by 42-evey
Custom plugins for hermes-agent — goal management, inter-agent bridge, model selection, cost control
# Add to your Claude Code skills
git clone https://github.com/42-evey/hermes-pluginsGuides for using ai agents skills like hermes-plugins.
Last scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T15:59:14.485Z",
"npmAuditRan": true,
"pipAuditRan": true
}See how hermes-plugins compares with popular alternatives.
hermes-plugins is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by 42-evey. Custom plugins for hermes-agent — goal management, inter-agent bridge, model selection, cost control. It has 522 GitHub stars.
Yes. hermes-plugins passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/42-evey/hermes-plugins" and add it to your Claude Code skills directory (see the Installation section above).
hermes-plugins is primarily written in Python. It is open-source under 42-evey on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh hermes-plugins against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Support Evey — runs 24/7 on free models, hardware costs ~$69/mo: Donate (BTC, ETH, SOL, XRP, DOGE)
23 custom plugins for hermes-agent — built for autonomous operation, observability, cost control, and self-improvement.
git clone https://github.com/42-evey/hermes-plugins.git
cp -r hermes-plugins/evey-* ~/.hermes/plugins/
cp hermes-plugins/evey_utils.py ~/.hermes/plugins/
# Restart hermes-agent
| Plugin | What It Does |
|---|---|
| evey-autonomy | Core autonomy engine: autonomous_decide, autonomous_plan, autonomous_reflect tools. The brain of self-directed behavior. |
| evey-council | 3-model debate for hard decisions. Multiple models argue, then consensus is extracted. |
| evey-delegate-model | Smart model routing with auto task-type detection, 3-retry per model, 4-model fallback chain. Sensitivity filter keeps private data local. |
| Plugin | What It Does |
|---|---|
| evey-telemetry | Structured JSON logging of every tool call, delegation, and error. Auto-rotating event log. telemetry_query tool for self-inspection. |
| evey-status | Unified status check — ONE tool call returns bridge + MQTT + costs + cron + goals + time context. |
| evey-mqtt | Auto-connecting MQTT real-time event stream. Subscribes to bridge/events/health/mother topics on plugin load. |
| evey-cost-guard | Budget enforcement via Langfuse. Tracks daily/per-task costs. Warns at 80%, alerts at 100%. |
| Plugin | What It Does |
|---|---|
| evey-reflect | Self-correction loop. Critiques outputs with a cheap model before sending. |
| evey-validate | Hallucination detection. Regex patterns + LLM scoring (0-10). |
| evey-email-guard | Prompt injection screening. Dual-layer: 20+ regex patterns + local AI classifier. |
| evey-sandbox | Sandboxed code execution with resource limits. |
| evey-session-guard | Session lifecycle management and cleanup. |
| Plugin | What It Does |
|---|---|
| evey-learner | Experiential learning — learns from interactions, applies learnings next time. |
| evey-memory-adaptive | Importance scoring + decay for memories. High-value memories persist, low-value fade. |
| evey-memory-consolidate | Nightly memory consolidation — extracts facts into MEMORY.md + Qdrant vectors. |
| evey-cache | Delegation caching — avoid re-asking the same questions to models. |
| evey-identity | Self-updating SOUL.md — evolves personality based on interactions. |
| Plugin | What It Does |
|---|---|
| evey-bridge | Bidirectional communication with Claude Code. File-based inbox/outbox + MCP server. |
| evey-goals | Autonomous goal management. Set, track, complete, review goals. |
| evey-telegram-ux | Telegram UX improvements — message formatting, interruption management. |
| evey-research | Automated research pipeline with web search and note-taking. |
| evey-digest | Daily digest compilation from multiple data sources. |
| evey-delegation-score | Score and rank delegation results for quality tracking. |
| File | What It Does |
|---|---|
| evey_utils.py | Shared retry logic (call_llm with exponential backoff), HTTP helpers. |
These plugins are part of Evey's autonomous AI agent stack:
MIT