LoopX Auto-Research Worker
loopx-project/loopx
Role playbook for a LoopX worker running an auto-research lane, with execution checklists, artifact contracts and stop conditions.
Run rigorous end-to-end autonomous ML and AI research after a user provides a dataset, target, and research budget.
Install Autoresearch
$ npx skills add haibarazz/awesome-codex-research --skill autoresearch -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install haibarazz/awesome-codex-research autoresearch --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/haibarazz/awesome-codex-research.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/autoresearch .claude/skills/autoresearch && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "autoresearch" agent skill from https://github.com/haibarazz/awesome-codex-research/tree/main/skills/autoresearch into .claude/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/haibarazz/awesome-codex-research/tree/main/skills/autoresearchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add haibarazz/awesome-codex-research --skill autoresearch -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install haibarazz/awesome-codex-research autoresearch --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/haibarazz/awesome-codex-research.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/autoresearch .agents/skills/autoresearch && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "autoresearch" agent skill from https://github.com/haibarazz/awesome-codex-research/tree/main/skills/autoresearch into .agents/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add haibarazz/awesome-codex-research --skill autoresearch -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install haibarazz/awesome-codex-research autoresearch --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/haibarazz/awesome-codex-research.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/autoresearch .cursor/skills/autoresearch && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "autoresearch" agent skill from https://github.com/haibarazz/awesome-codex-research/tree/main/skills/autoresearch into .cursor/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/haibarazz/awesome-codex-research.git --path skills/autoresearch--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add haibarazz/awesome-codex-research --skill autoresearch -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install haibarazz/awesome-codex-research autoresearch --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/haibarazz/awesome-codex-research.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/autoresearch .gemini/skills/autoresearch && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "autoresearch" agent skill from https://github.com/haibarazz/awesome-codex-research/tree/main/skills/autoresearch into .gemini/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install haibarazz/awesome-codex-research autoresearchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add haibarazz/awesome-codex-research --skill autoresearch -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/haibarazz/awesome-codex-research.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/autoresearch .github/skills/autoresearch && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "autoresearch" agent skill from https://github.com/haibarazz/awesome-codex-research/tree/main/skills/autoresearch into .github/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add haibarazz/awesome-codex-research --skill autoresearch -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install haibarazz/awesome-codex-research autoresearch --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/haibarazz/awesome-codex-research.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/autoresearch .opencode/skills/autoresearch && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "autoresearch" agent skill from https://github.com/haibarazz/awesome-codex-research/tree/main/skills/autoresearch into .opencode/skills/autoresearch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "autoresearch", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
autoresearch- GitHub stars
- 100
- Token cost
- ~2.2k tokens
- SKILL.md length
- 919 words
- Files
- 105 (incl. scripts, references, assets)
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- None found
At a glance
Run rigorous end-to-end autonomous ML and AI research after a user provides a dataset, target, and research budget.
- Works in 5 steps: infer exactly one current Phase from the… → consider only PHASE documents whose… → among those documents, read only files… → …
- AutoResearch must inspect
- SKILL.md covers Mandatory First Read, Activation Router, Codebase Bootstrap Boundary and Runtime Boundary, plus 3 more sections
- Runs JavaScript scripts from its folder; calls python3
What it does
Autoresearch is an agent skill from haibarazz/awesome-codex-research. Run rigorous end-to-end autonomous ML and AI research after a user provides a dataset, target, and research budget. Use when AutoResearch must inspect or safely bootstrap a missing codebase with ReproFlow, align and freeze the research brief, then independently analyze literature, reproduce methods, run and repair experiments, promote research bases, and continue until the performance target is reached or the preregistered budget is exhausted, while remaining reproducible and avoiding pseudo-innovation.
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 110 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/schemas/experiment_graph.schema.json` and `assets/schemas/runtime_request.schema.json`).
It sits in Agent Workflows, covering Autonomous loops and Deep research.
When your agent uses it
- AutoResearch must inspect
- Safely bootstrap a missing codebase with ReproFlow
- Align and freeze the research brief
- Then independently analyze literature
Example prompts
- “/autoresearch”
Requirements
- Python 3
- Node.js
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- infer exactly one current Phase from the frozen contracts and project artifacts;
- consider only PHASE documents whose activation.phases includes that Phase;
- among those documents, read only files whose read_when matches the immediate action;
- read ON_DEMAND files only while generating, updating, or validating their artifact;
- complete the current action and its exit checks before selecting the next Phase.
What it can do on your machine
Read from SKILL.md and the folder at commit e3ca125. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Autoresearch loads about 2.2k tokens when it runs, and up to ~40k if it reads all its reference files. Until then it costs about 130 tokens; SKILL.md has 919 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 919 words (~2,222 tokens).
“Use this project-local skill when the user wants to provide a dataset and research target, complete one startup alignment, and then delegate the entire research process to AI. After the Research Brief is frozen, the AI runs the evidence-producing research…”
- name
- autoresearch
Files
SKILL.md and 104 other files (scripts, references, assets) in skills/autoresearch of haibarazz/awesome-codex-research.
- SKILL.md
- agents/openai.yaml
- assets/candidate_priority_combinations.csv
- assets/schemas/experiment_graph.schema.json
- assets/schemas/runtime_request.schema.json
- assets/schemas/runtime_response.schema.json
- assets/schemas/runtime_state.schema.json
- assets/workflow.css
- assets/workflow.js
- examples/golden-run/.autoresearch/runtime_state.json
- examples/golden-run/BENCHMARK.md
- examples/golden-run/EXPERIMENT_GRAPH.html
- examples/golden-run/EXPERIMENT_GRAPH.json
- examples/golden-run/README.md
- examples/golden-run/RESEARCH_BRIEF.md
- … and 90 more
Open the folder on GitHubat commit e3ca125
Compare with similar skills
Autoresearch next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Autoresearch this skillhaibarazz/awesome-codex-research | 100 | — | ~2.2k | Automated safety check: Pass | None | |
| LoopX Auto-Research Workerloopx-project/loopx | 6.2k | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | |
| Slate Ar Qualityudecode/plate | 17k | — | ~474 | Automated safety check: Pass | Custom licence | |
| Show Me Your Work Decision Logcursor/plugins | 11k | 8 repos | ~1.6k | Automated safety check: Pass | None | |
| Autoresearch Iteration Loopuditgoenka/autoresearch | 6.5k | 1 repos | ~2k | Automated safety check: Pass | MIT | |
| Bounded AutoresearchAgriciDaniel/claude-obsidian | 15k | — | ~1.6k | Automated safety check: Pass | MIT |
Similar skills
Slate Ar Quality
udecode/plate
Slate v2 quality-gap Autoresearch shortcut. An agent skill from udecode/plate.
- Official
Show Me Your Work Decision Log
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
Autoresearch Iteration Loop
uditgoenka/autoresearch
Runs an autonomous modify, verify, keep-or-discard loop against any metric, with subcommands for planning, debugging, fixing, security audits, shipping and more.
Bounded Autoresearch
AgriciDaniel/claude-obsidian
Runs a bounded, source-grounded research loop that drafts a cited dossier and can propose a separately reviewed merge into an Obsidian vault.
Install Loop Engineering
cobusgreyling/loop-engineering
Installs Loop Engineering into a project through the single @cobusgreyling/loop CLI, scaffolding a report-only loop and a readiness score.
More from haibarazz/awesome-codex-research
All 9 skills in this repoCds Method Innovation
haibarazz/awesome-codex-research
Guide a complete baseline-first ML or computational data-science method-innovation project, from workspace and direction discovery through finding and running common and recent baselines, diagnosing…
Autodl Remote
haibarazz/awesome-codex-research
A skill your agent uses when the host coding agent should control an AutoDL or SSH server from the local machine, run remote commands, and explicitly upload or download selected files.
Autodl Remote Tmux
haibarazz/awesome-codex-research
A skill your agent uses when AutoDL Remote should run or monitor long remote jobs through tmux panes.
Auto Exp
haibarazz/awesome-codex-research
Plan, execute, monitor, verify, compare, and document reproducible machine-learning experiments.
Research Literature Review
haibarazz/awesome-codex-research
面向信息系统计算设计科学（CDS）研究，根据用户的数据、研究情境与研究问题，分别识别问题／理论视角和技术／算法两条文献对话线，检索并核验全文，制作可追溯的文献对话地图，最终澄清研究的最近邻、理论祖先、方法缺口与可辩护定位。适用于选题定位、相关工作规划、方法定位和后续综述；核心不是代写文献综述。
Review Comment Decomposer
haibarazz/awesome-codex-research
结合论文原文拆解审稿意见为最小可回应原子问题，规划补实验与回复构思两条工作线，归组共同关切，并输出带忠实中文翻译注释、每条 comment 一份建议逻辑和原子点英文小标题的可编译 LaTeX 回复骨架。用于返修规划、review decomposition、atomic concerns、rebuttal strategy 和回复信模板生成；完整回复正文留待作者后续撰写。
Related
Categories
Questions about Autoresearch
What does Autoresearch do?
Run rigorous end-to-end autonomous ML and AI research after a user provides a dataset, target, and research budget. Autoresearch is an agent skill from haibarazz/awesome-codex-research. Run rigorous end-to-end autonomous ML and AI research after a user provides a dataset, target, and research budget.
When should I use Autoresearch?
Autoresearch fits situations like: autoResearch must inspect; safely bootstrap a missing codebase with ReproFlow; align and freeze the research brief; then independently analyze literature.
How do I install Autoresearch in Claude Code?
Run `npx skills add haibarazz/awesome-codex-research --skill autoresearch -a claude-code`. Or copy the skill folder (skills/autoresearch in haibarazz/awesome-codex-research) into .claude/skills/autoresearch in your project. Claude Code loads it when a task matches its description.
How do I install Autoresearch in Codex?
Run `npx skills add haibarazz/awesome-codex-research --skill autoresearch -a codex`. Or copy the skill folder (skills/autoresearch in haibarazz/awesome-codex-research) into .agents/skills/autoresearch in your project. Codex loads it when a task matches its description.
Can I use Autoresearch in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add haibarazz/awesome-codex-research --skill autoresearch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/autoresearch, .gemini/skills/autoresearch, .github/skills/autoresearch and .opencode/skills/autoresearch in your project.
What does Autoresearch need to run?
Going by SKILL.md and its folder, Autoresearch needs JavaScript for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3; Node.js.
Does Autoresearch access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Autoresearch safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Autoresearch use?
No licence was found for Autoresearch or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Autoresearch use?
About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 38k tokens, read only when the agent opens those files.
What are the alternatives to Autoresearch?
Skills that share tags, products or a category with Autoresearch: LoopX Auto-Research Worker (loopx-project/loopx, 6.2k stars), Slate Ar Quality (udecode/plate, 17k stars), Show Me Your Work Decision Log (cursor/plugins, 11k stars) and Autoresearch Iteration Loop (uditgoenka/autoresearch, 6.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Autoresearch?
haibarazz (a GitHub user) maintains it in haibarazz/awesome-codex-research, which has 100 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 23, 2026.
Source: haibarazz/awesome-codex-research on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.