agentmods.dev

dakota: Skill for Claude Code

.agents/skills/dakota-image/SKILL.md

dakota-image is a skill for Claude Code, Codex from projectbluefin/dakota. It costs 25 tokens per session (908 once invoked), scanned A, original, MIT.

A development guide for building Dakota operating-system images, combining files into OCI container layers, testing startup in virtual machines, and checking local over-the-air updates.

In plain words
What is it for?
Use it when changing image contents, layer assembly, installer boundaries, virtual-machine tests, boot tests, or local update tests.
Why use it?
It helps developers choose the right image checks and avoid putting files in the wrong layer or claiming that an image works without startup evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is projectbluefin/dakota's own configuration. It tells Claude Code and Codex how to work on dakota itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dakota configures →

not rated 150repo +2 changed yesterday A scan SkillSpector: pass 25 tokens original MIT
View source ↗ projectbluefin/dakota projectbluefin.io
Reuse

Borrowing it

Nothing to install: this file belongs to projectbluefin/dakota. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/projectbluefin/dakota/testing/.agents/skills/dakota-image/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/projectbluefin/dakota

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 dakota-image

README.md
[![agentmods](https://agentmods.dev/badge/skills/projectbluefin/dakota/dakota-image/github.svg)](https://agentmods.dev/skills/projectbluefin/dakota/dakota-image)
Your own site
<a href="https://agentmods.dev/skills/projectbluefin/dakota/dakota-image"><img src="https://agentmods.dev/badge/skills/projectbluefin/dakota/dakota-image/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.

agentmods 80×15 button for dakota-image

Your own site · 80×15
<a href="https://agentmods.dev/skills/projectbluefin/dakota/dakota-image"><img src="https://agentmods.dev/badge/skills/projectbluefin/dakota/dakota-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 908 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00025 $0.00908
Opus 5 $0.00013 $0.00454
Sonnet 5 $0.00005 $0.00182
Haiku 4.5 $0.00003 $0.00091

Measured yesterday against content hash 556adab448e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dakota-image scanned grade A with 0 findings 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 yesterday.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/dakota-image/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dakota Image Integration

Use this skill when filesystem content crosses from BuildStream artifacts into OCI layers, or when testing and booting a local Dakota image.

When to Use

  • Modifying layer composition under elements/oci/layers/
  • Changing post-install integration steps in elements/oci/bluefin.bst
  • Running local VM boot tests (just boot-test, just boot-fast, just boot-vm)
  • Validating transactional OTA updates or testing local registries (references/local-ota.md)
  • Enforcing the installer boundary between Dakota and live installer tools

When NOT to Use

  • Building individual source packages or libraries → load dakota-packaging
  • Packaging GNOME Shell extensions → load dakota-extensions
  • Modifying GitHub Actions CI export or publication → load dakota-ci

Core Process

  1. Layer Composition: Compose layers with kind: compose. Build dependencies define layer contents.
  2. Order Post-Install Steps:
    • systemd-sysusers --root /layer
    • glib-compile-schemas /layer/usr/share/glib-2.0/schemas
    • dconf update /layer/etc/dconf/db
    • ldconfig -r /layer (must run LAST before build-oci)
  3. Validate: Run just validate to verify the composition graph.
  4. Boot Verification Ladder:
    • Level 1: just validate (graph structure)
    • Level 2: just lint (bootc container structure)
    • Level 3: just boot-test (automated headless smoke test)
    • Level 4: just boot-fast (interactive ephemeral VM with virtiofs)
    • Level 5: Local OTA testing (references/local-ota.md) for hardware verification

Invariants

  • Layer Element Kind: All layer elements in elements/oci/layers/ MUST use kind: compose. kind: stack produces empty artifacts and will break filesystem generation.
  • Linker Cache Load-Bearing Invariant: ldconfig -r /layer must execute after all library updates and before build-oci. Any command altering /usr/lib must precede ldconfig.
  • Installer Separation: Installer-specific Flatpaks or setup tools are purged on first boot via files/firstboot/. Installer UI changes belong in projectbluefin/bootc-installer, not Dakota.
  • Evidence Before Assertion: Never assert boot success without executing one of the boot test recipes.

Read the full file on GitHub · 79 lines

Files

What ships with it

1 file 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. yesterday Changed · +24 lines 556adab448e6
  2. 10d ago First seen · 55 lines · 25 tokens per session scan A fac0e02eaf30

Subscribe to this mod's changes

dakota-image is a skill published in the GitHub repository projectbluefin/dakota (150 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 908 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ContainersDevOps and cloudHardware and IoT
Related

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.

NVIDIA/skills · 35 tokens

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…

NVIDIA/skills · 153 tokens

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.

NVIDIA/skills · 78 tokens

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.

NVIDIA/skills · 32 tokens

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…

intel/gpu-ai-skills · 146 tokens

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…

togethercomputer/skills · 124 tokens