agentmods.dev

kelly-local-model-lab

kelly-local-model-lab is a skill for Codex from mr-kelly/skills. It costs 113 tokens per session (1,584 once invoked), scanned A, original, MIT.

A local workflow for curating training examples, saving fixed dataset versions, running LoRA or QLoRA fine-tuning on an Apple Silicon Mac, and comparing the result with the original model.

In plain words
What is it for?
Use it to prepare datasets, run local MLX-LM fine-tunes, test adapters against locked evaluations, and register the versions you approve.
Why use it?
It keeps training data, experiments, evaluations, and approved adapters organized and reproducible. It also separates model fine-tuning from adding current knowledge through search or retrieval.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: $skill-name invocation.

not rated 5repo yesterday A scan 113 tokens original MIT

Good fit Use it to prepare datasets, run local MLX-LM fine-tunes, test adapters against locked evaluations, and register the versions you approve.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mr-kelly/skills/kelly-local-model-lab
View source ↗ mr-kelly/skills mr-kelly.github.io
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add mr-kelly/skills --skill kelly-local-model-lab
Clone the repo
git clone --depth 1 https://github.com/mr-kelly/skills

Made for: 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 kelly-local-model-lab

README.md
[![agentmods](https://agentmods.dev/badge/skills/mr-kelly/skills/kelly-local-model-lab/github.svg)](https://agentmods.dev/skills/mr-kelly/skills/kelly-local-model-lab)
Your own site
<a href="https://agentmods.dev/skills/mr-kelly/skills/kelly-local-model-lab"><img src="https://agentmods.dev/badge/skills/mr-kelly/skills/kelly-local-model-lab/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 kelly-local-model-lab

Your own site · 80×15
<a href="https://agentmods.dev/skills/mr-kelly/skills/kelly-local-model-lab"><img src="https://agentmods.dev/badge/skills/mr-kelly/skills/kelly-local-model-lab.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,584 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 $0.00113 $0.01584
Opus 5 $0.00056 $0.00792
Sonnet 5 $0.00023 $0.00317
Haiku 4.5 $0.00011 $0.00158

Measured 8d ago against content hash c8bd7a492981, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

kelly-local-model-lab 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 8d ago.

The scan reads SKILL.md. This mod also ships 22 executable files (content/kelly-local-model-lab-app/app/accent-theme.js, content/kelly-local-model-lab-app/app/app.js, content/kelly-local-model-lab-app/app/js/busabase-client.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/kelly-local-model-lab/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kelly Local Model Lab

Use Busabase as the durable data and control plane while a trusted local Worker performs compute on Apple Silicon. Fine-tuning changes behavior; it is not a replacement for RAG when the goal is to inject current knowledge.

Mandatory Dependencies

Before creating, provisioning, or changing the AirApp, read and follow:

  1. $kelly-app-skill-creator for product behavior and UI quality;
  2. $busabase for Space selection, node discovery, ChangeRequests, and trusted writes;
  3. $busabase-app-creator for AirApp runtime, SDK, security, validation, and deployment;
  4. $kelly-app-skill-creator-tests before claiming full conformance.

If a dependency is unavailable, keep the canonical local artifact and training pipeline intact, stop before the unavailable Busabase operation, and report the missing dependency. Never replace Busabase with SQLite, local JSON, or another persistent workflow backend.

Operating Boundary

  • The AirApp reviews examples, runs, evaluations, and registered adapters. It never launches MLX, reads local model files, or performs training itself.
  • A trusted local Agent/Worker claims one eligible training-runs record, downloads its immutable Drive snapshot, trains locally, writes heartbeats, uploads the adapter and report, and then marks the run terminal.
  • Busabase Base records hold structured state and provenance. Drive/File holds dataset snapshots, adapters, reports, and model cards. Vault holds only named credential requirements; values never enter the browser.
  • Base-model caches are disposable local compute caches. They are not canonical workflow state and need not be uploaded to Busabase.
  • A deployed AirApp cannot call the Mac's localhost. Inference or training requests cross the same reviewed Busabase job boundary.

Read references/lab-schema.md before operating on resources, exporting data, claiming work, evaluating, or registering an adapter.

Default Experiment

Read the full file on GitHub · 143 lines

Files

What ships with it

60 files 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. 8d ago First seen · 143 lines · 113 tokens per session scan A c8bd7a492981

Subscribe to this mod's changes

kelly-local-model-lab is a skill published in the GitHub repository mr-kelly/skills (5 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 1,584 once invoked, about $0.0006 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 2026-09-03.

Claude CodeData and AIagent-skillsai-agentsclaude-skillscodex-skillsskill-md
Related

Other skills, from other repositories

baoyu-danger-gemini-web

Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation"…

JimLiu/baoyu-skills · 74 tokens

understand-knowledge

Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.

Egonex-AI/Understand-Anything · 32 tokens

better-prompt

A prompt editor that turns rough instructions for AI systems into clearer, more complete prompts. It follows published OpenAI and Anthropic guidance.

huangwb8/skills · 107 tokens

asyncopenai-concurrency-httpx-pool

Raise real concurrency in asyncio LLM batch scorers built on the OpenAI SDK (AsyncOpenAI, including OpenAI-compatible providers like DeepSeek). Use when: (1) raising an asyncio.Semaphore above 100 produces no throughput gain, (2) a batch pipeline saturates near 100 in-flight requests despite a larger semaphore, (3)…

kennethkhoocy/applied-micro-skills · 161 tokens

annotator-input-parity-check

Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2)…

kennethkhoocy/applied-micro-skills · 207 tokens

llm-campaign-drift-gate

Gate resumption of any multi-day LLM batch-scoring campaign that calls an unpinned model alias (deepseek-chat, gpt--latest, gemini--preview, any provider alias without a pinned version). Use when: (1) resuming a paused or credit-exhausted scoring run days after its last chunk, (2) topping up credits to finish a…

kennethkhoocy/applied-micro-skills · 179 tokens