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 skills add gvkhosla/pi-tinker --skill tinker-researchgit clone --depth 1 https://github.com/gvkhosla/pi-tinkerWrote 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/gvkhosla/pi-tinker/tinker-research)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00054 | $0.00439 |
| Opus 5 | $0.00027 | $0.00219 |
| Sonnet 5 | $0.00011 | $0.00088 |
| Haiku 4.5 | $0.00005 | $0.00044 |
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.
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_benchmarksfor public benches; keep/tinker evalfor 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.
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.
- 9d ago First seen · 42 lines · 54 tokens per session scan A 2eeb6dd38832
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.
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.
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.
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.
Training
Guides fine-tuning and post-training work with explicit data, objective, hardware, and rollback assumptions.
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.
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.