Hermes Production Gateway Operations

What it does

When your agent uses it

• Switching the global model or provider on a running Hermes gateway
• Planning a gateway restart with the least disruption to users
• Stopping restart and startup notifications from reaching end-users
• Tuning streaming and progress settings for a messaging deployment

Example prompts

• “Switch our Hermes gateway from GLM-5.2 to GLM-5.3, checking that the provider lists it first.”
• “Stop the gateway from pinging users every time it restarts.”
• “Plan a gateway restart that an operator can run over SSH.”
• “Roll back the model change, because tool calls started failing.”

Requirements

• A running Hermes gateway with access to ~/.hermes/config.yaml
• An operator with SSH and sudo to restart hermes-gateway.service
• A provider API key such as TOGETHER_API_KEY

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Verify the new model exists on the provider before changing config.
2. 2Edit config.yaml (at ~/.hermes/config.yaml)
3. 3Restart the gateway for changes to take effect

What it can do on your machine

Read from SKILL.md and the folder at commit 70a2273. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • curl
  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.together.xyz

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • TOGETHER_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hermes Production Gateway Operations loads about 2k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 106 tokens; SKILL.md has 854 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~106

When it runs · the whole SKILL.md, loaded when a task matches

~2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteRuns commands with sudoSKILL.md:51

  sudo systemctl restart hermes-gateway.service

• NoteRuns commands with sudoSKILL.md:149

  4. Have the operator restart via SSH: `sudo systemctl restart hermes-gateway.service`

• NoteMentions a .env fileSKILL.md:157

  ~/.hermes/.env              API keys and secrets

• WarningContains instruction-override wording (e.g. “without asking the user”)SKILL.md:165

  ges require a restart to take effect.** Do not tell the user

• NoteRuns commands with sudoSKILL.md:181

  `sudo systemctl stop hermes-gateway.service`.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hewi333/Mom-n-Pop-Skills at commit 70a2273, republished under its MIT licence (© hewi333). 854 words, ~1,993 tokens.

name

hermes-production-ops

description

Operate and maintain a live production Hermes gateway deployment: switch models/providers globally, manage gateway restarts, suppress operational notifications to end-users, tune streaming/progress config for messaging platforms, and recover from stuck states without sudo. Use when changing the global model, planning a gateway restart, or configuring platform behavior for end-user-facing deployments.

version

1.0.0

author

Hermes Agent

license

MIT

telegram:
  gateway_restart_notification: false

# config.yaml
gateway:
  tool_progress: final           # or 'summary' — NOT 'all' for end-user platforms
  long_running_notifications: true   # keep — useful for genuinely long tasks
agent:
  max_turns: 40-75               # 150 (default) is too generous for messaging

~/.hermes/config.yaml       Main config (model, providers, platform settings)
~/.hermes/.env              API keys and secrets
~/.hermes/logs/gateway.log  Gateway logs for debugging

© hewi333, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/hermes-production-ops of hewi333/Mom-n-Pop-Skills.

• SKILL.md
• references/gateway-restart-notifications.md
• references/gateway-streaming-config.md

Open the folder on GitHubat commit 70a2273