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 redhat-community-ai-tools/UnifAI --skill multi-agentgit clone --depth 1 https://github.com/redhat-community-ai-tools/UnifAIWrote 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/redhat-community-ai-tools/unifai/multi-agent)<a href="https://agentmods.dev/skills/redhat-community-ai-tools/unifai/multi-agent"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/multi-agent/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/redhat-community-ai-tools/unifai/multi-agent"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/multi-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.03137 |
| Opus 5.5 | $0.00011 | $0.01255 |
| Sonnet 5.5 | $0.00005 | $0.00627 |
| Haiku 4.5 | $0.00003 | $0.00314 |
Grade A, and why
mas-knowledge 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 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.
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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MAS Knowledge System
Orchestration engine: blueprint YAML → executable agent graph → runtime engine → streamed results.
System Graph
┌──────────┐
│ BOOTSTRAP│ wires everything
└────┬─────┘
│
┌─────────┼──────────┐
▼ ▼ ▼
┌───────┐ ┌────────┐ ┌────────┐
│SESSION │→│ELEMENTS│→│ ENGINE │ DOMAIN (lib/mas/)
└───┬───┘ └───┬────┘ └───┬────┘
│ │ │
▼ ▼ ▼
┌──────┐ ┌────────────────────┐
│ CORE │ │ ADAPTERS │ OUTER RING
└──────┘ │ flask, mongo, redis│
│ langgraph, temporal│
│ gemini, auth │
└────────────────────┘
File → Component Routing
| Path prefix | Component |
|---|---|
lib/mas/session/ |
Session |
lib/mas/elements/, catalog/, validation/ |
Elements |
lib/mas/engine/, graph/ |
Engine/Graph |
lib/mas/core/ |
Core |
lib/mas/resources/, lib/mas/blueprints/ |
Resources & Blueprints |
lib/mas/collaboration/, lib/mas/sharing/ |
Resources & Blueprints (edit locks, cloning) |
adapters/ |
Adapters |
bootstrap/, config/ |
Bootstrap |
Component Deep-Dives
For detailed component architecture and cross-component contracts:
| Component | Reference |
|---|---|
| Session | references/session.md — lifecycle, two-phase execution, ports, boundaries |
| Elements | references/elements.md — plugin system, nodes, tools, LLMs, auto-discovery |
| Engine/Graph | references/engine-graph.md — GraphState channels, plan layers, compilation, executors |
| Core | references/core.md — identity, ExecutionContext, ElementDeps, channels, enums |
| Resources & Blueprints | references/resources.md — registry/service split, built-in resource lifecycle, per-identity overlays, cascade promote/demote, admin edit locks |
| Adapters | references/adapters.md — inbound/outbound structure, conventions |
| Bootstrap | references/bootstrap.md — composition root, config, wiring |
What ships with it
11 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.
- recipes/add-new-llm.md 9.7 KB
- recipes/add-new-node.md 11 KB
- recipes/add-new-provider.md 8.7 KB
- recipes/add-new-tool.md 8.1 KB
- references/adapters.md 10 KB
- references/bootstrap.md 4.0 KB
- references/core.md 8.1 KB
- references/elements.md 12 KB
- references/engine-graph.md 6.1 KB
- references/resources.md 30 KB
- references/session.md 6.0 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.
- 1mo ago First seen · 263 lines · 27 tokens per session scan A a1b3e27b22c6
mas-knowledge is a skill published in the GitHub repository redhat-community-ai-tools/UnifAI (45 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 3,137 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
rag-hybrid-search
Hybrid search combining semantic and keyword retrieval for RAG pipelines. Implement BM25 + dense vector search with fusion strategies.
documentation-search
Search the internal knowledge base for runbooks, architecture documentation, ADRs, best practices, and troubleshooting guides using RAG. Use when looking for internal documentation, deployment procedures, architecture decisions, or operational runbooks.
rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
rag-chunking-strategy
Document chunking with multiple strategies including semantic, recursive, and fixed-size chunking.
vector-memory
HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.