model-sovereignty skillA
model-sovereignty is agent-read markdown (skill) from habitat-thinking/ai-literacy-superpowers: This skill should be used when the user asks about "local models", "custom models", "fine-tuning", "self-hosting models", "model selection", "which model should I use", "data privacy and models", "LoRA", "RAG vs fine-tuning", "Ollama", "vLLM", or wants guidance on whether to build, host, or customise their own AI models..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Model Sovereignty Model sovereignty is the practice of making deliberate decisions about which models to use, where they run, and whether to create custom models. It extends the framework's Theme #2 (Agency and Sovereignty) into the model layer. This skill guides practitioners through the decision framework from cross-cutting Theme #17 and Appendix P of the framework. ## The Decision Hierarchy Exhaust simpler approaches before escalating complexity. Each step adds maintenance burden. 1. **Prompting + context engineering** — the default. Most teams underestimate how far this carries them. Exhaust it first. 2. **RAG** — when the limitation is knowledge (volatile, large, or frequently changing information). 3. **Fine-tuning (LoRA/QLoRA)** — when the limitation is behaviour (consistent domain-specific patterns at scale). 4. **Distillation** — when the limitation is size or speed (edge deployment, latency-sensitive applications). 5. **Local hosting** — when the limitation is privacy, cost at scale, or independence from vendor defaults. ## The Decision Framework Walk through these questions in order. Stop at the first "yes." …
Read the whole file at its exact version.
How to install
mdr add habitat-thinking/ai-literacy-superpowers/model-sovereignty@git:20260408.1ba2441mdr add habitat-thinking/ai-literacy-superpowers/model-sovereignty@sha256:b67f8298c939cf5fPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_ki636xwvoij5texz)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4215 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
habitat-thinking/ai-literacy-superpowers · 106 stars · license NOASSERTION · pushed 2026-09-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ki636xwvoij5texz GET https://markdownregistry.com/api/v1/resolve?ref=habitat-thinking/ai-literacy-superpowers/model-sovereignty GET https://markdownregistry.com/api/v1/blob/b67f8298c939cf5f292abc7cd3793fe23673210632ea5a5b6b0ed47105dafb83
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.