AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Hermes Plugin Evaluation

skill-atlasomnia-donna-starter-hermes-plugin-evaluation · by AtlasOmnia

hermes-plugin-evaluation — Evaluate third-party Hermes Agent plugins before installation: cost, licensing, required services, data flow, dependencies, and setup risk.

No reviews yet
0 installs
0 views
view→install

Install

$ agentstack add skill-atlasomnia-donna-starter-hermes-plugin-evaluation

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-atlasomnia-donna-starter-hermes-plugin-evaluation)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
5d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Hermes Plugin Evaluation? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Hermes Plugin Evaluation

Use this when the user asks about installing, trusting, pricing, or using a third-party Hermes Agent plugin or integration.

Goal

Give a practical go/no-go read before touching the live Hermes gateway. Separate:

  • Plugin code cost/license — whether the repository itself is public/open-source/free to install.
  • Service cost — required SaaS account, usage billing, phone/SMS/voice costs, model API costs, tunnels, hosted routing, or paid feature gates.
  • Operational risk — what data leaves Hermes, whether the plugin opens public webhooks/tunnels, and whether it modifies gateway behavior.

Fast evaluation workflow

  1. Load authoritative Hermes context first when the task involves Hermes plugins:
  • Load hermes-agent if available.
  • Prefer official Hermes docs for CLI syntax and plugin lifecycle.
  1. Inspect the repository without installing it:
  • README / docs
  • plugin.yaml
  • pyproject.toml, package.json, lockfiles
  • LICENSE, NOTICE, or equivalent
  • setup wizard files and after-install notes
  • tool definitions, platform adapter files, webhook/tunnel code
  1. Answer cost precisely:
  • Say “plugin appears free/public” only for the repo/installable code.
  • Do not infer the hosted service is free just because the plugin is public.
  • Identify paid dependencies: phone numbers, SMS/MMS, voice minutes, hosted tunnels, OpenAI/Anthropic/etc. APIs, storage, or managed accounts.
  1. Check for a public pricing page, but treat absence as unknown, not free:
  • If pricing is missing/404/gated, say “pricing not publicly obvious; confirm with vendor.”
  1. Report required credentials and data paths:
  • Required env vars/API keys.
  • Optional credentials that change cost or data flow.
  • Whether inbound messages/calls pass through vendor infrastructure.
  1. Recommend a safe rollout:
  • Test in a non-critical Hermes profile or disabled gateway first.
  • Avoid putting it on the main gateway until pricing, credentials, and data flow are understood.
  • Run plugin-specific doctor/diagnostics before enabling public channels.

Response shape the user prefers

Keep it concise and decisive:

  • Short answer first: free, paid, mixed, or unclear.
  • What I verified as bullets.
  • Cost implication as bullets.
  • Recommended next step if installation/security matters.

Avoid broad explanations of Hermes unless he asks. He usually wants the practical answer.

Pitfalls

  • Public repo ≠ free service. Many plugins are just glue to a paid platform.
  • No LICENSE file means unclear license, even if GitHub visibility is public.
  • Phone/SMS/voice are rarely free at scale. Assume carrier/service costs unless docs explicitly say otherwise.
  • Hosted tunnels/webhooks imply external data flow. Flag this before installation.
  • Do not install first just to answer pricing/trust questions. Inspect first, then ask/confirm before side effects.
  • — condensed findings from evaluating inkbox-ai/hermes-agent-plugin for cost, setup requirements, and data-flow implications.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.