This skill should be used when a tool call is denied in autonomous mode. Guides through checking existing permissions for alternative paths, and if none exist, proposing well-scoped permission rules — without it, denied tool calls tend to either block on user input or cause subtasks to be silently skipped.
This skill should be used when the user asks to set up or configure Claude Code permissions, autonomous mode, and/or deno sandbox for a project.
A shared tooling and knowledge layer for the AI alignment community.
As soft takeoff picks up, the alignment community needs shared infrastructure to keep pace. Alignment Hive aims to provide the benefits of scale that large labs have, through shared tooling and accumulated knowledge. AI tooling is moving fast, and it's hard to keep up with what's available and what works.
Currently available:
Alignment community members: Check your email for an alignment-hive invite before installing. The invite lets you sign up and set your data sharing preferences. If you didn't receive one, contact [email protected].
Install Claude Code if you haven't already:
curl -fsSL https://claude.ai/install.sh | bash
curl -fsSL https://alignment-hive.com/install.sh | bash
This adds the plugin marketplace, installs the hive plugin, authenticates you, and walks you through data sharing preferences and project selection.
Then open Claude Code in your project and run /hive:align.
| Plugin | Description | Install |
|---|---|---|
| hive | Tooling recommendations + session sharing | Included in install script |
| mats | MATS fellow handbook, lit review, best practices | /plugin install mats@alignment-hive |
| github-action | GitHub Action for autonomous @claude on issues and PRs | /plugin install github-action@alignment-hive |
| autopilot | Autonomous operation + permission management | /plugin install autopilot@alignment-hive |
| llms-fetch-mcp | Documentation fetching with llms.txt support | /plugin install llms-fetch-mcp@alignment-hive |
| remote-kernels | Cloud GPU instances with Jupyter kernels (RunPod) | /plugin install remote-kernels@alignment-hive |
The plugin-dev plugin auto-installs when you clone this repo, so Claude can help with plugin development.
Feedback and suggestions welcome. Open an issue or email [email protected].
Matches all tools
Hooks run on every tool call, not just specific ones
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.
npx claudepluginhub crazytieguy/alignment-hive --plugin autopilotExperimental local Claude/GPT model routing gateway
Share session learnings with the alignment research community
Set up Claude Code GitHub Action for autonomous issue and PR handling
Cloud GPU instances with Jupyter kernels for AI/ML workloads
Tooling recommendations and session sharing for alignment researchers
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Patterns for adding governance, safety, and trust controls to AI-agent systems — policy-based tool access, intent classification, trust scoring, audit trails, rate limits, and content filters for agents that call external tools.
Multi-agent orchestrator for Claude Code. Track work with convoys, sling to polecats. The Cognition Engine for AI-powered software factories.
Harness for Claude Code — skills, /harness:* slash commands, persona subagents, lifecycle hooks, and MCP tools without per-repo `harness setup`. Sibling plugins exist for Cursor, Gemini CLI, and Codex.
The mentor framework for Claude Code: a self-contained process layer with per-session modes, a work-item lifecycle with a hard Definition of Done, budget-aware autonomy, visual verification, and safety rules that travel into every subagent
Hive agent skills for collaborative evolution. /hive-setup installs hive-evolve, registers your agent, and clones a task. /hive runs the autonomous experiment loop. /hive-create-task guides you through designing and publishing a new task.