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/svngoku/coding-agents-skillsnpx agentmods add skills/svngoku/coding-agents-skills/genai-tk-skillWrote 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/svngoku/coding-agents-skills/genai-tk-skill)<a href="https://agentmods.dev/skills/svngoku/coding-agents-skills/genai-tk-skill"><img src="https://agentmods.dev/badge/skills/svngoku/coding-agents-skills/genai-tk-skill/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/svngoku/coding-agents-skills/genai-tk-skill"><img src="https://agentmods.dev/badge/skills/svngoku/coding-agents-skills/genai-tk-skill.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 | $0.00236 | $0.04336 |
| Opus 5 | $0.00118 | $0.02168 |
| Sonnet 5 | $0.00047 | $0.00867 |
| Haiku 4.5 | $0.00024 | $0.00434 |
Grade A, and why
genai-tk 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 10d 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
genai-tk — GenAI & Agentic Toolkit
genai-tk (https://github.com/tclatos/genai-tk) is a Python toolkit that wraps LangChain, LangGraph, and 100+ LLM providers into a YAML-driven, configuration-first architecture. It's not a framework you build into — it's an inversion-of-control layer where profiles in YAML drive factories that produce LangChain runtime objects (LLMs, embeddings, retrievers, agents).
The mental model:
config/*.yaml ──► global_config() ──► Factory ──► LangChain object ──► your code
Quick Reference
| Topic | Reference |
|---|---|
| Agent frameworks: ReAct, Deep, Deer-flow, SmolAgents — profiles, tools, middleware, MCP, sandbox, skills | agents.md |
RAG: RetrieverFactory, ManagedRetriever, the six retriever types, ingestion |
rag.md |
Configuration: global_config(), app_conf.yaml, :merge, environments, model_id@provider |
configuration.md |
CLI: cli init, command groups, extending the CLI with CliTopCommand |
cli-and-init.md |
BAML structured extraction with BamlStructuredProcessor |
baml-structured.md |
Installation
The toolkit is installed via uv and is not on PyPI — install from the GitHub repo:
# Add to existing project
uv add git+https://github.com/tclatos/genai-tk@main
# With extras (postgres, browser, evals)
uv add "genai-tk[extra] @ git+https://github.com/tclatos/genai-tk@main"
# Development (clone & edit)
git clone https://github.com/tclatos/genai-tk.git && cd genai-tk
uv sync # core + dev
uv sync --all-groups # + postgres, browser, evals
After install, scaffold a project:
uv run cli init --name "My AI Project" # full scaffold (recommended)
uv run cli init --minimal # config + Makefile only
uv run cli init --deer-flow # also clone Deer-flow backend
uv sync
What ships with it
12 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.
- eval.yaml 1019 B
- genai-tk-skill.skill 33 KB
- graders/check.py 16 KB runs code
- instructions/langchain-agent-profile.md 2.0 KB
- references/agents.md 17 KB
- references/baml-structured.md 12 KB
- references/cli-and-init.md 13 KB
- references/configuration.md 12 KB
- references/rag.md 16 KB
- rubrics/quality.md 2.0 KB
- solutions/reference-langchain-agent-profile/config/agents/langchain.yaml 618 B
- solutions/reference-langchain-agent-profile/use_agent.py 422 B runs code
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.
- 10d ago First seen · 337 lines · 236 tokens per session scan A f9826e1daf55
genai-tk is a skill published in the GitHub repository svngoku/coding-agents-skills (11 stars, last pushed 27d ago), licensed MIT. It adds 236 tokens to every session and 4,336 once invoked, about $0.0012 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
iflytek-image-understanding
An image-analysis tool that describes pictures and answers questions about what they contain. It uses an AI vision service, which interprets visual content rather than only reading text files.
multi-agent-orchestration
Expert guide for designing and orchestrating multi-agent systems, agent swarms, graph-based workflows (LangGraph, CrewAI, AutoGen), shared state memory, and human-in-the-loop guardrails in English and Indonesian.
ai-media-generation-expert
Expert guide for AI image generation (Flux, DALL-E, Stable Diffusion), video generation (Sora, Runway), voice synthesis (ElevenLabs TTS), and speech recognition (Whisper STT) integration / Panduan ahli integrasi AI generasi gambar, video, suara (TTS), dan pengenalan suara (STT).
ai-cost-token-optimizer
Expert guide for LLM API cost optimization, Prompt Caching, model routing (Flash/Pro/Opus), semantic caching, and token budgeting / Panduan ahli optimasi biaya API LLM, Prompt Caching, model routing, dan semantic caching.
vector-db-rag-expert
Expert guide for high-performance Vector Databases, RAG architectures, pgvector HNSW indexing, hybrid search (Dense + BM25), and semantic chunking / Panduan ahli Vector DB, arsitektur RAG, pgvector HNSW, dan hybrid search.
ai-llm-integration-expert
Expert guide for integrating Large Language Models (LLMs), Model Context Protocol (MCP), RAG architecture, vector databases, and AI agents / Panduan ahli untuk integrasi LLM, Model Context Protocol (MCP), arsitektur RAG, vector database, dan agen AI.