tinker-inkling

tinker-inkling is a skill for Claude Code, Codex from gvkhosla/pi-tinker. It costs 66 tokens per session (702 once invoked), scanned A, original, Apache-2.0.

A guide for training and evaluating Inkling language models through Tinker, a service and toolkit for model training. It covers smaller and full Inkling models, including versions that support longer prompts.

In plain words
What is it for?
It helps write sampling, evaluation, synthetic-data, and post-training workflows for Inkling and Inkling-Small.
Why use it?
It records the correct model, renderer, tokenizer, setup, and thinking-effort settings, avoiding mismatched training or evaluation code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps write sampling, evaluation, synthetic-data, and post-training workflows for Inkling and Inkling-Small.

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

Made for: Claude Code, 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 tinker-inkling

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gvkhosla/pi-tinker/tinker-inkling"><img src="https://agentmods.dev/badge/skills/gvkhosla/pi-tinker/tinker-inkling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 702 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 pass 7 Sept 2026
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 $0.00066 $0.00702
Opus 5 $0.00033 $0.00351
Sonnet 5 $0.00013 $0.00140
Haiku 4.5 $0.00007 $0.00070

Measured 9d ago against content hash 14c91c3597e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tinker-inkling 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-inkling/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inkling in Pi

Thinking Machines' models for Tinker. Same renderer (tml_v0), tokenizer, and effort interface.

Id Size When
thinkingmachines/Inkling-Small 276B / 12B active, 64K ctx Default. Coding, grading, synthetic data, cheaper runs.
thinkingmachines/Inkling-Small:peft:262144 small, 256K ctx Efficient long-context inference/training.
thinkingmachines/Inkling 975B / 41B active, 64K ctx Only if the user asks for full Inkling.
thinkingmachines/Inkling:peft:262144 full, 256K ctx Full long-context inference/training.

Both are post-trained starting points, not base models.

Setup

uv pip install -U tinker-cookbook

Needs Python 3.11+, Tinker SDK 0.23+, torch>=2.10. tml-renderers is included. There is no [inkling] extra.

/tinker inkling
/model
/tinker inkling sweep --prompt "representative task" --efforts low,medium,high,xhigh --yes

Never tokenizer.encode() a chat prompt. Never hardcode the renderer name — use model_info.get_recommended_renderer_name.

Effort

Finite scalar in [0.0, 1.0). Renderer inserts the effort system message. Set it at sampling and when building training data. Default if omitted is 0.9 (high) — make that deliberate.

none minimal low medium high xhigh
0.0 0.1 0.2 0.7 0.9 0.99
  • Same effort for train data, baseline eval, and checkpoint eval.
  • Effort and max_tokens are independent. High effort can need 16k+.
  • Eval at temperature=1.0. Lowering temperature is not a substitute for lowering effort.
  • effort=0.0 conditions toward no reasoning; it is not a hard off switch.

Serving

Stay on Tinker. Cookbook has no Inkling merge/PEFT path. /tinker deploy writes API clients and a SERVING.md that says so. Do not send Inkling to HTDYM or vLLM.

Training

Cookbook get_lr("thinkingmachines/Inkling") raises NotImplementedError. Calibrate LR. Watch entropy. Prefer Small unless quality on the user's eval requires full Inkling.

Read the full file on GitHub · 57 lines

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 · 57 lines · 66 tokens per session scan A 14c91c3597e6

Subscribe to this mod's changes

tinker-inkling is a skill published in the GitHub repository gvkhosla/pi-tinker (24 stars, last pushed 12d ago), licensed Apache-2.0. It adds 66 tokens to every session and 702 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