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/seeed-projects/seeed-jetson-developtool/generative-ai-intronpx skills add Seeed-Projects/Seeed-Jetson-DevelopTool --skill generative-ai-introgit clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopToolWrote 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/seeed-projects/seeed-jetson-developtool/generative-ai-intro)<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/generative-ai-intro"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/generative-ai-intro.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 5.1 | $0.00074 | $0.00752 |
| Opus 5 | $0.00037 | $0.00376 |
| Sonnet 5 | $0.00015 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade B, and why
generative-ai-intro scanned grade B with 1 finding 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 6d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo reboot How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generative AI with reComputer Jetson
Execution model
Run one phase at a time. After each phase:
- Relay all command output to the user.
- If output contains
[STOP]→ stop immediately, consult the failure decision tree below. - If output ends with
[OK]→ tell the user "Phase N complete" and proceed to the next phase.
Prerequisites
| Requirement | Details |
|---|---|
| Hardware | NVIDIA Jetson Orin (reComputer recommended) |
| JetPack | 5.x or 6.x depending on specific application |
| Internet | Required for container pulls and model downloads |
Phase 1 — Identify the target application
This skill is an index of Generative AI topics on Jetson. Help the user identify which specific application they need:
Text Generation (Local Chatbots)
- Local AI Assistant with Ollama + AnythingLLM
- Local Voice Chatbot with Nvidia Riva + Llama2
Image Generation
- Local LLM Text-to-Image on reComputer
Audio Generation
- Speech Subtitle Generation on Jetson
- Deploy Whisper on Jetson Orin for real-time STT
Multimodal
- Run VLM on reComputer with Jetson Platform Services
Retrieval Augmented Generation (RAG)
- Local AI Assistant with Ollama + AnythingLLM
- Local RAG with LlamaIndex on Jetson
Other
- Fine-tune LLM with Llama-Factory on Jetson
- Quantized Llama2-7B with MLC LLM on Jetson Orin NX
- Zero-Shot Detection on reComputer
- Format LLM Output with Langchain on Jetson
[OK] — once the user selects a topic, direct them to the corresponding skill or wiki link.
Phase 2 — Deploy jetson-examples (common entry point)
Many Generative AI applications on Jetson use the jetson-examples package for one-line deployment:
pip3 install jetson-examples
sudo reboot
After reboot, deploy the chosen application:
reComputer run <application-name>
[OK] when the application container starts and the service is accessible.
For the full list of applications, wiki links, and detailed tutorials for each topic, see
references/source.body.md.
What ships with it
2 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.
- 6d ago First seen · 96 lines · 74 tokens per session scan B 1500439fb7a3
generative-ai-intro is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (54 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 752 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
jetson-inference-mem-tune
Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.
vhdl-rag-mcp
Semantic search over the organization's VHDL code, coding standards, VHDL-related documentation, and general source code via the vhdl-rag-mcp MCP server (searchhdl, searchvhdl, searchdocs, searchcode, searchknowledge, getsource, repositoryfiles). Use when implementing or modifying HDL, looking up or enforcing design…
integrated-browser
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.