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 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/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/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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 86 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 67 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 5.5 | $0.00030 | $0.00301 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 (56 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 752 once invoked, about $0.0003 per session on Opus 5.5. 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.
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.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.