docs, session state, cached DB schema. Use when the user asks to "add a context provider", "inject X into the prompt", "give the agent dynamic context", "wire…