What is hermes-agent?

An operations guide for Hermes, an AI agent service that runs in a Kubernetes namespace and stores state on persistent storage. It covers configuration, restarts, connectivity, shared files, and session cleanup.

Use it when changing Hermes configuration or runtime skills, restarting or debugging it, adjusting its state database or storage, or checking MCP, language-model, and Samba connections.

It prevents harmless-looking configuration edits from causing unclean restarts, hides problems that basic health checks miss, and avoids repeated database rewrites or unsafe storage changes.

How Aviator-Coding/home-ops configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to Aviator-Coding/home-ops. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Aviator-Coding/home-ops/main/.agents/skills/hermes-agent/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Aviator-Coding/home-ops

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/aviator-coding/home-ops/hermes-agent/github.svg)](https://agentmods.dev/skills/aviator-coding/home-ops/hermes-agent)

Your own site

<a href="https://agentmods.dev/skills/aviator-coding/home-ops/hermes-agent"><img src="https://agentmods.dev/badge/skills/aviator-coding/home-ops/hermes-agent/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/aviator-coding/home-ops/hermes-agent"><img src="https://agentmods.dev/badge/skills/aviator-coding/home-ops/hermes-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,292 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	$0.00082	$0.01292
Opus 5.5	$0.00033	$0.00517
Sonnet 5.5	$0.00016	$0.00258
Haiku 4.5	$0.00008	$0.00129

Measured 9d ago against content hash 6078f8c1418c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hermes-agent 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 9d 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.

.agents/skills/hermes-agent/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermes agent: config, restarts, state.db and routing

Hermes is the homelab operator in namespace ai. It is a single writer on an RWO ceph-block claim. Config, the runtime skill, and Samba share contents are payloads the pod reads: a comment edit there still restarts the pod uncleanly, so batch them and never pair one with an unrelated rollout.

Tripwires

Any byte of resources/config.yaml or a runtime skill restarts the pod. Both are configMapGenerator sources. The restart is unclean and the next boot integrity-checks all of state.db. restarts.md
Pod status and Gatus stay green while the gateway is stuck. Probes are TCP on the dashboard port 9119, which is a different s6 service from gateway-default. Read /opt/data/logs/gateway-startup-watchdog.log. Do not add a gateway liveness probe.
Never set sessions.vacuum_after_prune: true. last_vacuum is absent from state_meta, so the interval throttle never engages and a full rewrite through the WAL is retried on every prune that deletes rows. Growing the claim to 40Gi did not retire this. retention_days (narrower than upstream's 90) is the dial. state-db.md
sessions.auto_prune must be explicit true. Both call sites use .get("auto_prune", False), so an upstream default flip silently stops pruning. Gate: scripts/ci/hermes-state-db-retention-test.py.
Never set OPENAI_BASE_URL. It is a global OpenAI-SDK override. The default provider stays custom:gateway. providers.litellm is only a selectable second provider. A dummy OPENAI_API_KEY is the only env to re-add if boot demands an OpenAI key. llm-routing.md
Keep the image on the -desktop tag. The plain tag has no Chromium or VNC stack, and the process cannot apt install after it drops to uid 10000. Renovate is pinned to the suffix so it cannot drift back.
Never set container args back to gateway run. The image already starts gateway-default via s6. A second gateway CrashLoops. The command stays sleep infinity.
Keep the kopiur/pvc include on the overlay, strategy: Recreate, and replicas: 1. The claim is single-writer. KOPIUR_CAPACITY in git does not resize a live claim. shared-storage.md
Env-injected secrets do not refresh in a running pod without reloader.stakater.com/auto: "true" on the controller. The annotation is already set; removing it leaves rotated tokens stale until some other rollout.
Do not name the custom provider after a built-in id (openrouter, openai, ...). Hermes then treats it as the native integration and skips that entry's base_url. gateway and litellm are the safe names.

Read the full file on GitHub · 79 lines

Files

What ships with it

5 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.

9d ago Changed · +1 lines 6078f8c1418c
22d ago Changed · +1 lines fc30aa72b0ad
23d ago Changed · +1 lines 60ca300b2bb0
25d ago First seen · 76 lines · 82 tokens per session scan A 835484e0b85a

Subscribe to this mod's changes

hermes-agent is a skill published in the GitHub repository Aviator-Coding/home-ops (3 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 1,292 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-29.

Building agents DevOps and cloud

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

systematic-debugging

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

obra/superpowers · 21 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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

home-ops: Skill for Claude Code