What is hermes-skill-authoring?

A guide for creating and maintaining skills for Hermes Agent, an AI agent runtime. It explains the file format, folder structure, activation rules, environment variables, credentials, templates, shell commands, and media delivery.

Use it to create, edit, review, or debug Hermes skills. It helps package instructions, helper scripts, reference files, and integrations for the Hermes runtime.

It prevents skills written for another agent system from being installed in the wrong format. It also clarifies when an extension should be a skill rather than a tool.

hermes-skill-authoring — Skill by davidgut1982/hermes-toolkit

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 davidgut1982/hermes-toolkit --skill hermes-skill-authoring

Clone the repo

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

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

Your own site

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

Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,727 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 2 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	$0.00132	$0.01727
Opus 5.5	$0.00053	$0.00691
Sonnet 5.5	$0.00026	$0.00345
Haiku 4.5	$0.00013	$0.00173

Measured 2mo ago against content hash 1acb4025d739, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hermes-skill-authoring scanned grade A with 2 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 2mo 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.

Asks the agent to reveal its instructionslowSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

prompt: "Display prompt for setup"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

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

- **No external deps** by default — prefer stdlib Python, `curl`, and existing

skills/hermes-skill-authoring/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authoring Hermes Skills

Two SKILL.md dialects — don't mix them. The file you are reading is a Claude/Anthropic Agent Skill (frontmatter: just name + description). A Hermes skill is a different artifact with a richer frontmatter (version, author, license, platforms, metadata.hermes, …) consumed by the Hermes runtime. When you write a skill to install into Hermes, use the Hermes format documented below — not this file's format.

Skill or tool?

Make a skill when the capability is instructions + shell + existing Hermes tools (terminal, web_extract, read_file), wrapping a CLI/API, no baked-in keys. Make a tool when it needs end-to-end key/auth integration, must execute precise logic every time, or handles binary/streaming/realtime. Most extensions are skills.

Directory layout

my-skill/
├── SKILL.md            # required: the instructions
├── scripts/            # optional: helper scripts (parsers, API calls)
└── references/         # optional: docs loaded on demand

SKILL.md frontmatter (Hermes)

---
name: my-skill
description: Brief description (shown in skill search results)
version: 1.0.0
author: Your Name
license: MIT
platforms: [macos, linux]            # optional; omit = all platforms
metadata:
  hermes:
    tags: [Category, Subcategory, Keywords]
    related_skills: [other-skill]
    requires_toolsets: [web]         # hide unless this toolset is active
    requires_tools: [web_search]     # hide unless this tool exists
    fallback_for_toolsets: [browser] # hide WHEN this toolset is active
    fallback_for_tools: [browser_navigate]
    config:                          # non-secret settings -> config.yaml
      - key: my.setting
        description: "What it controls"
        default: "sensible-default"
        prompt: "Display prompt for setup"
required_environment_variables:      # secrets -> ~/.hermes/.env (never shown to model)
  - name: MY_API_KEY
    prompt: "Enter your API key"
    help: "Get one at https://example.com"
    required_for: "API access"
required_credential_files:           # OAuth token files, certs, service-account JSON
  - path: google_token.json
    description: "OAuth token (created by setup script)"
---

Read the full file on GitHub · 173 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.

2mo ago First seen · 173 lines · 132 tokens per session scan A 1acb4025d739

Subscribe to this mod's changes

hermes-skill-authoring is a skill published in the GitHub repository davidgut1982/hermes-toolkit (2 stars, last pushed 5mo ago), licensed MIT. It adds 132 tokens to every session and 1,727 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 2 findings (asks the agent to reveal its instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

hermes-skill-authoring next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hermes-skill-authoringdavidgut1982/hermes-toolkit	Skill	2	5mo ago	MIT	A	132	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex

hermes-skill-authoring