No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Lethe044 · Codex Skill · ★ 70
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is hermes-incident-commander safe to install? View the security audit →
⚕ Hermes Incident Commander An autonomous SRE agent that detects, diagnoses, and heals production infrastructure - then learns from every incident it resolves. Originally built on Hermes Agent by NousResearch for the "Show us what Hermes Agent can do" hackathon. Now also ships a standalone watchdog that runs on any real Linux host with nothing but an Anthropic API key — no Hermes installation required. What's New 📟 PagerDuty integration - the notifier can now trigger (and resolve) PagerDuty incidents via the Events API v2, alongside Discord/Slack, with zero new dependencies. See Standalone Mode. ☸️ Kubernetes pod crash-loop scenario - an 8th incident scenario (), in both the RL environment and the demo. 🛰️ Standalone Watchdog — monitor a real host's CPU/memory/disk and failed systemd units, get Claude-powered triage, and (opt-in) safe auto-remediation. No Hermes install needed. 📊 Offline
| Stars | 70 |
| Forks | 3 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 70.5797741691618/100 |
| Last Updated | 2026-09-19 |
| Created | 2026-03-12 |
| Platforms | claude-code, k8s, python |
| Est. Tokens | ~17k |
These tools work well together with hermes-incident-commander for enhanced workflows:
Looking for a hermes-incident-commander alternative? If you're comparing hermes-incident-commander with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A curated list of 100+ AI-powered tools, platforms, and resources for Site Reliability Engineering (SRE) — age
Universal development automation for ANY project. Claude Code implements features, runs tests, creates PRs aut
eBPF agent and MCP server for GPU causal observability
Monocle is a framework for tracing GenAI app code. This repo contains implementation of Monocle for GenAI apps
This MCP server provides documentation about Strands Agents to your GenAI tools, so you can use your favorite
AI-powered SRE platform — read-only infrastructure diagnostics with deep investigation, security governance, a
Explore other popular codex skill tools:
hermes-incident-commander is Autonomous SRE agent that detects, diagnoses, and self-heals production incidents - with a standalone watchdog that needs no Hermes install, just an Anthropic API key. Memory + Skills + Cron + Gateway. It is categorized as a Codex Skill with 70 GitHub stars.
hermes-incident-commander is primarily written in Python. It covers topics such as anthropic, atropos, automation.
You can find installation instructions and usage details in the hermes-incident-commander GitHub repository at github.com/Lethe044/hermes-incident-commander. The project has 70 stars and 3 forks, indicating an active community.
hermes-incident-commander is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to hermes-incident-commander on Agent Skills Hub include awesome-ai-sre, lazy-bird, ingero. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: