- Home
- Skills
- Agents & Orchestration
- HiveMesh — Multi-Agent Swarm Orchestrator
Works with the AI Agents you already use
HiveMesh — Multi-Agent Swarm Orchestrator
Run parallel autonomous coding agents across isolated Git worktrees with zero merge conflicts and deterministic TypeScript AST verification.
$5
HiveMesh — Multi-Agent Swarm Orchestrator
Example session with this skill installed
@hivemesh run "Implement OAuth2 biometric passkeys with session refresh and security audit" --roles backend,frontend,adversary
- Read your context and instructions
- Compiled the hivemesh
Swarm Orchestration Initialized (3 Agents)
| Agent | Worktree Branch | Domain Slice | Status |
|---|---|---|---|
agent-backend | swarm/backend-passkeys | Fastify WebAuthn registration & verification | ✅ Completed |
agent-frontend | swarm/frontend-auth | React passkey modal & biometric prompts | ✅ Completed |
agent-adversary | swarm/security-redteam | Replay attacks, race conditions & fuzz tests | ✅ Passed |
Blackboard Shared Discoveries:
- Posted OpenAPI contract for
/auth/passkey/verifyto SQLite FTS5 blackboard. - Verified TypeScript AST: Zero breaking changes or symbol conflicts across worktrees.
Next steps:
- Review verified PR diffs in the HiveMesh canvas.
- Run
npx hivemesh mergeto cleanly integrate all domain branches.
Connects securely to your tools. The creator never sees your data.
About this skill
When a single coding agent tackles large features, it either loses context, hallucinates file edits, or gets stuck in single-threaded loops.
HiveMesh transforms your coding agent into an elastic multi-agent swarm engine:
- Isolated Git Worktrees: Allocates dedicated worktrees per domain slice (backend, frontend, security) to prevent merge conflicts.
- Deterministic AST Conflict Detection: Analyzes symbol signatures using the TypeScript Compiler API and catches breaking changes before any git merge.
- SQLite FTS5 Blackboard: Full-text search with BM25 ranking enables parallel agents to share APIs, discoveries, and contracts in real-time.
- Automated Adversarial Self-Play: Built-in Red-Team agent attacks code with edge cases and race conditions before review.
- Interactive UI Dashboard: Visual mission control to inspect swarms and worktree diffs visually.
Compatible with Claude Code, Cursor, Antigravity, and terminal workflows. GitHub Repository: https://github.com/ghazy2001/hivemesh
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Requires Git worktree support and SQLite. AST conflict detection is scoped to TypeScript environments.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 9 days ago
- Accounts
Gmail
Discord
GitHub
- Software
node = 18
Githivemesh
Permissions
Allowed Hosts