tinker-research

tinker-research is a skill for Claude Code from gvkhosla/pi-tinker. It costs 54 tokens per session (439 once invoked), scanned A, original, Apache-2.0.

A research workflow for Tinker, a system used to train, evaluate, and deploy machine-learning models. It covers supervised fine-tuning, preference training, distillation, model selection, and experiments.

In plain words
What is it for?
Use it to plan or run training experiments, compare a baseline, evaluate models, perform smoke tests, and deploy a trained model.
Why use it?
It gives model-training work a defined path for choosing models, evaluating results, and running approved experiments.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery.

Good fit Use it to plan or run training experiments, compare a baseline, evaluate models, perform smoke tests, and deploy a trained model.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gvkhosla/pi-tinker/tinker-research
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 gvkhosla/pi-tinker --skill tinker-research
Clone the repo
git clone --depth 1 https://github.com/gvkhosla/pi-tinker

Made for: Claude Code.

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 tinker-research

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gvkhosla/pi-tinker/tinker-research"><img src="https://agentmods.dev/badge/skills/gvkhosla/pi-tinker/tinker-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 439 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 18
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00054 $0.00439
Opus 5 $0.00027 $0.00219
Sonnet 5 $0.00011 $0.00088
Haiku 4.5 $0.00005 $0.00044

Measured 9d ago against content hash 2eeb6dd38832, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tinker-research 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 9d 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.

skills/tinker-research/SKILL.md · 42 lines

What it actually says

Tinker research (Pi overlay)

Do not duplicate Tinker Cookbook. The canonical research skill, recipes, eval framework, and model lineup live upstream.

Canonical source

/plugin marketplace add thinking-machines-lab/tinker-cookbook

Then use /tinker:research (and /tinker:inkling when the model is Inkling). Live models: https://tinker-docs.thinkingmachines.ai/tinker/models/

If the Cookbook plugin is not installed, clone thinking-machines-lab/tinker-cookbook and read skills/research/SKILL.md plus tinker_cookbook/recipes/.

What Pi owns

Use the /tinker operator (or pi-tinker-agent) for the beginner loop. Do not hide Cookbook Python behind a new framework.

/tinker demo
/tinker improve <data> --goal "..." --budget demo
/tinker doctor
/tinker eval baseline --yes
/tinker smoke train_sft.py --yes
/tinker deploy latest

Default model is thinkingmachines/Inkling-Small. Use full Inkling only if the user asks. Never start API-using stages without --yes or explicit approval.

Hard rules

  • Resolve renderers with model_info.get_recommended_renderer_name. Never hardcode.
  • Eval before training. Prefer Cookbook run_benchmarks for public benches; keep /tinker eval for the user's task JSONL.
  • Check retired models before training. Llama 3.x is not a live Tinker default.
  • Weight export is Cookbook tinker_cookbook.weights, generated by /tinker deploy. Do not invent a vLLM stack.
  • Inkling serving stays on Tinker. See /skill:tinker-inkling.
Files

What ships with it

1 file 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. 9d ago First seen · 42 lines · 54 tokens per session scan A 2eeb6dd38832

Subscribe to this mod's changes

tinker-research is a skill published in the GitHub repository gvkhosla/pi-tinker (24 stars, last pushed 12d ago), licensed Apache-2.0. It adds 54 tokens to every session and 439 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

davila7/claude-code-templates · 69 tokens

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

OpenLAIR/dr-claw · 69 tokens

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Orchestra-Research/AI-Research-SKILLs · 69 tokens

Training

Guides fine-tuning and post-training work with explicit data, objective, hardware, and rollback assumptions.

agentic-in/elephant-agent · 23 tokens

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

liortesta/ClawdAgent · 69 tokens

model_finetuning

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

vuralserhat86/antigravity-agentic-skills · 67 tokens