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 global-utilsgit 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/global-utils)<a href="https://agentmods.dev/skills/redhat-community-ai-tools/unifai/global-utils"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/global-utils/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/global-utils"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/global-utils.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 | $0.00047 | $0.01570 |
| Opus 5 | $0.00023 | $0.00785 |
| Sonnet 5 | $0.00009 | $0.00314 |
| Haiku 4.5 | $0.00005 | $0.00157 |
Grade A, and why
global-utils-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 11d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Global Utils Knowledge System
Shared Python package at global_utils/src/global_utils/. Not a running service — installed as a dependency by every backend service (MAS, RAG, Identity, Platform, Celery, Temporal Worker).
Module Routing
| Module | Path | Key Exports | Description |
|---|---|---|---|
config |
config/ |
SharedConfig, ConfigManager, ConfigSource |
Pydantic BaseSettings, multi-source loading (env, .env, YAML, JSON) |
utils |
utils/ |
get_mongo_url, get_redis_url, get_temporal_url, get_rabbitmq_url, SingletonMeta, AsyncBridge |
Connection helpers, patterns |
redis |
redis/ |
RedisKVStore, build_redis_client, get_identity_session, UserSessionData |
Redis client, session management |
ports |
ports/ |
KVStore |
Shared abstract interfaces |
helpers |
helpers/ |
API arg parsing, decorators | Pydantic helpers, @from_body / @from_query |
docling |
docling/ |
DoclingClient, DoclingService |
Document conversion (local/remote) |
embedding |
embedding/ |
EmbeddingClient, EmbeddingService |
Embedding generation (local/remote) |
celery_app |
celery_app/ |
CeleryApp, send_task |
Shared Celery factory and config |
flask |
flask/ |
RequestRules, require_identity_session |
Common Flask setup, auth decorators |
Key Classes
| Class | File | Role |
|---|---|---|
SharedConfig |
config/config.py |
Pydantic BaseSettings singleton: MongoDB, RabbitMQ, Temporal, Redis fields |
ConfigManager |
config/manager.py |
JSON file-backed singleton config with env substitution |
ConfigSource (ABC) |
config/sources.py |
Abstract load() → dict for pluggable sources |
KVStore (ABC) |
ports/kv_store.py |
Hexagonal port for key-value operations with TTL |
RedisKVStore |
redis/redis_kv_store.py |
Adapter: implements KVStore + hash helpers for identity sessions |
SingletonMeta |
utils/singleton.py |
Metaclass for per-process single instance |
AsyncBridge |
utils/async_bridge.py |
Process-wide anyio BlockingPortal to run async from sync |
CeleryApp |
celery_app/init.py |
Singleton Celery with RabbitMQ broker + Mongo backend |
RequestRules |
flask/request_rules.py |
Flask before/after request hooks (size cap, headers) |
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.
- 11d ago First seen · 138 lines · 47 tokens per session scan A f9148c1442c0
global-utils-knowledge is a skill published in the GitHub repository redhat-community-ai-tools/UnifAI (44 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 1,570 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
chroma-integration
Chroma local vector database setup and operations for development and production.
milvus-integration
Milvus distributed vector database configuration for large-scale RAG applications.
seek
Designing search engines and vector DBs for full-text, vector, and hybrid retrieval, including permission-aware retrieval for multi-tenant or per-role corpora. Use for search design, index optimization, the RAG retrieval layer, or deciding where ACL filtering belongs in the query path.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
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…
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.