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 AtlasOmnia · Codex Skill · ★ 118
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is hermes-tool-router safe to install? View the security audit →
Hermes Tool Router Experimental standalone Hermes Agent plugin for reducing first-turn tool-schema overhead without repeatedly changing the tool prefix later in the conversation. Test on a separate Hermes profile first. Do not install an experimental router directly on a primary profile. How it works The router classifies only the first turn. High-confidence routes send a smaller tool schema to the main model; uncertainty keeps the full surface. If a pruned registered tool is needed later, Hermes adds its owning toolset without re-pruning the session. v0.2 design First-turn routing: deterministic intent classification narrows the live tool surface before the first provider request through stock Hermes hooks. Session-sticky surface: later turns reuse the initial surface instead of reclassifying and shrinking it. Monotonic recovery: requested toolsets are added permanently for the session. Fail open: uncertainty, invalid classifier output, missing confidence, timeout, registry mismatch, or unsupported runtime keeps the full tool surface. Optional classifier: external model routing is disabled by default. Deterministic misses fall back immediately with no network call. Dyn
| Stars | 118 |
| Forks | 10 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 75.4158722388993/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-19 |
| Created | 2026-05-28 |
| Platforms | python |
| Est. Tokens | ~15k |
These tools work well together with hermes-tool-router for enhanced workflows:
Looking for a hermes-tool-router alternative? If you're comparing hermes-tool-router 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.
Supercharge AI Agents, Safely
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
Battle-tested skill library for AI agents. Save 98% of API costs with ready-to-use code for crypto, PDFs, sear
Claude Code plugins for reliable AI coding. Flow-Next: plan-first workflows, Ralph autonomous mode (overnight
🪝 Claude Code hooks + an installable plugin marketplace: safety, cost, observability, productivity.
A command-line interface tool for serving LLM using vLLM.
Explore other popular codex skill tools:
hermes-tool-router is Deterministic, fail-open tool routing for Hermes Agent with an optional local-model fallback.. It is categorized as a Codex Skill with 118 GitHub stars.
hermes-tool-router is primarily written in Python. It covers topics such as hermes-agent, llm-tools, plugin.
You can find installation instructions and usage details in the hermes-tool-router GitHub repository at github.com/AtlasOmnia/hermes-tool-router. The project has 118 stars and 10 forks, indicating an active community.
hermes-tool-router is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to hermes-tool-router on Agent Skills Hub include mcpproxy-go, maestro, open-skills. 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: