Agent Sentinel

Agent Sentinel 🛡️🧠

**AI Cognitive Supervisor, Autonomous Resumption Engine & Rate Limit Sentinel for Claude Code Agents.**

[](https://nodejs.org) [](https://opensource.org/licenses/MIT) [](https://deepmind.google) [](#how-it-works)

---


Agent Sentinel is an intelligent supervisory dashboard and daemon designed for multi-agent Claude Code development workflows. Instead of relying on fragile regex matching, Agent Sentinel uses an **LLM Cognitive Supervisor** to analyze transcript semantics, distinguish between active execution and true rate limits, automatically issue resume instructions (*"continue"*), autonomously trigger bug-free hardening reviews upon task completion, and optionally hibernate your machine on weekly quota exhaustion.

---

🌟 Key Features

1. 🧠 LLM Cognitive Supervision (No Naive Regexes)

• Evaluates raw conversation turns using continuous LLM reasoning.
• Accurately differentiates between task completion, active tool execution, momentary network hiccups, 5-hour session ceilings, and weekly subscription limits.
• Renders an explicit "🧠 LLM Supervisor Interpretation" card on each agent with step-by-step diagnostic reasoning.

2. 🤖 Three Autonomous Prompting Modes

Configure behavior globally in Settings or override per agent:

1. Auto Continue (continue) (Enabled by default):
   • Automatically triggered when an agent reaches its quota/rate limit reset timestamp.
2. Auto Fix (The Ultimate Adversarial Bug-Free & Pixel-Perfect Hardening Loop):
   • When an agent finishes its goal, Sentinel aut