Loop Architect
fabricioctelles/skills
Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them.
Autonomously optimize a Claude Code skill or agent system by running it repeatedly, scoring outputs against evals, mutating owned artifacts (prompt, references, scripts, agent definitions), and…
Install Autoresearch
The automated check flagged lines worth reading first. See the safety section below.
$ npx skills add byungjunjang/jangpm-meta-skills --skill autoresearch -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install byungjunjang/jangpm-meta-skills 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/byungjunjang/jangpm-meta-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/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/byungjunjang/jangpm-meta-skills/tree/main/.claude/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/byungjunjang/jangpm-meta-skills/tree/main/.claude/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 byungjunjang/jangpm-meta-skills --skill autoresearch -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install byungjunjang/jangpm-meta-skills autoresearch --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/byungjunjang/jangpm-meta-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/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/byungjunjang/jangpm-meta-skills/tree/main/.claude/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 byungjunjang/jangpm-meta-skills --skill autoresearch -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install byungjunjang/jangpm-meta-skills autoresearch --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/byungjunjang/jangpm-meta-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/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/byungjunjang/jangpm-meta-skills/tree/main/.claude/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/byungjunjang/jangpm-meta-skills.git --path .claude/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 byungjunjang/jangpm-meta-skills --skill autoresearch -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install byungjunjang/jangpm-meta-skills autoresearch --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/byungjunjang/jangpm-meta-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/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/byungjunjang/jangpm-meta-skills/tree/main/.claude/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 byungjunjang/jangpm-meta-skills 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 byungjunjang/jangpm-meta-skills --skill autoresearch -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/byungjunjang/jangpm-meta-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/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/byungjunjang/jangpm-meta-skills/tree/main/.claude/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 byungjunjang/jangpm-meta-skills --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 byungjunjang/jangpm-meta-skills autoresearch --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/byungjunjang/jangpm-meta-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/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/byungjunjang/jangpm-meta-skills/tree/main/.claude/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
- 120
- Token cost
- ~6k tokens
- SKILL.md length
- 3,254 words
- Files
- 8 (incl. references)
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- None found
At a glance
Autonomously optimize a Claude Code skill or agent system by running it repeatedly, scoring outputs against evals, mutating owned artifacts (prompt, references, scripts, agent definitions), and…
- Works in 10 steps: gather context → read the skill → build the eval suite → …
- The user asks to run autoresearch
- SKILL.md covers When NOT to use this skill, the core job, project setup (required) and step 0: gather context, plus 13 more sections
- Calls git and python
What it does
Autoresearch is an agent skill from byungjunjang/jangpm-meta-skills. Autonomously optimize a Claude Code skill or agent system by running it repeatedly, scoring outputs against evals, mutating owned artifacts (prompt, references, scripts, agent definitions), and keeping improvements. Karpathy's autoresearch methodology. Trigger when the user asks to run autoresearch, or to optimize, benchmark, or run evals on a skill or agent. Also trigger on 스킬 개선, 스킬 최적화, 스킬 벤치마크, 스킬 평가, 에이전트 개선, 에이전트 최적화.
Its SKILL.md is about 6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `references/dashboard-guide.md`, `references/eval-guide.md` and `references/execution-guide.md`).
It sits in Agent Workflows, covering Autonomous loops and LLM evaluation. The repository describes itself as: AI에게 일을 시키는 프롬프트가 아닌, AI가 일하는 방식을 설계하는 메타 스킬 4종 — 설계(blueprint) · 인터뷰(deep-dive) · 개선(reflect) · 자기 검증개선(autoresearch).
When your agent uses it
- The user asks to run autoresearch
- Run evals on a skill
Example prompts
- “/autoresearch”
Requirements
- Python 3
Workflow steps
10 steps, taken from the step headings in SKILL.md.
- gather context
- read the skill
- build the eval suite
- define the live dashboard
- define the run harness
- establish baseline (or resume)
- human review phase (optional)
- run the autonomous experiment loop
- maintain the logs
- deliver results
What it can do on your machine
Read from SKILL.md and the folder at commit 41af514. 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
Shell commands in SKILL.md call:
gitpython
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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 6k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 110 tokens; SKILL.md has 3,254 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: warnings
The automated check found patterns that need a careful read before installing.
- WarningTells the agent its actions are pre-authorized / not to stop for confirmationSKILL.md:233
**NEVER STOP.** Once the loop starts, never pause to ask for confirmation. The user may be away. Keep running until the
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); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 3,254 words (~6,028 tokens).
“One-off skill edits — fixing a typo, tweaking a sentence, adding a description or a small rule — do not need an experiment loop. Just edit the skill file directly. Use autoresearch only when iterative run-score-mutate evaluation is actually wanted.”
- name
- autoresearch
Files
SKILL.md and 7 other files (references) in .claude/skills/autoresearch of byungjunjang/jangpm-meta-skills.
- SKILL.md
- references/dashboard-guide.md
- references/eval-guide.md
- references/execution-guide.md
- references/logging-guide.md
- references/mutation-guide.md
- references/pipeline-guide.md
- references/worked-example.md
Open the folder on GitHubat commit 41af514
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 skillbyungjunjang/jangpm-meta-skills | 120 | — | ~6k | Automated safety check: Warn | None | |
| Loop Architectfabricioctelles/skills | 106 | — | ~2.1k | Automated safety check: Notes | MIT | |
| Improving MCP ToolsPostHog/posthog | 40k | — | ~1.5k | Automated safety check: Pass | Custom licence | |
| Inngest AgentsAsymmetric-al/core | 381 | — | ~2.6k | Automated safety check: Pass | AGPL-3.0 | |
| Author Skillericrisco/rsc-harness | 180 | — | ~4.3k | Automated safety check: Pass | MIT | |
| Agents Best PracticesDenisSergeevitch/agents-best-practices | 2.4k | — | ~7.4k | Automated safety check: Pass | MIT |
Similar skills
- Official
Improving MCP Tools
PostHog/posthog
Run an improve-my-MCP campaign: an autoresearch-style loop that measures the MCP agent experience with the eval harness, picks the highest-impact tool problem from production data, makes one bounded…
Inngest Agents
Asymmetric-al/core
A skill your agent uses when building durable AI agents or agentic workflows with Inngest and AgentKit, including model calls, tool calls, multi-agent networks, human approval, realtime progress…
Author Skill
ericrisco/rsc-harness
A skill your agent uses when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into…
Agents Best Practices
DenisSergeevitch/agents-best-practices
A skill your agent uses when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain.
Autocontext Knowledge Creator
greyhaven-ai/autocontext
Runs the `autoctx` CLI to improve an approach to a task over several generations, score or refine a single output and inspect what a run produced.
More from byungjunjang/jangpm-meta-skills
Blueprint
byungjunjang/jangpm-meta-skills
Agentic system design blueprint generator. An agent skill from byungjunjang/jangpm-meta-skills.
Blueprint
byungjunjang/jangpm-meta-skills
Codex용 자동화 에이전트 시스템 설계서 생성 스킬. An agent skill from byungjunjang/jangpm-meta-skills.
Deep Dive
byungjunjang/jangpm-meta-skills
Socratic interview skill to deepen a spec or refine an existing agent blueprint.
Deep Dive
byungjunjang/jangpm-meta-skills
A Codex skill for Socratic interviews that deepen a spec or refine an existing agent blueprint.
Reflect
byungjunjang/jangpm-meta-skills
Session wrap-up and fix-learning capture skill. An agent skill from byungjunjang/jangpm-meta-skills.
Reflect
byungjunjang/jangpm-meta-skills
Session wrap-up and fix-learning capture skill for Codex. An agent skill from byungjunjang/jangpm-meta-skills.
Related
Categories
Questions about Autoresearch
What does Autoresearch do?
Autonomously optimize a Claude Code skill or agent system by running it repeatedly, scoring outputs against evals, mutating owned artifacts (prompt, references, scripts, agent definitions), and…. Autoresearch is an agent skill from byungjunjang/jangpm-meta-skills. Autonomously optimize a Claude Code skill or agent system by running it repeatedly, scoring outputs against evals, mutating owned artifacts (prompt, references, scripts, agent definitions), and keeping improvements.
When should I use Autoresearch?
Autoresearch fits situations like: the user asks to run autoresearch; run evals on a skill.
How do I install Autoresearch in Claude Code?
Run `npx skills add byungjunjang/jangpm-meta-skills --skill autoresearch -a claude-code`. Or copy the skill folder (.claude/skills/autoresearch in byungjunjang/jangpm-meta-skills) 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 byungjunjang/jangpm-meta-skills --skill autoresearch -a codex`. Or copy the skill folder (.claude/skills/autoresearch in byungjunjang/jangpm-meta-skills) 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 byungjunjang/jangpm-meta-skills --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 the command-line tools its instructions call (git and python). Our summary lists: Python 3.
Does Autoresearch access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Autoresearch safe to install?
Our automated static check of SKILL.md flagged 1 warning(s): tells the agent its actions are pre-authorized / not to stop for confirmation. Read the flagged lines before installing; the check is not a guarantee either way.
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 6k tokens (SKILL.md is roughly 24k 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 9.7k 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: Loop Architect (fabricioctelles/skills, 106 stars), Improving MCP Tools (PostHog/posthog, 40k stars), Inngest Agents (Asymmetric-al/core, 381 stars) and Author Skill (ericrisco/rsc-harness, 180 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Autoresearch?
byungjunjang (a GitHub user) maintains it in byungjunjang/jangpm-meta-skills, which has 120 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on August 5, 2026.
Source: byungjunjang/jangpm-meta-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.