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-security-firstgit 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-security-first)<a href="https://agentmods.dev/skills/lyonzin/knowledge-rag/rag-security-first"><img src="https://agentmods.dev/badge/skills/lyonzin/knowledge-rag/rag-security-first/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/lyonzin/knowledge-rag/rag-security-first"><img src="https://agentmods.dev/badge/skills/lyonzin/knowledge-rag/rag-security-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 YARA Match · line 52 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high YARA Match · line 181 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00094 | $0.02513 |
| Opus 5.5 | $0.00038 | $0.01005 |
| Sonnet 5.5 | $0.00019 | $0.00503 |
| Haiku 4.5 | $0.00009 | $0.00251 |
Grade B, and why
rag-security-first scanned grade B with 1 finding 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 1mo 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.
Harvests environment variablesmediumData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
Example: `search_knowledge(query="LSASS dump credential access detection", max_results=5)` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rag-security-first — RAG-driven security workflow
When to use this skill
Trigger this skill for any security-flavored task:
- Threat triage or incident response
- MITRE ATT&CK technique mapping (T1078, T1055, …)
- CVE lookup or vulnerability analysis
- Exploit / payload / attacker-technique questions
- Red team / blue team / purple team exercises
- CTF challenge analysis
- Detection engineering (Sigma / Snort / YARA / KQL / SPL / LQL rules)
- Defensive control validation
- Compliance / hardening questions
Prerequisite: the RAG should be loaded with security-relevant content. The cybersecurity preset is optimized for this — it ships 8 categories, 200+ routing keywords, and 69 query expansions covering sqli → SQL injection, privesc → privilege escalation, etc.
What this skill commits to
For security tasks, the corpus is primary:
- Search the corpus before hitting any external threat-intel MCP (
mcp__cti__*,mcp__virustotal__*,mcp__shodan__*). - Use the query-expansion mappings (
sqli→SQL injection) — they exist for a reason. - Cite the MITRE technique ID + the internal runbook link.
- Only escalate to external threat-intel when the corpus does not cover the specific IOC / CVE / technique in enough depth.
Steps
-
Classify the intent. Is it:
- Detection — "we saw X in logs, is this bad?"
- Response — "we confirmed compromise, what now?"
- Prevention — "how do we harden against X?"
- Research — "how does X actually work?"
-
Extract the security signature from the user's message:
- MITRE ATT&CK ID (
T1078,T1078.001,TA0004) - CVE ID (
CVE-2024-1234) - Malware family (
Cobalt Strike,Mimikatz,LSASS dump) - Attack technique term (
Kerberoasting,AS-REP Roasting,pass-the-hash) - IOC (hash, domain, IP — treat as verbatim in the search)
- MITRE ATT&CK ID (
-
Search the corpus with the security preset in mind:
search_knowledge(query="<signature> <intent>", max_results=5, min_score=0.15)Example:
search_knowledge(query="LSASS dump credential access detection", max_results=5)
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.
- 1mo ago First seen · 207 lines · 94 tokens per session scan B 4b3e9709f867
rag-security-first is a skill published in the GitHub repository lyonzin/knowledge-rag (300 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 2,513 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (harvests environment variables). 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
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…
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.
assessing-vector-and-embedding-weaknesses
Test vector stores for embedding inversion, cross-tenant leakage, and poisoning.
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…