labrat
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/fcakyon/labrat with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/fcakyon/labrat'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/fcakyon-phd-skills)HTML
<a href="/listings/fcakyon-phd-skills"><img src="/api/listings/fcakyon-phd-skills/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
<details open> <summary><b>Claude Code</b></summary>
claude plugin marketplace add fcakyon/labrat claude plugin install labrat@labrat
Update with `claude plugin update labrat@labrat`.
Coming from phd-skills? Remove it first with `claude plugin uninstall phd-skills@phd-skills` and `claude plugin marketplace remove phd-skills`.
</details>
<details> <summary><b>Claude.ai and Claude Desktop</b></summary>
Open **Customize**, then **Plugins**. Select **Add**, then **Add marketplace**, choose **Add from a repository** and enter `fcakyon/labrat`. Install Lab Rat from the **Discover** tab.
Needs a paid plan. Chat runs the skills. The plugin also syncs to Claude Code when you sign in there with the same account.
</details>
<details> <summary><b>Codex</b></summary>
codex plugin marketplace add fcakyon/labrat codex plugin add labrat@labrat
Update with `codex plugin marketplace upgrade labrat`.
</details>
<details> <summary><b>Cursor</b></summary>
cursor-agent plugin marketplace add https://github.com/fcakyon/labrat
Then start `cursor-agent`, enter `/plugin` and install Lab Rat. To update, run `cursor-agent plugin marketplace remove labrat`, add it again and reinstall.
</details>
<details> <summary><b>Gemini CLI</b></summary>
git clone https://github.com/fcakyon/labrat ~/.labrat gemini extensions link ~/.labrat/plugin
Update with `git -C ~/.labrat pull`.
</details>
Every tool gets the same 11 skills. The research peer review and notifications run in Claude Code only. Paper search needs [Paper Search CLI](https://github.com/fcakyon/paper-search-cli) (uv, Python 3.10+, [setup](plugin/skills/literature-research/references/paper-search.md)), nothing else does. Optional: `/labrat:setup` shows what it detected and turns on extras like notifications to ntfy, Slack or email, the command allowlist and LaTeX.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 41 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- {
- "name": "labrat",
- "owner": {
- "name": "Fatih Cagatay Akyon",
- "url": "https://scholar.google.com/citations?user=RHGyDE0AAAAJ"
- },
- "metadata": {
- "description": "Lab Rat: catch AI mistakes before they cost weeks of compute. Reproduce papers from arxiv. Debug runs evidence-first. Compare experiments at the right epoch. Launch with discipline."
- },
- "plugins": [
- {
- "name": "labrat",
- "displayName": "Lab Rat",
- "source": {
- "source": "git-subdir",
- "url": "https://github.com/fcakyon/labrat.git",
- "path": "plugin"
- },
- "description": "Lab Rat: catch AI mistakes before they cost weeks of compute. Reproduce papers from arxiv. Debug runs evidence-first. Compare experiments at the right epoch. Launch with discipline.",
- "version": "2.0.0",
- "author": {
- "name": "Fatih Cagatay Akyon"
- },
- "homepage": "https://github.com/fcakyon/labrat",
- "repository": "https://github.com/fcakyon/labrat",
- "license": "MIT",
- "keywords": [
- "research",
- "academic",
- "phd",
- "paper-reproduction",
- "debugging",
- "experiment-analysis",
- "citations",
- "latex"
- ],
- "category": "productivity",
- "tags": ["research", "academic", "latex", "ml-experiments"]
- }
- ]
- }
README.md · README · 136 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- <p align="center">
- <picture>
- <source media="(prefers-color-scheme: dark)" srcset="assets/wordmark-dark.svg" />
- <img src="assets/wordmark-light.svg" alt="Lab Rat" width="360" height="112" />
- </picture>
- </p>
- Lab Rat teaches your AI coding agent to work like a careful ML researcher: reproduce papers, launch and compare runs at the same epoch, and check every claim before it costs you weeks of compute.
- <p align="center">
- <a href="#install">
- <picture>
- <source media="(prefers-color-scheme: dark)" srcset="assets/tools-dark.svg" />
- <img src="assets/tools-light.svg" alt="Works in Claude Code, Codex, Cursor and Gemini CLI" width="454" height="24" />
- </picture>
- </a>
- </p>
- Built by [Fatih Cagatay Akyon](https://scholar.google.com/citations?user=RHGyDE0AAAAJ) (2000+ citations, 5 patents) from 2200+ Claude Code and Codex sessions. Every guardrail traces to a real mistake.
- <picture>
- <source media="(prefers-color-scheme: dark)" srcset="assets/flow-dark.svg" />
- <img src="assets/flow-light.svg" alt="Find papers, reproduce, design, launch, compare and publish, with compare looping back to design for the next experiment" width="980" />
- </picture>
- ## Install
- <details open>
- <summary><b>Claude Code</b></summary>
- ```sh
- claude plugin marketplace add fcakyon/labrat
- claude plugin install labrat@labrat
- ```
- Update with `claude plugin update labrat@labrat`.
- Coming from phd-skills? Remove it first with `claude plugin uninstall phd-skills@phd-skills` and `claude plugin marketplace remove phd-skills`.
- </details>
- <details>
- <summary><b>Claude.ai and Claude Desktop</b></summary>
- Open **Customize**, then **Plugins**. Select **Add**, then **Add marketplace**, choose **Add from a repository** and enter `fcakyon/labrat`. Install Lab Rat from the **Discover** tab.
- Needs a paid plan. Chat runs the skills. The plugin also syncs to Claude Code when you sign in there with the same account.
- </details>
- <details>
- <summary><b>Codex</b></summary>
- ```sh
- codex plugin marketplace add fcakyon/labrat
- codex plugin add labrat@labrat
- ```
- Update with `codex plugin marketplace upgrade labrat`.
- </details>
- <details>
- <summary><b>Cursor</b></summary>
- ```sh
- cursor-agent plugin marketplace add https://github.com/fcakyon/labrat
- ```
- Then start `cursor-agent`, enter `/plugin` and install Lab Rat. To update, run `cursor-agent plugin marketplace remove labrat`, add it again and reinstall.
- </details>
- <details>
- <summary><b>Gemini CLI</b></summary>
- ```sh
- git clone https://github.com/fcakyon/labrat ~/.labrat
- gemini extensions link ~/.labrat/plugin
- ```
- Update with `git -C ~/.labrat pull`.
- </details>
- Every tool gets the same 11 skills. The research peer review and notifications run in Claude Code only. Paper search needs [Paper Search CLI](https://github.com/fcakyon/paper-search-cli) (uv, Python 3.10+, [setup](plugin/skills/literature-research/references/paper-search.md)), nothing else does. Optional: `/labrat:setup` shows what it detected and turns on extras like notifications to ntfy, Slack or email, the command allowlist and LaTeX.
- ## Why
- AI agents make research mistakes that cost weeks of compute. Real ones from my sessions:
- - It read "done?" as "dont?" and started uploading thousands of files.
- - It restarted a 50-hour training job without diffing the config against the reference run. Three days lost.
- - It killed an experiment over a proxy metric that had not converged, before the downstream eval could show the real result.
- - It ran `rm -rf` on a path it remembered wrong and deleted local checkpoints.
- The skills teach the method, not a script, so the agent writes code for your setup (wandb, neptune, local files) and stops to check the evidence before it claims a result.
- ## Skills
- A skill starts when you describe its task, or run it as `/labrat:<skill>`.
- | Say | Skill |
- | --- | --- |
- | "find related papers on X", "find gaps in the literature on X" | [literature-research](plugin/skills/literature-research/SKILL.md) |
- | `/labrat:reproduce arxiv 2508.12345` | [reproduce](plugin/skills/reproduce/SKILL.md), from the paper to replication runs |
- | "design an ablation study" | [experiment-design](plugin/skills/experiment-design/SKILL.md) |
- | "launch the new training run" | [launch](plugin/skills/launch/SKILL.md), with a pre-flight checklist |
- | "why is my loss diverging?" | [debug](plugin/skills/debug/SKILL.md), evidence before fixes |
- | "compare run alpha to baseline" | [compare](plugin/skills/compare/SKILL.md), at the same epoch |
- | "analyze dataset bias" | [dataset-curation](plugin/skills/dataset-curation/SKILL.md) |
- | "check my numbers match the code", "verify my BibTeX", "prepare code for release" | [paper-check](plugin/skills/paper-check/SKILL.md) |
- | "review my methods section", "set up LaTeX for CVPR" | [paper-write](plugin/skills/paper-write/SKILL.md) |
- | "what will reviewers ask?", "pick my strongest ablations" | [rebuttal](plugin/skills/rebuttal/SKILL.md) |
- | `/labrat:setup` | [setup](plugin/skills/setup/SKILL.md) |
- In Claude Code, a fresh-context research peer [hook](plugin/hooks/claude-hooks.json) checks each conclusion against the actual artifacts and sends you to the matching skill, like the launch checklist before a run.
- For long runs, pair it with `/loop 30m check experiment logs, notify me if metrics beat the baseline or if loss starts to diverge`.
- ## Star history
- <a href="https://www.star-history.com/#fcakyon/labrat&Date">
- <picture>
- <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=fcakyon/labrat&type=Date&theme=dark" />
- <img alt="Lab Rat star history" src="https://api.star-history.com/svg?repos=fcakyon/labrat&type=Date" />
- </picture>
- </a>
- ## Contributors
- <a href="https://github.com/fcakyon/labrat/graphs/contributors">
- <img alt="Contributors" src="https://contrib.rocks/image?repo=fcakyon/labrat" />
- </a>
- MIT license.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.