hermes-skills

hermes-skills is a plugin for Claude Code from prompt-security/clawsec. Its manifest loads nothing; the 2 skills it bundles cost 54 tokens per session together, scanned A, original, AGPL-3.0.

A security add-on for Hermes and related coding agents. It checks agent instruction files such as SOUL.md and verifies that installed skills have not been changed unexpectedly.

In plain words
What is it for?
It is for auditing agent setups, checking skill integrity, and receiving security recommendations.
Why use it?
It helps detect instruction drift, security issues, and altered skills before they affect an agent.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Good fit It is for auditing agent setups, checking skill integrity, and receiving security recommendations.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add prompt-security/clawsec/plugin install hermes-skills
About the project

ClawSec is a collection of security skills and signed advisory data for AI agent runtimes. It helps operators verify skills, detect configuration changes, audit agent environments, and require approval for risky installations across OpenClaw, NanoClaw, Hermes, and Picoclaw. The catalogue entries are ClawSec’s skills, plugins, and instructions for those runtimes.

prompt-security/clawsec · 1,102 stars · on GitHub · prompt.security

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.

Clone the repo
git clone --depth 1 https://github.com/prompt-security/clawsec

Made for: Claude Code.

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.

agentmods badge for hermes-skills

README.md
[![agentmods](https://agentmods.dev/badge/plugins/prompt-security/clawsec/hermes-skills/github.svg)](https://agentmods.dev/plugins/prompt-security/clawsec/hermes-skills)
Your own site
<a href="https://agentmods.dev/plugins/prompt-security/clawsec/hermes-skills"><img src="https://agentmods.dev/badge/plugins/prompt-security/clawsec/hermes-skills/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.

agentmods 80×15 button for hermes-skills

Your own site · 80×15
<a href="https://agentmods.dev/plugins/prompt-security/clawsec/hermes-skills"><img src="https://agentmods.dev/badge/plugins/prompt-security/clawsec/hermes-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 2 skills cost 54 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Security

Grade A, and why

hermes-skills 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 7d 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.

.claude-plugin/marketplace.json#hermes-skills · 8 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Contents

What it installs

The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 54 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside marketplace.json#hermes-skills 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.

  1. 7d ago First seen · 8 lines scan A 356d7adc5aea

Subscribe to this mod's changes

hermes-skills is a plugin published in the GitHub repository prompt-security/clawsec (1,102 stars, last pushed yesterday), licensed AGPL-3.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.

Related

Other plugins, from other repositories

lobu

Give Claude shared, permission-aware company context, durable organizational memory, and governed actions through Lobu MCP.

lobu-ai/lobu · not measured

agent-development

Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Covers Task tool delegation, model selection, memory limits, and declarative instruction design. Use when: creating custom agents, designing agent descriptions for auto-delegation…

danstrem2/clawdbot-skill-master-pack · not measured

ai-sdk-core

Build backend AI with Vercel AI SDK v6 stable. Covers Output API (replaces generateObject/streamObject), speech synthesis, transcription, embeddings, MCP tools with security guidance. Includes v4→v5 migration and 15 error solutions with workarounds. Use when: implementing AI SDK v5/v6, migrating versions…

danstrem2/clawdbot-skill-master-pack · not measured

ai-sdk-ui

Build React chat interfaces with Vercel AI SDK v6. Covers useChat/useCompletion/useObject hooks, message parts structure, tool approval workflows, and 18 UI error solutions. Prevents documented issues with React Strict Mode, concurrent requests, stale closures, and tool approval edge cases. Use when: implementing AI…

danstrem2/clawdbot-skill-master-pack · not measured

azure-auth

Microsoft Entra ID (Azure AD) authentication for React SPAs with MSAL.js and Cloudflare Workers JWT validation using jose library. Full-stack pattern with Authorization Code Flow + PKCE. Prevents 8 documented errors. Use when: implementing Microsoft SSO, troubleshooting AADSTS50058 loops, AADSTS700084 refresh token…

danstrem2/clawdbot-skill-master-pack · not measured

better-auth

Self-hosted auth for TypeScript/Cloudflare Workers with social auth, 2FA, passkeys, organizations, RBAC, and 15+ plugins. Requires Drizzle ORM or Kysely for D1 (no direct adapter). Self-hosted alternative to Clerk/Auth.js. Use when: self-hosting auth on D1, building OAuth provider, multi-tenant SaaS, or…

danstrem2/clawdbot-skill-master-pack · not measured