deploy-depth-anything-v3

deploy-depth-anything-v3 is a skill for Claude Code, Codex from Seeed-Projects/Seeed-Jetson-DevelopTool. It costs 69 tokens per session (1,250 once invoked), scanned B, original, MIT.

A deployment guide for Depth Anything V3, an AI model that estimates how far away surfaces are in ordinary single-camera images, on an NVIDIA Jetson AGX Orin. It connects the model to ROS2, a software framework commonly used in robotics, and uses TensorRT for faster processing.

In plain words
What is it for?
Generating depth maps from a USB camera or video on Jetson AGX Orin hardware. It is useful for robotics applications that need distance information from RGB images.
Why use it?
It removes the manual setup of the ROS2 workspace, model files, camera input, and Jetson acceleration settings. The process checks each installation phase before continuing.

Skill for Claude CodeCodex

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

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.

agentmods
npx agentmods add skills/seeed-projects/seeed-jetson-developtool/deploy-depth-anything-v3
Any agent
npx skills add Seeed-Projects/Seeed-Jetson-DevelopTool --skill deploy-depth-anything-v3
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 deploy-depth-anything-v3

README.md
[![agentmods](https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/deploy-depth-anything-v3.svg)](https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/deploy-depth-anything-v3)
Your own site
<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/deploy-depth-anything-v3"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/deploy-depth-anything-v3.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,250 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00069 $0.01250
Opus 5 $0.00034 $0.00625
Sonnet 5 $0.00014 $0.00250
Haiku 4.5 $0.00007 $0.00125

Measured 6d ago against content hash ca478ec67c30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

deploy-depth-anything-v3 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 apt update
seeed_jetson_develop/skills/openclaw/deploy-depth-anything-v3/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy Depth Anything V3 on Jetson AGX Orin

Depth Anything V3 generates high-quality depth maps from single RGB images. This skill deploys it on Jetson AGX Orin with ROS2 and TensorRT acceleration for real-time robotics use.


Execution model

Run one phase at a time. After each phase:

  • Relay all output to the user.
  • 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.

Prerequisites

Requirement Detail
Hardware Jetson AGX Orin (e.g. reComputer Mini J501)
JetPack 6.2
ROS2 Humble installed and sourced
Camera USB camera connected
Network Internet for cloning repos and downloading ONNX models

Phase 1 — Install system dependencies (~3 min)

sudo apt update
sudo apt install -y \
    build-essential cmake git libopencv-dev \
    python3-pip python3-colcon-common-extensions v4l-utils
pip3 install numpy opencv-python

[OK] when all packages install without error.


Phase 2 — Configure CUDA environment (~1 min)

echo '
# CUDA Environment
export CUDA_HOME=/usr/local/cuda
export PATH=$CUDA_HOME/bin:$PATH
export LD_LIBRARY_PATH=$CUDA_HOME/lib64:$LD_LIBRARY_PATH
export CUDACXX=$CUDA_HOME/bin/nvcc
' >> ~/.bashrc
source ~/.bashrc
nvcc --version

[OK] when nvcc --version prints CUDA version info. [STOP] if nvcc is not found.


Phase 3 — Install ROS2 camera packages (~2 min)

sudo apt install -y ros-humble-usb-cam ros-humble-cv-bridge \
    ros-humble-image-transport ros-humble-image-geometry ros-humble-rviz2

[OK] when all ROS2 packages install successfully.


Phase 4 — Clone and build the ROS2 workspace (~5 min)

git clone https://github.com/zibochen6/ros2-depth-anything-v3-trt.git
cd ros2-depth-anything-v3-trt
colcon build --packages-select depth_anything_v3 --cmake-args -DCMAKE_BUILD_TYPE=Release
source install/setup.bash

Read the full file on GitHub · 164 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. 6d ago First seen · 164 lines · 69 tokens per session scan B ca478ec67c30

Subscribe to this mod's changes

deploy-depth-anything-v3 is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (54 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 1,250 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 2026-08-30.

Related

Other skills, from other repositories

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.

microsoft/vscode · 68 tokens

spark-environment-setup

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

wshobson/agents · 76 tokens

spark-memory-thermal-ops

Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.

wshobson/agents · 59 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

davila7/claude-code-templates · 76 tokens

amc-run-video-calibration

Calibrates pre-recorded cam.mp4 datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to amc-run-rtsp-calibration.

NVIDIA/skills · 57 tokens