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.
npx agentmods add skills/rchaz/tunelab/tune-datanpx skills add rchaz/tunelab --skill tune-datagit clone --depth 1 https://github.com/rchaz/tunelabWrote 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.
[](https://agentmods.dev/skills/rchaz/tunelab/tune-data)<a href="https://agentmods.dev/skills/rchaz/tunelab/tune-data"><img src="https://agentmods.dev/badge/skills/rchaz/tunelab/tune-data.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00108 | $0.04426 |
| Opus 5 | $0.00054 | $0.02213 |
| Sonnet 5 | $0.00022 | $0.00885 |
| Haiku 4.5 | $0.00011 | $0.00443 |
Grade A, and why
tune-data 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tune-data — build the dataset
Data quality determines fine-tuning quality more than any hyperparameter. The pipeline: ingest → (distill) → dedupe → split → validate → datacard. Every step has a bundled script; chain them, don't skip the gates.
<skill-dir> below = the directory containing this SKILL.md. Stdlib scripts run with python3; distill_generate.py is PEP 723 (uv run). Run everything from the user's project workdir.
Before asking the user anything: read the project state
On invocation, check the workdir first — a fresh session (or one that just compacted) must resume mid-pipeline from disk alone:
EXPERIMENT-LOG.md— tune-decide writes the interview summary and level decision here precisely so you never re-ask. Look for: task shape, data inventory, the chosen level, any frozen labeling prompt or dedupe threshold from a prior session.runs/*/state.json— if any run hasstatus: running|interrupted, training is usingdata_dirright now (or will resume into it). Do not regenerate splits underneath it; ask before touching that directory.- Partial pipeline artifacts — resume where disk says you are: a raw teacher-output file smaller than the input means resume labeling (the script skips done ids; session-native, count ids and continue);
deduped.jsonlpresent means go to split;data/{train,valid,test}.jsonlpresent means re-run validate and go to the datacard.
If there is no level decision in EXPERIMENT-LOG.md, route to tune-decide before building anything — whatever the task shape. Classification smell (N fixed categories, labels already logged) is the most urgent case: a Level 1 embeddings+classifier may need no fine-tuning dataset at all, and proving that in 10 minutes beats preparing data for a LoRA the user doesn't need.
After every completed stage, append to EXPERIMENT-LOG.md (append-only, ## <date> — <event> with short Decision / Run (config) / Result / Predicted-vs-actual / Lesson lines as applicable). That log is what makes the dataset reproducible.
What ships with it
6 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.
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.
- 5d ago First seen · 197 lines · 108 tokens per session scan A fe28bc5bbcd3
tune-data is a skill published in the GitHub repository rchaz/tunelab (6 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 4,426 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
implementing-llms-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.
tinker-fine-tuning
Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.
colab-finetuning
Fine-tune LLMs on Google Colab GPUs directly from openscience. Connects to Colab runtimes via WebSocket bridge for remote training with Unsloth. Supports SFT, GRPO, DPO, vision, and TTS workflows on free T4 to Pro A100 GPUs.
llm-integration
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.
peft-fine-tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.