dakota: Skill for Claude Code

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

dakota-extensions is a skill for Claude Code, Codex from projectbluefin/dakota. It costs 43 tokens per session (1,447 once invoked), scanned A, original, MIT.

A development guide for packaging and configuring GNOME Shell extensions, Quick Settings panels, and their settings in the Dakota system image. GNOME Shell is the desktop interface used by the GNOME Linux desktop.

In plain words
What is it for?
Use it to add, patch, update, or configure GNOME extensions in the Bluefin shell-extensions directory, including their default dconf settings.
Why use it?
It gives you a consistent process for adding or updating extensions and checking that they work with the GNOME version Dakota uses. It also helps avoid packaging an extension with unsupported settings or syntax.

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 →

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-extensions/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-extensions

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/projectbluefin/dakota/dakota-extensions"><img src="https://agentmods.dev/badge/skills/projectbluefin/dakota/dakota-extensions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,447 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.
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 $0.00043 $0.01447
Opus 5.5 $0.00017 $0.00579
Sonnet 5.5 $0.00009 $0.00289
Haiku 4.5 $0.00004 $0.00145

Measured 1mo ago against content hash 93de0d9afa54, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dakota-extensions 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 1mo 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.

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-extensions/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dakota GNOME Extensions

Dakota packages curated GNOME Shell extensions built from source or upstream repositories directly into the immutable system image.

When to Use

  • Packaging a new GNOME Shell extension into elements/bluefin/shell-extensions/
  • Updating or patching an existing extension in elements/bluefin/shell-extensions/
  • Enabling or configuring default extension settings in dconf schemas
  • Resolving extension compatibility for the tracked GNOME version (GNOME 45–50+)

When NOT to Use

  • Packaging native system software, CLI tools, or background daemons → load dakota-packaging
  • Low-level OCI layer composition → load dakota-image
  • Developer/CI workflows → load dakota-ci

Core Process

  1. Verify Upstream Extension:
    • Inspect metadata.json for supported shell-version entries (must match Dakota's GNOME release, currently targeting GNOME 50).
    • Ensure code uses modern ESM syntax (import ... from 'resource:///...').
  2. Create Element:
    • Add elements/bluefin/shell-extensions/<name>.bst using kind: manual.
    • Source from pinned git commit or release tag.
    • For release ZIPs with metadata.json at the archive root, set base-dir: "" in the kind: zip source. The plugin default ('*') extracts a child directory instead, dropping root-level files. Inspect the pinned archive's layout before choosing an extraction root; source-tree archives may have a wrapper directory.
    • Extract UUID via jq and install files into:
      _uuid="$(jq -r .uuid metadata.json)"
      _dest="%{install-root}%{datadir}/gnome-shell/extensions/${_uuid}"
      install -d "${_dest}"
      cp -R * "${_dest}/"
      
  3. Compile Schemas:
    • If the extension ships a schemas/ directory, compile schemas in install-commands:
      glib-compile-schemas "${_dest}/schemas"
      
  4. Aggregate in Stack:
    • Add the new extension element to elements/bluefin/gnome-shell-extensions.bst.
  5. Configure Default Enablement:
    • Check both files/dconf/ and elements/bluefin/shell-extensions/disable-ext-validator.bst, which generates Dakota's default enabled-extensions schema override.
    • Enable basic desktop behavior by default only when its pinned metadata supports the target Shell version and its backend services are available. Personal integrations (sync/VPN controls, clipboard history, extra audio controls, and power reminders) remain opt-in with their dependencies installed. BudsLink may stay enabled because its default panel is hidden without supported devices. A disabled version validator does not establish compatibility.
    • For administrator-managed prerequisites, provide explicit setup from the control rather than silently granting permissions. Dakota's Tailscale setup uses a narrowly scoped, administrator-authenticated helper; it does not authorize users at boot.
    • Diagnose live settings with /usr/bin/gsettings and gnome-extensions, not Homebrew's GSettings CLI. Existing user lists can mask new defaults; preserve those selections rather than installing login migrations to force new defaults.
  6. Validate & Build: Graph validation (bst show) does not stage sources or execute installation commands. Build the changed extension and inspect its installed metadata and schemas; a green graph check alone cannot verify archive extraction.
    just validate
    just bst build bluefin/shell-extensions/<name>.bst
    

Read the full file on GitHub · 105 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. 1mo ago Changed · +3 lines 93de0d9afa54
  2. 1mo ago First seen · 102 lines · 43 tokens per session scan A eaf9111537fa

Subscribe to this mod's changes

dakota-extensions is a skill published in the GitHub repository projectbluefin/dakota (193 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,447 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-08.

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