mantis-meta-agent is a skill listed under Google Cloud Agent 1; its action record describes it as a persistent supervisor that launches and monitors a long-running automated review campaign 11. Its page does not describe it directly, and the only other source naming Mantis is a prediction-market product unrelated to agent supervision 3, so no alternatives are listed for the skill itself.
- 1
Google Cloud Agentgoogle.comverified and signed
Hosts the mantis-meta-agent skill, which acts as the persistent supervisor launching and monitoring an automated review campaign 11.
official:repository · cybernetic-agent-governance-engineskill · google-cloud-solution-multi-agent-securityskill · mantis-meta-agentrepository · agent-shell-tools
for agents: mantis-meta-agent · administer_dose · execute_trade_action
Sources
- 1AI and Cloud Computing Services | Google Cloudcloud.google.com · read 2026-10-29
- 3Mantis | Prediction Market Discoverymantiss.store · read 2026-10-29
- 11mantis-meta-agent: declares "mantis-meta-agent" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
mantis-meta-agent · mantis-meta-agent verified and signed
Acts as the persistent supervisor, launching and monitoring the automated review campaign. Use when running a long-running, continuous security review campaign that needs autonomous coordination. Don't use for executing individual review stages directly.
mcp-deploy-manage-agents · mcp-deploy-manage-agents verified and signed
Skill converted from mcp-deploy-manage-agents.prompt.md
· Mantis website read, tools not yet checked
Route live prediction market intent across venues, compare odds, and use the original Mantis product experience.
agentic · deepagents verified and signed
PyCQA/bandit-action · Bandit by PyCQA verified and signed
The official Bandit Action developed by PyCQA
agent · @mastra/core verified and signed
· OpenCode website read, tools not yet checked
OpenCode - The open source coding agent.
agents · mini-swe-agent verified and signed
· CrewAI website read, tools not yet checked
The Leading Multi-Agent Platform
meta/meta-llama-3-8b-instruct · meta/meta-llama-3-8b-instruct verified and signed
An 8 billion parameter language model from Meta, fine tuned for chat completions
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.