A model-training skill for fine-tuning a model, meaning adapting it to behave more like examples, with expert agent work collected from SimLab. It uses Tinker's supervised-learning process, where example outputs guide training.

Use it to fine-tune a model on expert coding-agent trajectories from SimLab.

It provides the stated workflow for turning expert agent trajectories into additional model training.

tinker-sft — Skill for Claude Code and Codex by collinear-ai/simlab

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 collinear-ai/simlab --skill tinker-sft

Clone the repo

git clone --depth 1 https://github.com/collinear-ai/simlab

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/collinear-ai/simlab/tinker-sft/github.svg)](https://agentmods.dev/skills/collinear-ai/simlab/tinker-sft)

Your own site

<a href="https://agentmods.dev/skills/collinear-ai/simlab/tinker-sft"><img src="https://agentmods.dev/badge/skills/collinear-ai/simlab/tinker-sft/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/collinear-ai/simlab/tinker-sft"><img src="https://agentmods.dev/badge/skills/collinear-ai/simlab/tinker-sft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,677 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 unknown 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.02677
Opus 5.5	$0.00000	$0.01071
Sonnet 5.5	$0.00000	$0.00535
Haiku 4.5	$0.00000	$0.00268

Measured 2mo ago against content hash aa0a4609bfa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tinker-sft 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 2mo ago.

The scan reads SKILL.md. This mod also ships 7 executable files (run.sh, scripts/eval_agent.py, scripts/export_sft.py, …), 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.

cookbook/tinker-sft/SKILL.md · 218 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Files

What ships with it

8 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.

2mo ago First seen · 218 lines · 0 tokens per session scan A aa0a4609bfa4

Subscribe to this mod's changes

tinker-sft is a skill published in the GitHub repository collinear-ai/simlab (24 stars, last pushed 3mo ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 2,677 tokens. 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.

Data and AI

tinker-sft next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tinker-sftcollinear-ai/simlab	Skill	24	3mo ago	none	A	0	Claude Code, Codex
agent-platform-model-registrygoogle/skills	Skill	22k	yesterday	Apache-2.0	A	60	Claude Code, Codex
foundry-config-setupmicrosoft/agent-framework	Skill	15k	yesterday	MIT	A	65	Claude Code, Codex
google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skills	Skill	22k	yesterday	Apache-2.0	A	132	Claude Code, Codex
training-checkwanshuiyin/Auto-claude-code-research-in-sleep	Skill	19k	3d ago	MIT	A	35	Claude Code
nemo-automodel-launcher-configNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	30	Claude Code
finetuningmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	132	Claude Code