Borrowing it
Nothing to install: this file belongs to vpeetla-ai/multi-agent-system-pattern. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vpeetla-ai/multi-agent-system-pattern/main/.cursor/skills/rag-governance/SKILL.mdgit clone --depth 1 https://github.com/vpeetla-ai/multi-agent-system-patternWrote 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/vpeetla-ai/multi-agent-system-pattern/rag-governance)<a href="https://agentmods.dev/skills/vpeetla-ai/multi-agent-system-pattern/rag-governance"><img src="https://agentmods.dev/badge/skills/vpeetla-ai/multi-agent-system-pattern/rag-governance.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.00292 |
| Opus 5 | $0.00027 | $0.00146 |
| Sonnet 5 | $0.00011 | $0.00058 |
| Haiku 4.5 | $0.00005 | $0.00029 |
Grade A, and why
rag-governance 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- rag-governance — 100% identical, 0 lines differ
What it actually says
RAG Governance
Principles
- Access before ranking — filter by tenant/role before vector search
- Citations required — every answer cites chunk IDs
- HITL for sensitive — low confidence or PII-tagged chunks → gateway pause
Hybrid retrieval
query → embed → vector + BM25 → merge (hybrid_alpha) → rerank → top_k
VAP strategy adapter
enterprise_ragstrategy in venkat-ai-platform delegates to Enterprise RAG API- Env:
ENTERPRISE_RAG_API_URL
LoopForge tuning (ODAEU)
top_k,hybrid_alpha,rerank_thresholdversioned in RAG config tree- Lessons stored when eval fails
Reference
enterprise_rag_platform— Qdrant adapter, OTLP exportloop-engine-agent-platform/src/loop_engine/rag/
Tests
- Golden queries with expected chunk IDs
- Access denial: user without role gets empty retrieval, not leaked chunks
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 · 42 lines · 54 tokens per session scan A 4cd65b7adc6f
rag-governance is a skill published in the GitHub repository vpeetla-ai/multi-agent-system-pattern (2 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 292 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
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
compare-race
Use when the user wants to send the same prompt to several LLMs and compare the answers - sequentially (stopwatch, clean per-lane timing) or in parallel (true race), with optional repetitions per model, judged by the starting model across quality, correctness, completeness, instruction fidelity and latency (time is…
agent-builder
Build production-ready LLM agents with LangGraph, tool use, memory, streaming, and error handling. Use when designing or implementing an AI agent, multi-agent system, or agentic workflow.
intent-classification
A skill that sorts natural-language user messages into three categories: complaint, inquiry, or suggestion. The result can be used to decide where each message should go.
deepagents-thread-inspector
Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or summarize a local dcode thread, inspect checkpoint metadata, list recent local threads, or parse…
query-writing
Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database, write SQL, run a SELECT statement, retrieve data, filter records, or generate reports from database tables.