hermes

hermes is a skill for Claude Code from felipefontoura/bento. It costs 144 tokens per session (1,801 once invoked), scanned A, original, MIT.

A set of instructions for operating the Hermes agent gateway on a Bento-hosted server. Hermes lets scripts, bots, and people chat with an AI agent through an API, while MCP servers add extra tools to that agent.

In plain words
What is it for?
Use it to call Hermes from a script or bot, inspect sessions, enable or disable tools, change the AI provider or model, and connect services such as search or YouTube tools.
Why use it?
It gives one place to chat with the agent, manage its sessions and tools, change its settings, and connect new tool servers without reinstalling the gateway.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: built for hermes-agent.

Part of the bento plugin — 13 skills shipped together

Good fit Use it to call Hermes from a script or bot, inspect sessions, enable or disable tools, change the AI provider or model, and connect services such as search or YouTube tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/felipefontoura/bento/hermes
Install

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.

Any agent
npx skills add felipefontoura/bento --skill hermes
Clone the repo
git clone --depth 1 https://github.com/felipefontoura/bento

Made for: Claude Code.

Or install bento, the plugin that ships this one along with the rest of its 13 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for hermes

README.md
[![agentmods](https://agentmods.dev/badge/skills/felipefontoura/bento/hermes.svg)](https://agentmods.dev/skills/felipefontoura/bento/hermes)
Your own site
<a href="https://agentmods.dev/skills/felipefontoura/bento/hermes"><img src="https://agentmods.dev/badge/skills/felipefontoura/bento/hermes.svg" alt="Measured on agentmods" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,801 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00144 $0.01801
Opus 5 $0.00072 $0.00901
Sonnet 5 $0.00029 $0.00360
Haiku 4.5 $0.00014 $0.00180

Measured 8d ago against content hash 58d3a4c93a51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

hermes scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://$HERMES_API_HOST/v1/chat/completions" \
plugins/bento/skills/hermes/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You operate a Hermes agent gateway already deployed by bento. Hermes runs gateway run and supervises, in parallel: an OpenAI-compatible API server (:8642, for bots/scripts), a dashboard (:9119, Traefik basic-auth gate), and a CLI reachable via docker exec. This is day-2 work — chat, configure, and extend the agent. You do NOT redeploy the stack — that is /bento:deploy. All artifacts stay in English.

Where config lives. The daemon's mutable config is /opt/data/config.yaml inside the hermes container (the .env next to it holds secrets, mode 0600). Edit config and add MCP servers in the hermes daemon container (hermes_hermes), never in another stack that mounts the binary read-only.

When to invoke

  • "chat with / call my hermes agent" (from a script, bot, or by hand)
  • "add an MCP server to hermes" / "give the agent the <youtube/search/...> tools"
  • "list / inspect sessions", "list / enable / disable tools"
  • "change the model or provider", "show the hermes config"

For getting hermes running use /bento:deploy. For provider API keys (OpenAI/Anthropic/OpenRouter) use /bento:auth — hermes reads those propagated envs.

Discover the instance — don't hardcode

ssh "$user@$host" "jq -r '.envs.hermes.HERMES_API_HOST' \$HOME/.config/bento/state.json"  # API gateway host
ssh "$user@$host" "jq -r '.envs.hermes.HERMES_HOST'     \$HOME/.config/bento/state.json"  # dashboard host
ssh "$user@$host" "jq -r '.envs.hermes.HERMES_API_KEY'  \$HOME/.config/bento/state.json"  # Bearer for the API (don't echo)
ssh "$user@$host" "jq -r '.envs.hermes.HERMES_MODEL_NAME' \$HOME/.config/bento/state.json" # advertised model name

API base URL = https://<HERMES_API_HOST>. Container (conventional in bento swarm): hermes_hermes.1.*.

hermes_container() { ssh "$user@$host" "docker ps --filter name=hermes_hermes -q | head -1"; }
hx() { ssh "$user@$host" "docker exec \$(docker ps -qf name=hermes_hermes) hermes $*"; }  # run a hermes CLI subcommand

Read the full file on GitHub · 130 lines

Changes

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.

  1. 8d ago First seen · 130 lines · 0 tokens per session scan A 58d3a4c93a51

Subscribe to this mod's changes

hermes is a skill published in the GitHub repository felipefontoura/bento (20 stars, last pushed 1mo ago), licensed MIT. It adds 144 tokens to every session and 1,801 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

post-build-flow

Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.

n8n-io/n8n · 53 tokens

intent-recognition

Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an…

n8n-io/n8n · 146 tokens

data-table-manager

Load before calling data-tables or parse-file. Use for natural standalone requests like "what data tables do I have?", "show/list my tables", or "what columns are in this table?", and whenever the user asks to list, show, create, inspect, import, seed, query, update, clean up, rename columns in, or delete data tables…

n8n-io/n8n · 113 tokens

planned-task-runtime

Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks.

n8n-io/n8n · 58 tokens

planning

ONLY for coordinated multi-artifact work: multiple workflows with dependencies, shared data-table schema/migration across tasks, or the user explicitly asked to review a plan first. Load create-tasks via loadtool before calling it (search "create tasks" if not visible). Do NOT use for new one-off workflows…

n8n-io/n8n · 88 tokens

n8n-cli

Use the n8n CLI to manage workflows, credentials, executions, and more on an n8n instance. Use when the user asks to interact with n8n, automate workflows, manage credentials, or operate their instance from the command line.

n8n-io/n8n · 55 tokens