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 PracticalSwan/agent-skills --skill nemo-retrievergit clone --depth 1 https://github.com/PracticalSwan/agent-skillsWrote 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/practicalswan/agent-skills/nemo-retriever)<a href="https://agentmods.dev/skills/practicalswan/agent-skills/nemo-retriever"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/nemo-retriever/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/practicalswan/agent-skills/nemo-retriever"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/nemo-retriever.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 | $0.00030 | $0.01342 |
| Opus 5 | $0.00015 | $0.00671 |
| Sonnet 5 | $0.00006 | $0.00268 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
nemo-retriever 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 3d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nemo-retriever
The retriever CLI indexes a folder of PDFs into LanceDB (retriever ingest) and serves vector search over it (retriever query). For any task about searching/answering questions across a folder of PDFs, use this CLI — do not write a custom RAG.
Beyond PDFs and beyond semantic search. retriever ingest also handles images, Office, HTML, TXT, audio, and video — see references/setup.md for the per-format recipe and references/install.md for the install extras ([multimedia], libreoffice, ffmpeg). For non-semantic operations — page filter, verbatim quote with citation, corpus-level aggregate, chart/image caption hits — see references/query.md. Don't fall back to native Read/Grep/Python on non-PDF inputs.
Install (if retriever is missing)
If command -v retriever returns nothing, follow references/install.md to install the NeMo Retriever Library before proceeding. It prints RETRIEVER_VENV=<path>; substitute that path for <RETRIEVER_VENV> in every example in this skill (setup, query, troubleshooting, and the CLI references).
Workflow — read the reference for the current phase, then execute
| Turn type | Read this once | Then execute |
|---|---|---|
Setup turn (first turn — ./lancedb/nv-ingest.lance doesn't exist) |
references/setup.md |
Build the index |
| Query turn (every subsequent turn — user asks a question) | references/query.md |
One retriever query call |
| Anything errored or returned empty | references/troubleshooting.md |
Apply the named recovery; do not improvise |
For the full retriever ingest / retriever query CLI specs, see references/cli/ingest.md and references/cli/query.md. You do not need these for routine turns — <RETRIEVER_VENV>/bin/retriever <subcommand> --help is faster.
Before ingesting a mixed folder, inventory extensions (find <dir> -name '*.*' | sed 's/.*\.//' | sort -u) — --input-type=auto silently drops anything outside the supported set. See references/troubleshooting.md "Unsupported file types".
What ships with it
13 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.
- BENCHMARK.md 4.1 KB
- CHANGELOG.md 4.9 KB
- evals/evals.json 3.6 KB
- references/cli/ingest.md 4.8 KB
- references/cli/query.md 3.5 KB
- references/install.md 4.1 KB
- references/query.md 7.2 KB
- references/setup.md 3.7 KB
- references/troubleshooting.md 3.5 KB
- scripts/filename_fast_path.py 5.3 KB runs code
- scripts/grep_corpus.py 3.5 KB runs code
- skill-card.md 4.1 KB
- skill.oms.sig 6.3 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.
- 3d ago Changed · -1 lines a102ef373aa2
- 4d ago Changed ef9d53544e37
- 7d ago First seen · 88 lines · 30 tokens per session scan A 3c09b574df81
nemo-retriever is a skill published in the GitHub repository PracticalSwan/agent-skills (14 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 1,342 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
nemotron-retrieval-recipes
Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron embed/rerank retrieval recipes.
sweet-index
Use when (re)indexing a Sweet Search project. Runs the full-profile indexer with GPU model prewarming (CoreML cascade on M3+, candle Metal on M1/M2, ORT CPU elsewhere), kills ORT CPU models during indexing to avoid memory contention, and rewarms them for query readiness on completion. Incremental runs under 20 files…
vector-search-workflows
Vector search indexing and querying workflows using MCP Vector Search, including setup, reindexing, auto-index strategies, and MCP integration.
nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
knowledge
Knowledge systems authority — RAG pipelines, vector search with Qdrant, embedding generation, semantic chunking, knowledge graph construction, retrieval evaluation, and citation-aware QA patterns.
nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.