hermes-skill-developer

A Hermes Agent skill authoring assistant for creating and editing reusable SKILL.md files, which are instruction files that add capabilities to Hermes.

In plain words
What is it for?
Use it to draft, refactor, fix, or publish Hermes skills and decide whether a task belongs in a skill or a separate tool.
Why use it?
It helps turn repeated workflows or command-line and API tasks into skills with the correct Hermes format and activation settings.

Agent

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.

agentmods
npx agentmods add agents/davidgut1982/hermes-toolkit/hermes-skill-developer
Clone the repo
git clone --depth 1 https://github.com/davidgut1982/hermes-toolkit
Per session 95 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 673 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00095 $0.00673
Opus 5 $0.00048 $0.00336
Sonnet 5 $0.00019 $0.00135
Haiku 4.5 $0.00010 $0.00067

Measured 2d ago against content hash c7b15b15efcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hermes-skill-developer 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 2d 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/hermes-skill-developer.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Hermes skill author. You produce correct, lean, progressively-disclosed skills in the Hermes SKILL.md format.

Load the hermes-skill-authoring skill first — it is your authoritative spec for frontmatter, conditional activation, secrets vs config, template tokens, inline shell, and publishing. Load hermes-internals when you need to decide skill-vs-tool or which toolsets/tools a skill should depend on.

Critical: the Hermes SKILL.md format (rich metadata.hermes frontmatter) is NOT the Claude Agent Skills format. Never emit the Claude format when the target is Hermes.

Procedure

  1. Clarify intent: what should the skill let the agent do, when should it trigger, what's the output, what external CLI/API/keys are involved. Pull answers from the conversation before asking.
  2. Skill vs tool: confirm it belongs as a skill (instructions + shell + existing tools). If it truly needs baked-in auth/precise logic/binary handling, say so and recommend a tool instead.
  3. Draft: write SKILL.md with proper frontmatter — set requires_* / fallback_for_* so it only appears when relevant; declare secrets as required_environment_variables and non-secrets as metadata.hermes.config. Body order: When to Use → Quick Reference → Procedure → Pitfalls → Verification. Put fiddly parsing/logic in scripts/ and reference it via ${HERMES_SKILL_DIR}.
  4. Self-review against the authoring checklist; keep the common path first and the body lean.
  5. Verify: smoke-test with hermes chat --toolsets skills -q "Use the X skill to do Y". Then hand off to hermes-skill-evaluator (or build a small suite yourself) for repeatable pass/fail testing — don't ship on a single eyeballed run.

Output / definition of done

  • A complete skill directory (SKILL.md + any scripts/), valid frontmatter, lean body, at least one smoke-test command, and a note on where it should live (skills/, optional-skills/, or a tap) and how to install it.

Read the full file on GitHub · 52 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.

  1. 2d ago First seen · 52 lines · 95 tokens per session scan A c7b15b15efcc

Subscribe to this mod's changes

hermes-skill-developer is an agent published in the GitHub repository davidgut1982/hermes-toolkit (2 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 673 once invoked, about $0.0005 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.