Real-time guardrail that shows token spend & kills runaway LLM/agent loops.
- ✓Open-source license (MIT)
- ✓Clear description
- ✓Topics declared
- !Inactive (>180d)
git clone https://github.com/dipampaul17/AgentGuard && cp AgentGuard/*.md ~/.claude/agents/Subagents overview
What people ask about AgentGuard
What is dipampaul17/AgentGuard?
+
dipampaul17/AgentGuard is subagents for the Claude AI ecosystem. Real-time guardrail that shows token spend & kills runaway LLM/agent loops. It has 160 GitHub stars and was last updated 12mo ago.
How do I install AgentGuard?
+
You can install AgentGuard by cloning the repository (https://github.com/dipampaul17/AgentGuard) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is dipampaul17/AgentGuard safe to use?
+
Our security agent has analyzed dipampaul17/AgentGuard and assigned a Trust Score of 72/100 (tier: OK). See the full breakdown of passed checks and flags on this page.
Who maintains dipampaul17/AgentGuard?
+
dipampaul17/AgentGuard is maintained by dipampaul17. The last recorded GitHub activity is from 12mo ago, with 1 open issues.
Are there alternatives to AgentGuard?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy AgentGuard to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/dipampaul17-agentguard)<a href="https://claudewave.com/repo/dipampaul17-agentguard"><img src="https://claudewave.com/api/badge/dipampaul17-agentguard" alt="Featured on ClaudeWave: dipampaul17/AgentGuard" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.