dakota: Skill for Claude Code

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

dakota-packaging is a skill for Claude Code, Codex from projectbluefin/dakota. It costs 34 tokens per session (1,114 once invoked), scanned A, original, MIT.

A packaging guide for adding software built from source to Dakota, including Go, Rust, Zig, standalone programs, and GNOME extensions. Packaging here means building software and placing it into the operating-system image.

In plain words
What is it for?
Use it when adding, removing, or updating software, build elements, source archives, dependency stacks, or OCI image contents.
Why use it?
It helps developers use Dakota’s source-based build system, pin and verify inputs, support the right processor types, and add software to the correct image layers.

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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 files/scripts/generate_cargo_sources.py path/to/Cargo.lock.

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-packaging/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-packaging

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/projectbluefin/dakota/dakota-packaging"><img src="https://agentmods.dev/badge/skills/projectbluefin/dakota/dakota-packaging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,114 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00034 $0.01114
Opus 5.5 $0.00014 $0.00446
Sonnet 5.5 $0.00007 $0.00223
Haiku 4.5 $0.00003 $0.00111

Measured 2d ago against content hash 822986bdd45e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dakota-packaging 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 2d 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.

- Network calls (`curl`, `wget`, `git clone`) inside `install-commands`
.agents/skills/dakota-packaging/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dakota Packaging

Package software as BuildStream elements. Dakota builds natively from source and does not consume RPMs, DNF repositories, COPRs, or Containerfile overlays.

When to Use

  • Adding a new native CLI tool, service, or library to Dakota
  • Updating an existing package element under elements/bluefin/ or elements/core/
  • Generating offline crate sources for Rust programs
  • Removing deprecated software and cleaning up dependency stacks

When NOT to Use

  • Packaging GNOME Shell extensions → load dakota-extensions
  • Host Homebrew integration or formulas → load dakota-workstation
  • Layer composition in elements/oci/layers/ → load dakota-image
  • ujust user commands → load dakota-ujust

Core Process

  1. Locate Reference Pattern: Identify an existing element with the same toolchain (Go, Rust, Zig, Meson, CMake, Autotools, or binary).
  2. Verify Upstream: Confirm upstream source, open-source license, release tag, and multi-arch support (x86_64 and aarch64).
  3. Declare Element: Create elements/bluefin/<name>.bst or under the appropriate subdirectory.
  4. Wire Dependencies: Wire into elements/bluefin/deps.bst (the aggregator stack) or the relevant layer composition element.
  5. Generate Offline Sources (Rust):
    python3 files/scripts/generate_cargo_sources.py path/to/Cargo.lock
    
  6. Validate and Build:
    just validate
    just bst build bluefin/<name>.bst
    
  7. Inspect Output: Check installed paths and permissions inside the artifact before expanding layer filters.

Language Invariants

  • Go: Use go build with flags ensuring deterministic, offline compilation (-buildvcs=false, -trimpath). Statically or dynamically link as appropriate. Do not run go get or go install across the network.
  • Rust: Never hand-craft crate lists. Always use files/scripts/generate_cargo_sources.py from Cargo.lock to generate kind: cargo2 source blocks. Build with cargo --frozen --offline.
  • Zig: Pin the exact toolchain version; specify the target triple explicitly. Generate dependency sources from upstream's lock data (Ghostty: files/scripts/generate_ghostty_sources.py), never by hand. Populate the package cache by unpacking each archive and running zig fetch <directory>: zig fetch <local tarball> caches it without stripping the top-level directory, and the package then fails its hash check at build time. Never ignore a failed zig fetch.
  • C/Meson/Autotools: Inherit build dependencies from junctions (freedesktop-sdk.bst:components/...). Do not install unpinned dependencies.
  • Binary Releases: Require per-architecture URLs, SHA256 checksums, and license installation to %{install-root}%{datadir}/licenses/<package>/.

Read the full file on GitHub · 89 lines

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. 2d ago Changed 822986bdd45e
  2. 1mo ago Changed · +32 lines · +2 tokens per session 0490df230370
  3. 2mo ago First seen · 57 lines · 32 tokens per session scan A 97c92b46a25a

Subscribe to this mod's changes

dakota-packaging is a skill published in the GitHub repository projectbluefin/dakota (193 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 1,114 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens