By ahundt
Run fully autonomous AI coding sessions that generate step-by-step plans, execute tasks with self-critique and best practices, enforce file policies to prevent clutter, block risky commands via safety guards, manage tmux for isolated testing, and export refined plans.
Set AutoFile policy to justify-create mode (require justification for new files)
Set AutoFile policy to strict-search mode (only modify existing files)
Show current AutoFile policy and settings
Allow all file creation - full permission to create and modify files
Start autoproc - procedural autonomous workflow (legacy command)
Automate CLI application testing workflows using byobu sessions with comprehensive verification, error handling, and reporting. Perfect for testing command-line tools, plugins, and terminal applications with consistent methodologies and detailed test result analysis.
Automate byobu/tmux session lifecycle management with health monitoring and recovery. Create, monitor, and clean up byobu sessions automatically (tmux backend). Perfect for long-running CLI tasks and automated workflows that require persistent terminal sessions.
Search, recover, and analyze AI session histories across Claude Code, AI Studio, and Gemini CLI. Use when user asks to "find that file from last week", "search sessions", "recover context after compaction", "what did the AI do", "export session to markdown", "find corrections", "analyze session quality", "improve CLAUDE.md from past mistakes", or "turn AI mistakes into rules". Contains session search, file recovery, correction detection, self-improvement workflow.
Expertise in maintaining, debugging, and deploying the autorun hook system for Claude Code and Gemini CLI. Use when the user asks to "fix hooks", "deploy autorun", "debug hook errors", "update autorun version", or when troubleshooting "invisible failures" where safety guards appear inactive, piped commands are blocked, or work appears to have "reverted" after a session.
(Renamed) Search, recover, and analyze sessions from Claude Code, AI Studio, and Gemini CLI — use /ar:ai-session-tools (this is an alias that redirects there).
Guides creation and improvement of Claude Code skills using Anthropic's official methodology. Use when user wants to "create a skill", "build a skill", "make a new skill", "write a new skill", "improve an existing skill", "audit my skill", "refine my skill", "test a skill", "package a skill for distribution", or needs guidance on skill structure, progressive disclosure, description quality, testing, or distribution.
Create demo videos for CLI and TUI tools. Use when user asks to "record a demo", "make a demo GIF", "create a demo video", "record my CLI tool", "asciinema demo", "demo recording script". Covers asciinema+agg+ffmpeg pipeline, tmux recording, multi-shell, and dual-purpose demo+test harnesses in Python, Rust, TypeScript, and Bash.
Matches all tools
Hooks run on every tool call, not just specific ones
Uses power tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
rm becomes trash, git reset --hard becomes git stash# Install (requires UV - see UV Installation below)
uv pip install git+https://github.com/ahundt/autorun.git
autorun --install
# Verify installation
/ar:st
# Expected: "AutoFile policy: allow-all"
Plan & Execute (most common workflow):
/ar:plannew Design a REST API with authentication and tests
/ar:planrefine # Critique and improve the plan
/ar:planprocess # Execute the plan
/ar:go Build a login form with tests # Or run a task directly
File Policy (prevent file clutter):
/ar:f # Strict: only modify existing files
/ar:j # Justify: require justification for new files
/ar:a # Allow: create files freely (default)
Safety:
/ar:sos # Emergency stop
Works with both Claude Code and Gemini CLI — see Dual CLI Support.
Self-Improvement (learn from past sessions):
aise messages corrections --since 30d # Find recurring AI mistakes
aise analyze # Full qualitative analysis
# → Add findings to CLAUDE.md, skills, or hook blocks (see /ar:ai-session-tools Workflow 6)
The autorun marketplace includes 2 plugins: autorun and pdf-extractor.
Note: plan-export functionality is now built into the autorun plugin. Use
/ar:planexportcommands for plan management.
Install the entire marketplace directly from GitHub:
# Install plugins from GitHub
uv pip install git+https://github.com/ahundt/autorun.git
# Register plugins with Claude Code
autorun --install
Install from a local clone:
# Clone repository
git clone https://github.com/ahundt/autorun.git
cd autorun
# Install marketplace
uv pip install .
# Register plugins with Claude Code
autorun --install
npx claudepluginhub ahundt/autorun --plugin arPDF data extraction with multi-backend support (markitdown, docling, pdfplumber, etc.)
Describe your goal, approve the spec, then step away — Claude and Codex loop together until it's right.
Autonomous session orchestrator for Claude Code - manages multi-phase development workflows
Elite AI development framework: reference-first design, agent orchestration, automated quality gates, and battle-tested engineering workflows
(Alpha) Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context — stack, decisions, patterns, safety rules, and a handoff from the previous session.
Generate better AI code with task-aware policies for Claude Code.
GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.