# Hivemind

> Coordinate opencode workers with a reviewing primary agent.

- Canonical page: https://ai-skills-catalog.com/skills/hivemind
- Category: Automation
- Author: Alireza Rezvani
- License: Apache-2.0
- Source: https://github.com/alirezarezvani/claude-skills/tree/main/engineering/hivemind
- Last updated: 2026-11-14
- Risk level: Low
- Declared permissions: Read project files; Write generated skill files

## Compatibility

- Claude: Packaged. Package: https://ai-skills-catalog.com/api/skills/hivemind/package?agent=Claude
- Codex: Packaged. Package: https://ai-skills-catalog.com/api/skills/hivemind/package?agent=Codex
- GPT: Packaged. Package: https://ai-skills-catalog.com/api/skills/hivemind/package?agent=GPT
- Gemini: Packaged. Package: https://ai-skills-catalog.com/api/skills/hivemind/package?agent=Gemini
- Cursor: Packaged. Package: https://ai-skills-catalog.com/api/skills/hivemind/package?agent=Cursor
- OpenCode: Packaged. Package: https://ai-skills-catalog.com/api/skills/hivemind/package?agent=OpenCode

## Sections of SKILL.md

- Prerequisites (external dependency)
- Data flow (read before installing)
- Setup
- Components
- Invocation contract
- Verify instead of re-reading (do this before you trust a claim)
- Free models are not always up
- Golden Rule (non-negotiable)
- Single worker flow (/oc)
- Swarm flow (multi-worker)
- Benchmarking
- Fallback ladder (all flows)
- Fleet patterns
- Windows notes (hard-won)
- Known limits
- Anti-patterns
- Cross-references

## Bundled files

- .claude-plugin/plugin.json
- LICENSE.txt
- README.md
- assets/agents/coder.md
- assets/agents/scout.md
- assets/agents/tester.md
- assets/agents/verifier.md
- assets/commands/hive.md
- assets/commands/migration.md
- assets/commands/oc.md
- assets/commands/research-sweep.md
- assets/commands/review-panel.md
- assets/commands/swarm.md
- assets/commands/test-fleet.md
- scripts/bench/grader-prompt.md
- scripts/bench/run-bench.mjs
- scripts/oc-aggregate.mjs
- scripts/oc-status.mjs
- scripts/oc-verify.mjs
- scripts/oc-worker.mjs

## Installation

### Claude

1. Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files.
2. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.
3. For Claude apps, upload the ZIP in the Skills section of the capabilities settings.
4. Start a new session and describe the task in your own words. Claude picks the skill when the request matches its description.

### Codex

1. Download the Codex package. The ZIP contains one folder named after the skill, with SKILL.md and bundled resources.
2. Unpack the complete folder into .agents/skills/ inside your repository, or into ~/.agents/skills/ for personal use. Preserve its relative reference-file paths.
3. Start a new Codex session and invoke the skill by name or with $skill-name, or describe a matching task.
4. AGENTS.md is separate project guidance. The ZIP does not generate or modify that file.

### GPT

1. Download the GPT package from the skill page.
2. Create or edit a custom GPT (or a ChatGPT project) and paste the contents of SKILL.md into the instructions field.
3. Upload the bundled reference files as knowledge so the GPT can consult them.
4. Test with one of the example prompts from the skill page and adjust the instructions if your use case differs.

### Gemini

1. Download the Gemini package from the skill page.
2. For a project, unpack the complete folder into .gemini/skills/ or .agents/skills/. For personal use, use ~/.gemini/skills/ or ~/.agents/skills/.
3. Run /skills reload in Gemini CLI, then /skills list to check discovery. There is no need to paste the skill into GEMINI.md.
4. Test a matching task and verify the referenced tools and files are available.

### Cursor

1. Download the Cursor package from the skill page.
2. Unpack the complete skill folder into .cursor/skills/ or .agents/skills/ in your project. For personal local use, ~/.cursor/skills/ and ~/.agents/skills/ are also supported.
3. Start a new Cursor session. Type / in Agent chat and select the skill name, or describe a matching task.
4. Commit the skill folder and resources for team use. Personal local skills are not automatically available to remote agents or automation runs.

### OpenCode

1. Download the OpenCode package from the skill page.
2. Unpack the complete folder into .opencode/skills/ in your project, or ~/.config/opencode/skills/ for personal use. OpenCode also supports .agents/skills/ and .claude/skills/ compatibility locations.
3. Keep supporting files at their original relative paths. AGENTS.md is separate project-wide guidance and is not generated by this ZIP.
4. Start OpenCode in the project and test a matching task with the model and permissions you use.

## FAQ

### What does the Hivemind skill do?

Coordinate opencode workers with a reviewing primary agent.

### Which AI agents can use Hivemind?

Packages for Claude, Codex and 4 more are built from the same source instructions.

### How do I install Hivemind in Claude?

Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.

### Who made Hivemind and what is the license?

Hivemind is published by Alireza Rezvani under the Apache-2.0 license. The source is https://github.com/alirezarezvani/claude-skills/tree/main/engineering/hivemind. The catalog keeps the original attribution.

### What permissions does Hivemind need?

Declared permissions: read project files, write generated skill files. Risk level: low. Check the scripts in the source before running them.

## Related Automation skills

- [Workflow Builder](https://ai-skills-catalog.com/skills/workflow-builder): Author deterministic JavaScript orchestration files for Claude Code’s Workflow tool.
- [Agent Protocol](https://ai-skills-catalog.com/skills/agent-protocol): Define a structured communication contract for collaborating executive agents.
- [Autoresearch Agent](https://ai-skills-catalog.com/skills/autoresearch-agent): Sets up repeatable experiments around one target file and a fixed evaluator. It records configuration and history, lets an agent make a bounded change, evaluates the metric, and retains or discards the result before the next iteration.
- [Browser Automation](https://ai-skills-catalog.com/skills/browser-automation): Build repeatable Playwright workflows for extracting web data, filling forms and handling browser sessions.
- [Agenthub](https://ai-skills-catalog.com/skills/agenthub): Coordinates parallel candidate solutions in isolated Git worktrees. A session defines the task and evaluation criteria, tracks agent branches and message-board state, ranks completed results, and merges the chosen candidate with a result summary.
- [Full Page Screenshot](https://ai-skills-catalog.com/skills/full-page-screenshot): Capture an entire webpage as one PNG through Chrome DevTools Protocol. The bundled Node script can target an existing authenticated tab or open a URL, resize the viewport, wait for content and write the screenshot for inspection.
