Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/thrashr888/agentkernel/hermesgit clone --depth 1 https://github.com/thrashr888/agentkernelWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01024 |
| Opus 5 | $0.00000 | $0.00512 |
| Sonnet 5 | $0.00000 | $0.00205 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade C, and why
hermes scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
# Or: curl -fsSL https://raw.githubusercontent.com/thrashr888/agentkernel/main/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# Or: curl -fsSL https://raw.githubusercontent.com/thrashr888/agentkernel/main/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Agent
Run Hermes Agent (NousResearch) with agentkernel for isolated code execution.
Quick Start
Hermes Agent is a self-improving autonomous AI agent with 40+ built-in tools including terminal, file operations, web search, browser automation, vision, and code execution. It features persistent memory and a skills system that learns from experience.
# Option 1: Use the built-in template
agentkernel run --template hermes-sandbox -- python -m hermes_cli.main --help
# Option 2: Use the Dockerfile example
agentkernel sandbox create hermes-dev --config examples/agents/hermes/agentkernel.toml
agentkernel sandbox start hermes-dev
agentkernel attach hermes-dev
Setup
1. Install agentkernel
brew tap thrashr888/tap && brew install agentkernel
# Or: curl -fsSL https://raw.githubusercontent.com/thrashr888/agentkernel/main/install.sh | sh
2. Create and start a sandbox
agentkernel sandbox create hermes-dev --config examples/agents/hermes/agentkernel.toml
agentkernel sandbox start hermes-dev
3. Launch Hermes
agentkernel attach hermes-dev
# Inside the sandbox:
cd /opt/hermes-agent && python -m hermes_cli.main
API Keys
Hermes supports multiple LLM providers via LiteLLM. Pass at least one provider key:
# OpenRouter (recommended - access to all models)
export OPENROUTER_API_KEY=sk-or-...
# Anthropic (direct)
export ANTHROPIC_API_KEY=sk-ant-...
# OpenAI (direct)
export OPENAI_API_KEY=sk-...
Configuration
Hermes uses two config files inside ~/.hermes/:
.env- API keys and backend settingsconfig.yaml- Model selection, tools, memory, compression settings
Key config options in config.yaml:
model:
default: "anthropic/claude-opus-4.6"
provider: "auto"
terminal:
backend: "local"
timeout: 180
toolsets:
- all
memory:
memory_enabled: true
Run hermes setup inside the sandbox for a guided configuration wizard.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 154 lines · 0 tokens per session scan C c56e7842dd1b
hermes is an agent published in the GitHub repository thrashr888/agentkernel (58 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,024 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
researcher
Deep research agent that uses Actionbook browser CLI to browse the web, collect information from multiple sources, and generate structured json-ui reports.
html-reader
Background agent for reading ar5iv.org HTML papers using agent-browser CLI.
product-designer
Use this agent when you need UX critique, information architecture analysis, or feature design validation for ccboard. Specializes in developer tool UX, data density optimization, keyboard-first interaction design, and ensuring new features match how developers actually think and work. Examples:\n\n \nContext: User…
frontend-developer
Build React components, implement responsive layouts, and handle client-side state management. Masters React 19, Next.js 15, and modern frontend architecture. Optimizes performance and ensures accessibility. Use PROACTIVELY when creating UI components or fixing frontend issues.
verify
Verifies edits conform to project AGENTS.md and suggests simplifications.
human-3-coach
You are a specialized development coach based on Dan Koe's HUMAN 3.0 framework - a holistic personal development system that integrates Mind, Body, Spirit, and Vocation to help individuals reach their highest potential.