Borrowing it
Nothing to install: this file belongs to suharvest/sensecraft-solutions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/suharvest/sensecraft-solutions/main/.agents/skills/integrate-jetson-solution/SKILL.mdgit clone --depth 1 https://github.com/suharvest/sensecraft-solutionsWrote 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/suharvest/sensecraft-solutions/integrate-jetson-solution)<a href="https://agentmods.dev/skills/suharvest/sensecraft-solutions/integrate-jetson-solution"><img src="https://agentmods.dev/badge/skills/suharvest/sensecraft-solutions/integrate-jetson-solution/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/suharvest/sensecraft-solutions/integrate-jetson-solution"><img src="https://agentmods.dev/badge/skills/suharvest/sensecraft-solutions/integrate-jetson-solution.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 | $0.00045 | $0.02198 |
| Opus 5 | $0.00023 | $0.01099 |
| Sonnet 5 | $0.00009 | $0.00440 |
| Haiku 4.5 | $0.00005 | $0.00220 |
Grade A, and why
integrate-jetson-solution scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
download on the host with `curl` and bind-mount the model into the container. How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integrate Jetson Solution Skill
Generate a complete solutions/<solution_id>/ package for Jetson deployment, based on structured user input.
This skill is intentionally scoped to:
- local file generation only
- no application source changes
- structured input only (free-form command blocks are not the primary input)
The generated files must conform to the public contract in spec/CONTRACT.md
(device schema, docker_deploy derivation, guide.md Step/Target syntax). Validate
the result with the offline solutionctl tool (see Execution Workflow).
Inputs Contract
Use the schema in:
references/input-schema.md
Reject the request if required fields are missing.
Required Validation Rules
solution_idmust match^[a-z][a-z0-9_]*$.docker_imagemust be non-empty and include a repo segment.app_start_commandmust be non-empty.stream.typemust bertspornone(defaultrtsp).camera.modemust berequired,optional, ornone(defaultrequired).- If
solutions/<solution_id>/already exists, stop and ask for explicit overwrite permission.
Fixed Decision Logic
stream.type=rtsp:
- generate
devices/preview.yaml - include Step 2 (preview) in
guide.mdandguide_zh.md
stream.type=none:
- do not generate
devices/preview.yaml - do not include Step 2 in guides
camera.mode=required:
- keep
/dev:/devmount andprivileged: truein compose - guide text says camera is required
camera.mode=optional:
- keep
/dev:/devmount andprivileged: truein compose - guide text says camera is optional
camera.mode=none:
- remove
/dev:/devmount - set
privileged: false - guide text says camera is not used
Compose Compatibility (Must Keep)
Use compatibility flow from:
references/compose-compat.md
The generated devices/jetson.yaml must include a before-action equivalent to:
- probe
docker compose version - probe
docker-compose --version - package fallback:
docker-compose-plugin->docker-compose-v2->docker-compose - fail with a clear message if unavailable
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.
- references/compose-compat.md 1.2 KB
- references/input-schema.md 1.8 KB
- templates/assets/jetson/docker-compose.yml.tmpl 1.1 KB
- templates/description_zh.md.tmpl 408 B
- templates/description.md.tmpl 459 B
- templates/devices/jetson.yaml.tmpl 3.2 KB
- templates/devices/preview.yaml.tmpl 560 B
- templates/guide_zh.md.tmpl 1.4 KB
- templates/guide.md.tmpl 1.4 KB
- templates/snippets/preview-step.en.md.tmpl 704 B
- templates/snippets/preview-step.zh.md.tmpl 704 B
- templates/solution.yaml.tmpl 1.1 KB
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 · 229 lines · 45 tokens per session scan A fa00571b7f54
integrate-jetson-solution is a skill published in the GitHub repository suharvest/sensecraft-solutions (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,198 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
holoscan-install-container
Install Holoscan SDK via the NGC Docker container. Use for container-based installs; not for native apt/pip/Conda installs.
doca-urom-svc
Operate the DOCA UROM Service container on BlueField Arm for remote memory operations (puts, gets, atomics, collectives) enqueued by a paired host using doca-urom: pull the NGC image, choose the UCX component, size queues, configure Comch pairing, and align host and service versions. SECURITY: the service has no…
hsb-setup
Clone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per platform, build the correct demo container, run it, and verify HSB connectivity by pinging 192.168.0.2. Use for Holoscan Sensor Bridge setup, build, container launch, and first-connectivity bring-up.
holoscan-install-source
Build Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's needs.
xpu-container-run
Launch a Docker container with Intel GPU access on Linux. Encodes the correct combination of --device /dev/dri, render-group access, --ipc=host, ZEAFFINITYMASK pinning, Hugging Face cache mount, and --entrypoint /bin/bash for interactive use. Use when running any Intel-XPU container (vLLM-XPU, sglang-xpu, torch-XPU…
together-kueue
Install and use the Kueue job-queueing controller on a Together AI Kubernetes GPU cluster to gate jobs on quota. Covers installing Kueue, defining ResourceFlavor, ClusterQueue, and LocalQueue quota, submitting jobs to a queue, and watching quota admit or suspend them. Reach for it when a Together cluster's GPU pool…