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.
npx skills add AtlasOmnia/hermes-custom-pack --skill hermes-plugin-evaluationgit clone --depth 1 https://github.com/AtlasOmnia/hermes-custom-packWrote 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.
[](https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/hermes-plugin-evaluation)<a href="https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/hermes-plugin-evaluation"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/hermes-plugin-evaluation.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00037 | $0.00743 |
| Opus 5 | $0.00018 | $0.00371 |
| Sonnet 5 | $0.00007 | $0.00149 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
hermes-plugin-evaluation 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.
This is a copy
100% identical to hermes-plugin-evaluation — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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 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
- Load authoritative Hermes context first when the task involves Hermes plugins:
- Load
hermes-agentif available. - Prefer official Hermes docs for CLI syntax and plugin lifecycle.
- Inspect the repository without installing it:
- README / docs
plugin.yamlpyproject.toml,package.json, lockfilesLICENSE,NOTICE, or equivalent- setup wizard files and
after-installnotes - tool definitions, platform adapter files, webhook/tunnel code
- 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.
- 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.”
- 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.
- 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.
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.
- 7d ago First seen · 79 lines · 37 tokens per session scan A b7343b474243
hermes-plugin-evaluation is a skill published in the GitHub repository AtlasOmnia/hermes-custom-pack (56 stars, last pushed 22d ago), licensed MIT. It adds 37 tokens to every session and 743 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to hermes-plugin-evaluation, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
config
Use when configuring obshare-cli credentials, checking saved settings, testing connectivity, clearing local config, or setting optional Obsidian bridge values used by the V0.2.0 direct-share stack.
obshare-cli
Use when setting up obshare-cli 0.2.0, reviewing available commands, or choosing the right command for config, upload, permission, history, delete, and the plugin-first direct-share workflow.
agent-dreaming-agnostic
Memory-agnostic background consolidation — reviews sessions, scores candidates, promotes durable insights to the active memory backend (built-in MEMORY.md or Holographic). Three-phase (Light/Deep/Condensation/REM). Run via cron or manually.
permission
Use when changing Feishu document visibility, copy permissions, or download permissions for an uploaded document token.
upload
Use when uploading a Markdown note to Feishu, optionally applying public or copy/download permissions, or requesting JSON upload results for automation or the Obsidian plugin direct-share flow.
delete
Use when removing a Feishu document by token and cleaning the matching entry from local obshare-cli upload history.