run-local-model-lab SKILL.md skillA
run-local-model-lab from understudylabs/orchestra-agent-tools is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add understudylabs/orchestra-agent-tools/run-local-model-lab@git:20261027.533318ePins git:20261027.533318e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- understudylabs/orchestra-agent-tools
- Path
skills/run-local-model-lab/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261027.533318e, committed Oct 27, 2026
- First version recorded
- Jul 17, 2026
- Size
- 10,005 bytes
- Repository stars
- 19
- License
- MIT
Use when a developer wants to stand up and run a local model on Apple Silicon against their real workload — "run this model on my Mac", "is a local model good enough before I pay for hosted". Covers the MLX serving rig, scored real-workload evals, and the route decision. For comparing many candidate models on one eval, use compare-model-sweep.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Run Local Model Lab Run a local model against an existing Orchestra workload/eval to determine the best route for the objective. Local inference is $0 and private, and it may be the only legal path under ZDR / SOC2 / local-only constraints, but do not use a weak local result to avoid an informative remote anchor when remote evaluation is allowed and could change the decision. Same-family models (e.g. local Gemma 4 → remote Gemma 4 31B via the gateway) graduate cleanly. **Apple Silicon + MLX only.** On Macs, MLX is the native local path — quantized open weights against unified memory at the best tokens/sec, no GPU drivers, no build step. This skill standardizes on **`mlx_lm.server`** (an OpenAI-compatible endpoint, one model per port); it does not use Ollama or llama.cpp. **Want to *meet* the model, not just score it?** Use [`../ladder/SKILL.md`](../ladder/SKILL.md) for the no-data onboarding climb: it opens the local `gemma-4-e2b` lane in a browser, streams scored tasks, and can optionally compare against the billed gateway lane. Keep this skill for measured runs against the user's real workload. This skill measures and recommends; it does not download weights or change …
Read the whole file at its exact version.
How to install
mdr add understudylabs/orchestra-agent-tools/run-local-model-lab@sha256:dee7f7b245953974The line at the top of this page pins the label git:20261027.533318e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_hpyim2slm7xvnrbs)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 17, 2026 and Oct 27, 2026, about one every 26 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261027.533318e latest | 2026-10-27 | 533318e | 10,005 B | A | view · diff |
| git:20261027.3c367b0 | 2026-10-27 | 3c367b0 | 10,007 B | A | view · diff |
| git:20260722.7efedb0 | 2026-07-22 | 7efedb0 | 10,010 B | A | view · diff |
| git:20260719.1185398 | 2026-07-19 | 1185398 | 9,453 B | A | view · diff |
| git:20260717.172e27a | 2026-07-17 | 172e27a | 9,091 B | A | view |
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 (10005 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
understudylabs/orchestra-agent-tools · 19 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hpyim2slm7xvnrbs GET https://markdownregistry.com/api/v1/resolve?ref=understudylabs/orchestra-agent-tools/run-local-model-lab GET https://markdownregistry.com/api/v1/blob/dee7f7b24595397468ddfbc8c71a2edf0ad476d6bda1b9d320ac317cd7061dcd
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.