Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Autonomous loop engine with orchestrated subagents, DAG-based task execution, context persistence across iterations, and intelligent failure recovery with circuit breaker
npx claudepluginhub theglitchking/aeon-loop --plugin aeon-loopStop all agents immediately by creating abort signal. Use /abort clear to resume.
Start autonomous task execution loop with fresh agent sessions per iteration
Pause the loop after current iteration completes. Workers finish their tasks then stop.
Generate a Product Requirements Document for planning
Resume a paused loop from where it left off.
Error recovery specialist. Analyzes failed chunks, identifies root causes, and attempts targeted fixes.
You are the **loop orchestrator** - you spawn worker agents to execute iterations.
You are an **iteration worker** in the Aeon Loop autonomous execution system.
Task decomposition and delegation agent. Use for complex multi-step tasks that benefit from breaking down into smaller units. Delegates to worker agents.
Pure execution agent for chunk tasks. Operates in tight action-feedback loops. No planning, just execution.
Unified project workflow: PRD generation → Planning → Approval → Execution. Start here for any new project. Guides you through requirements, creates plans, and executes autonomously or collaboratively.
Activates tight action-feedback operating mode. Use for any task requiring shell commands, file operations, iterative problem-solving, debugging, or when the user wants efficient execution without verbose explanations.
Explore and analyze the current codebase using parallel subagents. Generates a comprehensive report of project structure, patterns, architecture, and dependencies.
Generate a Product Requirements Document (PRD) for planning. Use when starting a new feature, project, or complex task. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out, prd for.
Initialize persistent planning structure for a task. Creates .planning/[task-slug]/ with task_plan.md and notes.md. Use when you want to plan without autonomous execution.
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.0 — Patch release for cursor-agent smoke checks in untrusted workspaces. Run /octo:setup.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Generate production-quality SVG technical diagrams (architecture, flowchart, UML, ER, sequence, etc.) with 7 built-in styles. Export as SVG+PNG via @resvg/resvg-js.
Bash Loop operating mode for Claude Code - action over explanation, tight feedback loops, intelligent context preservation, and graceful subagent control
Persistent markdown-based planning with task directories, progress tracking, and context engineering for multi-step Claude Code workflows
Eliminate context rot in Claude Code with intelligent memory hierarchy, auto-learning hooks, and specialized subagents. 8-layer architecture with SessionStart/End hooks and MCP knowledge base.
Polyglot progressive linting for monorepos — adapter-driven baselines, per-app drift detection, and idempotent skips. Supports JavaScript/TypeScript (ESLint, Biome), Python (Ruff), Go (golangci-lint), Rust (Clippy), Terraform/OpenTofu (tflint), and Ansible (ansible-lint).
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
/claude /plugin for Autonomous task execution for Claude Code. Start a task, walk away, return to find it complete.
| Feature | ralph-loop | aeon-flux | mind-glaive | aeon-loop |
|---|---|---|---|---|
| Loop engine | ✅ | - | - | ✅ |
| Abort system | - | ✅ | - | ✅ |
| Context persistence | - | partial | ✅ | ✅ |
| Subagent coordination | - | ✅ | - | ✅ (enhanced) |
| Pattern learning | - | - | ✅ | ✅ |
| Attention preservation | - | ✅ | ✅ | ✅ |
| Action philosophy | - | ✅ | - | ✅ |
| Persistent planning | - | - | - | ✅ |
| PRD generation | - | - | - | ✅ |
Aeon Loop is a Claude Code plugin that enables autonomous, multi-iteration task execution. It combines:
| Source Plugin | What It Contributes |
|---|---|
| Ralph Loop | Autonomous iteration engine (Stop hook re-injects prompt) |
| Aeon Flux | Abort system + "action over explanation" philosophy |
| Mind Glaive | Context persistence across iterations and compactions |
| Persistent Planning | Manus-style persistent markdown planning |
v1 → v2 breaking change: the hand-rolled
aeon-loop install --scope userflow was removed. Installation is now handled automatically by either the Claude Code plugin marketplace or npm's postinstall. See CHANGELOG.md for migration details.
/plugin marketplace add TheGlitchKing/aeon-loop
/plugin install aeon-loop@aeon-loop-marketplace
/aeon-flux
Pins the version in package.json, visible to teammates, CI, and LLMs reading the repo.
npm install --save-dev @theglitchking/aeon-loop
Postinstall writes .claude/aeon-loop.json (update policy: nudge) and registers a SessionStart update-check hook in .claude/settings.json (skipped if the marketplace plugin is already enabled in ~/.claude/settings.json).
Every install ships with an update policy. Default is nudge — one-liner notification at session start when a newer version is available, no automatic changes.
aeon-loop status # installed / latest / policy / hook state
aeon-loop policy auto # auto-update on session start
aeon-loop policy nudge # one-liner nudge only (default)
aeon-loop policy off # silent
aeon-loop update # update now
Slash-command parity: /aeon-loop:status, /aeon-loop:policy <mode>, /aeon-loop:update, /aeon-loop:relink.
Note: This package includes both aeon-loop and aeon-flux bundled together. The unified workflow guides you through everything.
When you run /aeon-flux, you'll be guided through a complete project lifecycle:
/aeon-flux
│
▼
┌─────────────────────────────────────────────────────────────┐
│ PHASE 0: EXPLORATION (Optional) │
│ │
│ "I see this is an existing project. │
│ Would you like me to explore the codebase first?" │
│ │
│ 1.1. Full analysis (structure, patterns, architecture) │
│ 1.2. Quick overview │
│ 2.1. Skip - I'm familiar with this codebase │
│ 2.2. Skip - This is a new project │
│ │
│ → Launches parallel agents to explore │
│ → Saves report to .planning/exploration/report.md │
└─────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────┐
│ PHASE 1: DISCOVERY │
│ │
│ "What would you like to build?" │
│ │
│ → Asks 3-5 clarifying questions with numbered options │
│ → You respond: "1.1, 2.2, 3.1" │
│ → Continues until 90% confident │
└─────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────┐
│ PHASE 2: PRD CREATION │
│ │
│ → Generates Product Requirements Document │
│ → Right-sized user stories (completable in one iteration) │
│ → Saves to .planning/[task-slug]/prd.md │
│ │
│ "Does this PRD capture what you want?" │
└─────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────┐