What is hermes-deploy-guard?

A safety procedure for running Hermes from a checked-out development folder, where the files in that folder are used directly by the live agent. Hermes is an AI agent with a gateway, command-line interface, and messaging connections.

Use it when restarting, updating, or developing near a live Hermes installation. It helps verify the active branch, configuration files, process links, and gateway state.

It reduces the risk of running the wrong Git branch or changing only one of Hermes's two configuration files. It also provides checks and recovery steps for gateway, process, and lock problems.

hermes-deploy-guard — Skill for Claude Code and Codex by davidgut1982

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/davidgut1982/hermes-toolkit

agentmods

npx agentmods add skills/davidgut1982/hermes-toolkit/hermes-deploy-guard

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/davidgut1982/hermes-toolkit/hermes-deploy-guard/github.svg)](https://agentmods.dev/skills/davidgut1982/hermes-toolkit/hermes-deploy-guard)

Your own site

<a href="https://agentmods.dev/skills/davidgut1982/hermes-toolkit/hermes-deploy-guard"><img src="https://agentmods.dev/badge/skills/davidgut1982/hermes-toolkit/hermes-deploy-guard/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/davidgut1982/hermes-toolkit/hermes-deploy-guard"><img src="https://agentmods.dev/badge/skills/davidgut1982/hermes-toolkit/hermes-deploy-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 729 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00087	$0.00729
Opus 5	$0.00044	$0.00365
Sonnet 5	$0.00017	$0.00146
Haiku 4.5	$0.00009	$0.00073

Measured 8d ago against content hash 375e6307040f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hermes-deploy-guard scanned grade A with 0 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 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/hermes-deploy-guard/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermes Deploy Guard

A Hermes editable install has no build step: the checked-out git branch is the running code. This skill is the invariant that keeps that safe and the exact recovery when it breaks. (Background: hermes-internals → "Homelab deployment realities".)

The invariant

Live checkout: /opt/hermes/home/.hermes/hermes-agent.
It MUST stay on branch integrated (carries profile-aware delegation).
Never git checkout a feature branch on the live tree. Two prior outages came from exactly that. Dev work goes in a git worktree or hermes -p dev.

Two config files (fix both)

File	Read by
`/opt/hermes/home/config.yaml`	gateway (Telegram / messaging)
`/opt/hermes/home/.hermes/config.yaml`	TUI / CLI (`HERMES_HOME=/opt/hermes/home/.hermes`)

A config change in one only silently fails on the other surface.

Health checks

# 1. branch integrity — must print: integrated
git -C /opt/hermes/home/.hermes/hermes-agent rev-parse --abbrev-ref HEAD

# 2. PID/lock symlinks (required after a dashboard restart)
ls -l /opt/hermes/home/.hermes/gateway.pid /opt/hermes/home/.hermes/gateway.lock
#    -> should point at /opt/hermes/home/gateway.{pid,lock}

Ops/service checks go through the cluster-ops MCP (service_status, disk_usage, journal_tail, …) — terminal/code_execution are disabled on this build.

Recovery (run in order, only when drift/breakage is confirmed)

cd /opt/hermes/home/.hermes/hermes-agent
git checkout integrated                                   # restore running branch (the ONE allowed checkout)
pip install -e .                                          # re-link editable install
# restart the gateway (dashboard, or `hermes gateway stop --all` then start)
ln -sf /opt/hermes/home/gateway.pid  /opt/hermes/home/.hermes/gateway.pid    # recreate symlinks
ln -sf /opt/hermes/home/gateway.lock /opt/hermes/home/.hermes/gateway.lock
# verify end-to-end (Woodstock IL weather + chat should go green):
python ../hermes-eval-harness/scripts/hermes_eval.py \
  --suite ../hermes-eval-harness/scripts/suites/smoke.yaml --backend library --workers 4

Read the full file on GitHub · 68 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.

8d ago First seen · 68 lines · 87 tokens per session scan A 375e6307040f

Subscribe to this mod's changes

hermes-deploy-guard is a skill published in the GitHub repository davidgut1982/hermes-toolkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 729 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

DevOps and cloud

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens