run-vlm

run-vlm is a skill for Claude Code, Codex from Seeed-Projects/Seeed-Jetson-DevelopTool. It costs 60 tokens per session (1,091 once invoked), scanned B, original, MIT.

A deployment guide for running a visual language model on an NVIDIA Jetson. A visual language model can interpret images or video together with written prompts.

In plain words
What is it for?
Use it to install and validate the specified VLM service on a reComputer J4012 running JetPack 6.0.
Why use it?
It provides the required setup sequence for Jetson Platform Services, including memory preparation and package installation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to install and validate the specified VLM service on a reComputer J4012 running JetPack 6.0.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/seeed-projects/seeed-jetson-developtool/run-vlm
Install

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.

Any agent
npx skills add Seeed-Projects/Seeed-Jetson-DevelopTool --skill run-vlm
Clone the repo
git clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopTool

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for run-vlm

README.md
[![agentmods](https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/run-vlm.svg)](https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/run-vlm)
Your own site
<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/run-vlm"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/run-vlm.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,091 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 16 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 38
    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 39
    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 40
    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 41
    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 76
    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 77
    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 94
    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 95
    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 96
    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 97
    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 98
    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 99
    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 39
    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 138
    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 139
    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 141
    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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.01091
Opus 5 $0.00030 $0.00545
Sonnet 5 $0.00012 $0.00218
Haiku 4.5 $0.00006 $0.00109

Measured 5d ago against content hash 2de722a5d94a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

run-vlm 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 5d 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 fallocate -l 10G /swapfile
seeed_jetson_develop/skills/openclaw/run-vlm/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VLM Deployment — Jetson Platform Services

Deploys a Vision Language Model service on Jetson via JPS (Jetson Platform Services). VLMs support image, video, and text prompts using a combination of LLM and vision transformer. 10 GB swap is strongly recommended due to model memory requirements.

Hardware: reComputer J4012 (Orin NX 16GB), JetPack 6.0, Ubuntu 22.04 Package: vlm-1.1.0.tar.gz

Reference: references/source.body.md (Seeed wiki source, package download link)


Execution model

Run one phase at a time. After each phase:

  • If output contains [STOP] → stop immediately, consult the failure decision tree
  • If output ends with [OK] → tell the user "Phase N complete" and proceed to the next phase

Phase 1 — add swap (~2 min)

Check current swap:

free -h

If swap is already ≥ 10 GB → skip to Phase 2.

Add a 10 GB swapfile:

sudo fallocate -l 10G /swapfile
sudo chmod 600 /swapfile
sudo mkswap /swapfile
sudo swapon /swapfile

Verify:

free -h

Expected: Swap: row shows ~10G total. [OK]


Phase 2 — extract VLM package (~1 min)

Confirm the package is present:

ls -lh vlm-1.1.0.tar.gz

If missing → [STOP] package not found. Download link is in references/source.body.md.

Extract and enter the directory:

tar -xzvf vlm-1.1.0.tar.gz
cd vlm

[OK] when cd vlm succeeds and ls shows config/ and docker-compose.yml.


Phase 3 — copy configs (~30 s)

sudo cp config/platform-nginx.conf /etc/nginx/conf.d/
sudo cp config/prometheus.yml /etc/prometheus/

Verify:

ls /etc/nginx/conf.d/platform-nginx.conf
ls /etc/prometheus/prometheus.yml

[OK] if both files are present.


Phase 4 — start platform services (~2 min)

Start the 6 JPS services in order:

sudo systemctl start jetson-monitoring
sudo systemctl start jetson-sys-monitoring
sudo systemctl start jetson-redis
sudo systemctl start jetson-ingress
sudo systemctl start jetson-vst
sudo systemctl start jetson-platform-services

Read the full file on GitHub · 145 lines

Files

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.

Changes

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.

  1. 5d ago First seen · 145 lines · 60 tokens per session scan B 2de722a5d94a

Subscribe to this mod's changes

run-vlm is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (54 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 1,091 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

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…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens