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 lyonzin/knowledge-rag --skill rag-cite-sourcesgit clone --depth 1 https://github.com/lyonzin/knowledge-ragWrote 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/lyonzin/knowledge-rag/rag-cite-sources)<a href="https://agentmods.dev/skills/lyonzin/knowledge-rag/rag-cite-sources"><img src="https://agentmods.dev/badge/skills/lyonzin/knowledge-rag/rag-cite-sources.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 63 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00070 | $0.01446 |
| Opus 5 | $0.00035 | $0.00723 |
| Sonnet 5 | $0.00014 | $0.00289 |
| Haiku 4.5 | $0.00007 | $0.00145 |
Grade A, and why
rag-cite-sources 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rag-cite-sources — every claim traces to a source
When to use this skill
Whenever an answer contains any of these:
- A specific number, threshold, config value, or version taken from the corpus
- A statement about how the system currently works, was designed, or was decided
- A code snippet, function signature, or API contract quoted from indexed files
- A "the runbook says", "the ADR says", "the RFC decided", "we agreed" claim
- A recommendation grounded in prior team practice
Basically: if a curious reader would want to double-check where you got that, cite.
What this skill commits to
Every technical claim in the response carries a citation of the form:
[path/to/file.md:42]— line-anchored (fromsearch_knowledgeresult'ssourcefield)[path/to/file.md#section-heading]— section-anchored for Markdown[path/to/file.md]— file-only, when line/section is not available
Citations are inline at the point of the claim, not batched at the end. One claim = one citation.
Steps
-
When you call
search_knowledgeorget_document, capture:- The
sourcefield (usually the file path) - The
filename(short name for display) - Any
chunk_idor line hint in the metadata - The actual
contentyou are about to quote or paraphrase
- The
-
When you draft the response, mark every fact-carrying sentence with its source. Preferred inline syntax:
Per ADR-0018 [docs/adr/0018-auth.md], the payment service uses mTLS between services. The retry policy is 3 attempts with exponential backoff [services/payment/retry.py]. -
If quoting verbatim, use fenced blockquote + citation:
> "All external API calls must timeout after 30 seconds." > — [docs/architecture/http-contracts.md#timeouts] -
If synthesizing across multiple sources, cite each:
The service uses OAuth2 [docs/adr/0018-auth.md] with a 15-minute access token TTL [config/auth.yaml:12] and refresh-token rotation on every use [docs/security/oauth-flow.md].
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 · 150 lines · 70 tokens per session scan A 0f6a0fa15648
rag-cite-sources is a skill published in the GitHub repository lyonzin/knowledge-rag (273 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 1,446 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 2026-08-30.
Other skills, from other repositories
rag-perf
Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).
rag-blueprint
NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion…
rag-eval
Filesystem RAG benchmarks: corpus/, train.json, evaluaterag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.
pinecone:full-text-search
Create, ingest into, and query a Pinecone full-text-search (FTS) document index using the graduated document-schema API (Python SDK 10.0.0, API version 2026-07). Use when the user or agent asks to build a text search index on Pinecone, add dense or sparse vector fields, ingest documents, construct scoreby clauses…
pinecone:n8n
Build n8n workflows using the Pinecone Assistant node or Pinecone Vector Store node. Use when building RAG pipelines, chat-with-docs workflows, configuring Pinecone nodes in n8n, troubleshooting Pinecone n8n nodes, or asking about best practices for Pinecone in n8n.
rag
Use when building grounded Q&A over your own corpus — chunk, retrieve hybrid, rerank, ground, cite chunk ids, refuse when the sources fall short — or when the right document is retrieved but the answer is still wrong, invented, or unmeasured. NOT operating the store itself — collection schema, HNSW efsearch…