claude

autoresearch

Name: autoresearch
Author: Hasin Ahmed

Autonomous goal-directed iteration for puku-cli. 14 subcommands: iterate against any metric, plan, debug, fix, security audit, ship, scenario, predict, learn, reason, probe, evals, improve, regression. Inspired by Karpathy's autoresearch loop.

0 on GitHubby Hasin Ahmedv2.2.0-puku.1MITupdated 4 months agoproductivity

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin autoresearch in Hasin-ai/autoresearch-puku. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (14)

autoresearch:debug
Hunt bugs with scientific method: hypothesize, test, falsify, repeat
autoresearch:evals
Analyze iteration results: trends, plateaus, regressions, recommendations
autoresearch:fix
Crush errors one-by-one until zero remain: tests, types, lint, build
autoresearch:improve
Research ICP challenges, discover improvements, generate PRDs
autoresearch:learn
Scout codebase and auto-generate docs — or a navigable wiki knowledge base — with validation-fix loop
autoresearch:plan
Convert a goal into validated Scope, Metric, Direction, Verify config
autoresearch:predict
5 expert personas debate proposed changes before implementation
autoresearch:probe
8 personas interrogate requirements until constraints saturate
autoresearch:reason
Adversarial debate with blind judges until convergence
autoresearch:regression
Layered regression stability gate: capture baseline behavior on the base ref, diff the candidate, verdict STABLE/UNSTABLE before you push
autoresearch:scenario
Generate edge cases across 12 dimensions from a seed scenario
autoresearch:security
STRIDE + OWASP security audit with red-team adversarial personas
autoresearch:ship
Ship anything through 8 phases: checklist, dry-run, deploy, verify
autoresearch
Autonomous iteration loop: modify, verify, keep/discard against any metric

Slash commands (14)

/autoresearch:autoresearch-debug
Hunt bugs with scientific method: hypothesize, test, falsify, repeat
/autoresearch:autoresearch-evals
Analyze iteration results: trends, plateaus, regressions, recommendations
/autoresearch:autoresearch-fix
Crush errors one-by-one until zero remain: tests, types, lint, build
/autoresearch:autoresearch-improve
Research ICP challenges, discover improvements, generate PRDs
/autoresearch:autoresearch-learn
Scout codebase and auto-generate docs — or a navigable wiki knowledge base — with validation-fix loop
/autoresearch:autoresearch-plan
Convert a goal into validated Scope, Metric, Direction, Verify config
/autoresearch:autoresearch-predict
5 expert personas debate proposed changes before implementation
/autoresearch:autoresearch-probe
8 personas interrogate requirements until constraints saturate
/autoresearch:autoresearch-reason
Adversarial debate with blind judges until convergence
/autoresearch:autoresearch-regression
Layered regression stability gate: capture baseline behavior on the base ref, diff the candidate, verdict STABLE/UNSTABLE before you push
/autoresearch:autoresearch-scenario
Generate edge cases across 12 dimensions from a seed scenario
/autoresearch:autoresearch-security
STRIDE + OWASP security audit with red-team adversarial personas
/autoresearch:autoresearch-ship
Ship anything through 8 phases: checklist, dry-run, deploy, verify
/autoresearch:autoresearch
Autonomous iteration loop: modify, verify, keep/discard against any metric

Hooks (13)

PreToolUse
bash "${CLAUDE_PLUGIN_ROOT}/hooks/node-hook-runner.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/scout-block.cjs"
PreToolUse
bash "${CLAUDE_PLUGIN_ROOT}/hooks/node-hook-runner.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/privacy-block.cjs"
PreToolUse
bash "${CLAUDE_PLUGIN_ROOT}/hooks/node-hook-runner.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/scout-block.cjs"
PreToolUse
bash "${CLAUDE_PLUGIN_ROOT}/hooks/node-hook-runner.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/privacy-block.cjs"
PreToolUse
bash "${CLAUDE_PLUGIN_ROOT}/hooks/node-hook-runner.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/dangerous-cmd-block.cjs"
PreToolUse
bash "${CLAUDE_PLUGIN_ROOT}/hooks/node-hook-runner.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/scout-block.cjs"
PreToolUse
bash "${CLAUDE_PLUGIN_ROOT}/hooks/node-hook-runner.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/privacy-block.cjs"
UserPromptSubmit
bash "${CLAUDE_PLUGIN_ROOT}/hooks/node-hook-runner.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/iteration-context.cjs"
UserPromptSubmit
bash "${CLAUDE_PLUGIN_ROOT}/hooks/node-hook-runner.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/dev-rules-reminder.cjs"
UserPromptSubmit
bash "${CLAUDE_PLUGIN_ROOT}/hooks/node-hook-runner.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/simplify-gate.cjs"
SubagentStart
bash "${CLAUDE_PLUGIN_ROOT}/hooks/node-hook-runner.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/subagent-context.cjs"
SessionStart
bash "${CLAUDE_PLUGIN_ROOT}/hooks/node-hook-runner.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/session-init.cjs"
SessionEnd
bash "${CLAUDE_PLUGIN_ROOT}/hooks/node-hook-runner.sh" "${CLAUDE_PLUGIN_ROOT}/hooks/stop-notify.cjs"

View source on GitHub

Similar plugins

mattpocock-skills

claude

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

Maintain autoresearch?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted