Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ibm-self-serve-assets/building-blocksnpx agentmods add skills/ibm-self-serve-assets/building-blocks/streamhouse-continuous-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/ibm-self-serve-assets/building-blocks/streamhouse-continuous-rag)<a href="https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/streamhouse-continuous-rag"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/streamhouse-continuous-rag/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/ibm-self-serve-assets/building-blocks/streamhouse-continuous-rag"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/streamhouse-continuous-rag.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 | $0.00074 | $0.02146 |
| Opus 5.5 | $0.00030 | $0.00858 |
| Sonnet 5.5 | $0.00015 | $0.00429 |
| Haiku 4.5 | $0.00007 | $0.00215 |
Grade A, and why
streamhouse-continuous-rag 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 27d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Streamhouse Continuous RAG
Use this skill when working on the FactoryPulse project or when the user asks for a Confluent Cloud Streamhouse implementation centered on Continuous RAG.
Start here
Before changing code, read:
README.mddocs/ARCHITECTURE.mddocs/TECHNICAL_SPEC.md- The relevant file under
support/in this skill.
Treat those files as the project contract. If code and documentation disagree, fix both in the same change.
Architecture invariants
Preserve these design principles unless the user explicitly asks to change them:
- Python runtime is 3.12 and the backend is FastAPI.
- Confluent Cloud Kafka is the event backbone. Do not turn Continuous RAG into a scheduled/nightly document-loading job.
- New or changed knowledge enters
rag.knowledge.rawas an event. - Knowledge chunks/embeddings are materialized continuously to
rag.knowledge.embeddings. - Questions and knowledge must use the same embedding model in the managed Flink profile.
- Every RAG answer must return its retrieved evidence. Never hide the grounding path.
- The manufacturing story must connect machine condition, production impact, quality impact, and maintenance knowledge.
- Tableflow is the analytical/history path. Do not place Tableflow in the low-latency interactive RAG request path.
- Never hardcode Confluent, Schema Registry, IBM Cloud, or watsonx.ai secrets in source, examples, screenshots, or logs.
- Keep the UI enterprise-oriented, responsive, and operational rather than looking like a generic chatbot.
Choose the correct RAG profile
local
Use this for the fastest demo or development loop.
- Consume
rag.knowledge.rawin Python. - Chunk documents in Python.
- Generate deterministic demo embeddings.
- Publish chunks to
rag.knowledge.embeddings. - Replay the compacted embedding topic to rebuild the read index.
Always explain that the deterministic embedding is a demo fallback, not a production semantic embedding model.
What ships with it
3 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.
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.
- 27d ago First seen · 207 lines · 74 tokens per session scan A 888bcdf6b54a
streamhouse-continuous-rag is a skill published in the GitHub repository ibm-self-serve-assets/building-blocks (28 stars, last pushed yesterday), licensed Apache-2.0. It adds 74 tokens to every session and 2,146 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-25.
Other skills, from other repositories
apigee-agent-gateway-governance
Stands up an Apigee API proxy that a Google Cloud Agent Gateway calls as an ext-proc (Service Extension) callout on an agent's LLM traffic, to meter token usage per model, extract caller identity, and apply Model Armor prompt screening or a semantic cache. Use when wiring Apigee in as an AI gateway behind an Agent…
ai-pipeline-orchestration
Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster.
managed-model-endpoints
Register a model service in the managed family — a local model server container the daemon starts/stops on demand, or a remote upstream model API (https). Read the runbook, allocate a port (local only), compose idempotent start/stop scripts (local only), register once. Load when the user wants a model service…
aws-bedrock
AWS Bedrock — fully managed foundation models on AWS infrastructure. Use when deploying AI in AWS-native environments, needing enterprise compliance (SOC2, HIPAA), running Claude, Llama, Titan, or Mistral on AWS, leveraging Knowledge Bases for RAG, or applying Guardrails for content safety.
cloudflare-vectorize
Serverless vector database at the edge with Cloudflare Vectorize. Use when: building semantic search on Cloudflare Workers, RAG pipelines at the edge, low-latency vector similarity search, or storing and querying embeddings without managing a separate vector database.
cloudflare-ai
You are an expert in Cloudflare Workers AI, the serverless AI inference platform running on Cloudflare's global network. You help developers run LLMs, embedding models, image generation, speech-to-text, and translation models at the edge with zero cold starts, pay-per-use pricing, and integration with Workers, Pages…