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 agentmods add skills/redhat-community-ai-tools/unifai/codebasenpx skills add redhat-community-ai-tools/UnifAI --skill codebasegit 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/codebase)<a href="https://agentmods.dev/skills/redhat-community-ai-tools/unifai/codebase"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/codebase.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 | $0.00042 | $0.00870 |
| Opus 5 | $0.00021 | $0.00435 |
| Sonnet 5 | $0.00008 | $0.00174 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
codebase-overview 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 4d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UnifAI Codebase Overview
UnifAI is a multi-service platform for building and running AI agent workflows. The monorepo contains backend services (Python/Flask), a frontend (React/TypeScript), shared libraries, and infrastructure tooling.
Domain Routing Table
| Path prefix | Domain | Skill |
|---|---|---|
multi-agent/ |
Multi-Agent System (MAS) | domains/multi-agent/SKILL.md |
rag/ |
RAG Pipeline | domains/rag/SKILL.md |
shared-resources/identity/ |
Identity & Auth | domains/identity/SKILL.md |
ui/client/src/ |
Frontend UI | domains/ui/SKILL.md |
global_utils/ |
Global Utilities | domains/global-utils/SKILL.md |
backend/ |
Platform Backend | domains/backend/SKILL.md |
rag/infrastructure/celery/ |
Celery Workers | domains/celery/SKILL.md |
temporal-worker/ |
Temporal Workers | domains/temporal-worker/SKILL.md |
helm/ |
Helm / Deploy Charts | domains/helm/SKILL.md |
Domain skills are auto-surfaced via paths when editing files in their scope.
Service Architecture Summary
| Service | Role | Tech Stack | Port |
|---|---|---|---|
| multi-agent | AI agent orchestration engine | Python, Flask, MongoDB, Redis, LangGraph | 5001 |
| rag | Document ingestion & retrieval | Python, Flask, MongoDB, Qdrant, Celery | 5002 |
| identity | Auth, teams, SSO | Python, Flask, Keycloak, MongoDB | 5003 |
| backend (platform) | Admin config, platform API | Python, Flask, MongoDB | 5000 |
| ui | Web frontend | React, TypeScript, Vite, TailwindCSS | 3000 |
| global_utils | Shared Python library | Python (package) | — |
| celery | Async task workers for RAG | Python, Celery, Redis | — |
| temporal-worker | Distributed workflow execution | Python, Temporal | — |
Cross-Cutting Concerns
| Concern | Where it lives |
|---|---|
| Authentication | shared-resources/identity/ + global_utils/identity.py |
| Configuration | Each service's config/ + global_utils/config/ |
| MongoDB access | Each service's adapters/ or infrastructure/ |
| Redis caching | global_utils/redis/ + per-service usage |
| Message queues | RabbitMQ via Celery (global_utils/celery_app/) |
| Workflow orchestration | Temporal (multi-agent/adapters/outbound/temporal/) |
What ships with it
27 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.
- domains/backend/SKILL.md 6.4 KB
- domains/celery/SKILL.md 4.6 KB
- domains/global-utils/SKILL.md 6.6 KB
- domains/helm/recipes/add-shared-pvc.md 2.5 KB
- domains/helm/references/shared-storage.md 1.5 KB
- domains/helm/SKILL.md 4.4 KB
- domains/identity/SKILL.md 7.2 KB
- domains/multi-agent/recipes/add-new-llm.md 9.7 KB
- domains/multi-agent/recipes/add-new-node.md 11 KB
- domains/multi-agent/recipes/add-new-provider.md 8.7 KB
- domains/multi-agent/recipes/add-new-tool.md 8.1 KB
- domains/multi-agent/references/adapters.md 10 KB
- domains/multi-agent/references/bootstrap.md 4.0 KB
- domains/multi-agent/references/core.md 8.1 KB
- domains/multi-agent/references/elements.md 12 KB
- domains/multi-agent/references/engine-graph.md 6.1 KB
- domains/multi-agent/references/resources.md 30 KB
- domains/multi-agent/references/session.md 6.0 KB
- domains/multi-agent/SKILL.md 13 KB
- domains/rag/references/bootstrap.md 4.9 KB
- domains/rag/references/data-sources.md 5.2 KB
- domains/rag/references/infrastructure.md 6.4 KB
- domains/rag/references/pipeline.md 4.7 KB
- domains/rag/references/vector-retrieval.md 4.6 KB
- domains/rag/SKILL.md 10 KB
- domains/temporal-worker/SKILL.md 6.6 KB
- domains/ui/SKILL.md 11 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.
- 4d ago First seen · 67 lines · 42 tokens per session scan A 77e4d4d01064
codebase-overview is a skill published in the GitHub repository redhat-community-ai-tools/UnifAI (44 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 870 once invoked, about $0.0002 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
vector-backend-operations
Select and connect the right vector-store backend for the vector-mcp MCP server — chromadb, postgres/pgvector, qdrant, couchbase, or mongodb — and supply the correct dbtype/connection parameters that every collection and search call needs. Use when the agent must decide which engine to target, wire up…
enrich
Use when the agent needs access to information beyond its training data — knowledge sources, RAG pipelines, or grounding data.
knowledge
Knowledge systems authority — RAG pipelines, vector search with Qdrant, embedding generation, semantic chunking, knowledge graph construction, retrieval evaluation, and citation-aware QA patterns.
mastra
Comprehensive Mastra framework guide. Teaches how to find current documentation, verify API signatures, and build agents and workflows. Covers documentation lookup strategies (embedded docs, remote docs), core concepts (agents vs workflows, tools, memory, RAG), TypeScript requirements, and common patterns. Use this…
ontology-refresh-governance
Refresh the operational-to-ontology projection, validate class and property contracts, enrich changed nodes for semantic search, and inspect Oracle Scheduler evidence.
beastmode-langgraph
LangGraph binding for the universal Beastmode orchestration contract.