What is hermes-in-buzz?

A setup guide for connecting a remote Hermes agent gateway to a Buzz community, where Buzz is a messaging client and relay. The two machines communicate through the same relay rather than through an SSH connection.

Use it to connect a Hermes gateway running on one machine with Buzz used from another, including CLI setup, relay permissions, logs, and message tests.

It addresses the configuration and verification work needed for messages to travel between Buzz and Hermes. It also checks relay authorization and confirms both incoming and outgoing messages.

hermes-in-buzz — Skill for Claude Code and Codex by tonbistudio

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 tonbistudio/buzz-skills --skill hermes-in-buzz

Clone the repo

git clone --depth 1 https://github.com/tonbistudio/buzz-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tonbistudio/buzz-skills/hermes-in-buzz/github.svg)](https://agentmods.dev/skills/tonbistudio/buzz-skills/hermes-in-buzz)

Your own site

<a href="https://agentmods.dev/skills/tonbistudio/buzz-skills/hermes-in-buzz"><img src="https://agentmods.dev/badge/skills/tonbistudio/buzz-skills/hermes-in-buzz/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tonbistudio/buzz-skills/hermes-in-buzz"><img src="https://agentmods.dev/badge/skills/tonbistudio/buzz-skills/hermes-in-buzz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,146 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 5 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Rogue Agent · line 42
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
medium Privilege Escalation · line 259
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
medium Privilege Escalation · line 262
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
medium Rogue Agent · line 272
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
medium Rogue Agent · line 276
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.04146
Opus 5	$0.00020	$0.02073
Sonnet 5	$0.00008	$0.00829
Haiku 4.5	$0.00004	$0.00415

Measured 12d ago against content hash 23b9943223c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

hermes-in-buzz scanned grade B 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/update_buzz_credentials.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo loginctl enable-linger "$USER"

hermes-in-buzz/SKILL.md · 371 lines

How it starts

The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermes in Buzz

Overview

Set up a dedicated Hermes Agent running on one machine as a native messaging agent in a Buzz community used from another machine. The default topology is:

Buzz Desktop / web client
          |
          v
      Buzz relay
          ^
          | Nostr WebSocket + buzz CLI
          |
Remote Hermes gateway

The client PC does not SSH into the Hermes host. Both independently connect to the same Buzz relay, and Buzz Desktop may be offline while Hermes continues running.

This skill executes the setup, not merely describes it. Continue until the CLI works, relay authorization succeeds, the gateway logs buzz connected, and one inbound plus outbound message has been verified.

Authoritative docs change quickly. At the start of every run, load the hermes-agent skill and inspect:

https://hermes-agent.nousresearch.com/docs/integrations/buzz
https://hermes-agent.nousresearch.com/docs/user-guide/messaging/buzz
https://hermes-agent.nousresearch.com/docs/user-guide/features/acp
the latest stable block/buzz release and its actual assets

If docs and this skill differ, follow the docs and patch this skill after the successful run.

When to Use

Use when:

Buzz Desktop is on one computer and Hermes should run continuously on another;
a user says they created a Buzz agent but the Hermes gateway is silent;
errors progress through buzz CLI binary not found, relay_membership_required, zero channels, or ignored mentions;
moving an existing native Buzz/Hermes gateway to Linux, macOS, Windows, or WSL.

Do not use this native-gateway workflow when the user explicitly wants Buzz to own the runtime and show ACP activity. In that case use the official buzz-acp relay-bridge guide. Do not improvise an SSH-stdio bridge unless the user explicitly requests an experimental design.

Hard Security Rules

Use a dedicated agent identity. Never reuse the human Buzz nsec as BUZZ_PRIVATE_KEY.
Never ask for an nsec, API token, or owner key in chat or via clarify.
Secret input must be local and hidden (getpass, Read-Host -AsSecureString, or equivalent), never argv.
Never print, log, persist temporarily, or return owner private-key material.
Store the agent key and BUZZ_AUTH_TAG only in the active profile's Hermes secret environment file. Resolve HERMES_HOME; do not assume ~/.hermes when a profile is active.
Use hermes config set for non-secret settings. Never hand-edit config.yaml.
Default to allow_all_users: false, an explicit owner allowlist, and require_mention: true. Do not broaden access merely to diagnose delivery.
Ask approval before installing Rust, Git, build tools, downloading Buzz, or changing persistence/service configuration.
An ACP-hosted Hermes can execute terminal tools without a visible approval because Buzz may auto-answer ACP permissions. Keep ACP agents owner-only. Native gateway approvals retain Hermes gateway semantics.

Read the full file on GitHub · 371 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

12d ago First seen · 371 lines · 41 tokens per session scan B 23b9943223c1

Subscribe to this mod's changes

hermes-in-buzz is a skill published in the GitHub repository tonbistudio/buzz-skills (263 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 4,146 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIs Building agents

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

agui-dotnet-protobuf

Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…

ag-ui-protocol/ag-ui · 162 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

fastapi-router-py

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

microsoft/skills · 46 tokens

aws-sdk-java-v2-core

Provides AWS SDK for Java 2.x client configuration, credential resolution, HTTP client tuning, timeout, retry, and testing patterns. Use when creating or hardening AWS service clients, wiring Spring Boot beans, debugging auth or region issues, or choosing sync vs async SDK usage.

giuseppe-trisciuoglio/developer-kit · 62 tokens

migrate-segw-to-rap

Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…

arc-mcp/arc-1 · 106 tokens

hermes-in-buzz