synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.
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/synthetic-sciences/openscience/tinker-training-costnpx skills add synthetic-sciences/openscience --skill tinker-training-costgit clone --depth 1 https://github.com/synthetic-sciences/openscienceWrote 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/synthetic-sciences/openscience/tinker-training-cost)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/tinker-training-cost"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/tinker-training-cost.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 | $0.00055 | $0.01823 |
| Opus 5 | $0.00028 | $0.00911 |
| Sonnet 5 | $0.00011 | $0.00365 |
| Haiku 4.5 | $0.00006 | $0.00182 |
Grade A, and why
tinker-training-cost 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 yesterday.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tinker Training Cost Calculator
Calculate training costs for Tinker fine-tuning jobs by tokenizing your dataset with the correct model tokenizer and applying current pricing.
Quick Start
Use the bundled script to calculate training costs:
# List available models and pricing
python scripts/calculate_cost.py --list-models
# Calculate cost for a JSONL dataset
python scripts/calculate_cost.py training_data.jsonl --model Qwen3-8B --epochs 3
# Output as JSON
python scripts/calculate_cost.py training_data.jsonl --model Llama-3.1-70B --json
The script:
- Loads the correct tokenizer for the selected model
- Counts tokens in your JSONL file (supports chat, text, and instruction formats)
- Calculates the estimated training cost
Cost Formula
Training Cost = (total_tokens × epochs × train_price_per_million) / 1_000_000
Where:
total_tokens= tokens in your training dataset (from tokenization)epochs= number of training passes (default: 3)train_price_per_million= model-specific training rate from pricing table
Tinker Pricing
All prices as of January 5, 2026 Source: https://thinkingmachines.ai/tinker/
All prices are in USD per million tokens.
| Category | Description |
|---|---|
| Prefill | Processing input context (inference) |
| Sample | Generating output tokens (inference) |
| Train | Training/fine-tuning tokens |
Qwen Models
| Model | Prefill | Sample | Train |
|---|---|---|---|
| Qwen3-4B-Instruct-2507 | $0.07 | $0.22 | $0.22 |
| Qwen3-8B | $0.13 | $0.40 | $0.40 |
| Qwen3-30B-A3B | $0.12 | $0.30 | $0.36 |
| Qwen3-VL-30B-A3B-Instruct | $0.18 | $0.44 | $0.53 |
| Qwen3-32B | $0.49 | $1.47 | $1.47 |
| Qwen3-235B-Instruct-2507 | $0.68 | $1.70 | $2.04 |
| Qwen3-VL-235B-A22B-Instruct | $1.02 | $2.56 | $3.07 |
Llama Models
| Model | Prefill | Sample | Train |
|---|---|---|---|
| Llama-3.2-1B | $0.03 | $0.09 | $0.09 |
| Llama-3.2-3B | $0.06 | $0.18 | $0.18 |
| Llama-3.1-8B | $0.13 | $0.40 | $0.40 |
| Llama-3.1-70B | $1.05 | $3.16 | $3.16 |
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.
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.
- yesterday First seen · 189 lines · 55 tokens per session scan A 6b06a4abcce9
tinker-training-cost is a skill published in the GitHub repository synthetic-sciences/openscience (3,473 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,823 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 2026-09-03.
Other skills, from other repositories
Training
Guides fine-tuning and post-training work with explicit data, objective, hardware, and rollback assumptions.
ai-engineer
Builds production AI/ML systems — model training, fine-tuning, MLOps pipelines, model serving, evaluation frameworks, RAG optimization, and agent orchestration at scale. Use when the user asks to build, train, or deploy ML models, set up MLOps pipelines, optimize RAG systems, create inference endpoints, or design…
llm-finetuning
LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization.
ml-engineer
Machine learning engineer expert for PyTorch, scikit-learn, model evaluation, and MLOps.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
data-leakage-detection
Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.