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 thomasbek3/hermes-bot-kit --skill computer-basicsgit clone --depth 1 https://github.com/thomasbek3/hermes-bot-kitWrote 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/thomasbek3/hermes-bot-kit/computer-basics)<a href="https://agentmods.dev/skills/thomasbek3/hermes-bot-kit/computer-basics"><img src="https://agentmods.dev/badge/skills/thomasbek3/hermes-bot-kit/computer-basics/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.
<a href="https://agentmods.dev/skills/thomasbek3/hermes-bot-kit/computer-basics"><img src="https://agentmods.dev/badge/skills/thomasbek3/hermes-bot-kit/computer-basics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00019 | $0.00545 |
| Opus 5.5 | $0.00008 | $0.00218 |
| Sonnet 5.5 | $0.00004 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
computer-basics 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computer basics
This skill is optional. Hermes does not inject it into the system prompt. Behavioral policy lives in the identity section and tool descriptions.
What this bot has
This profile can drive one pinned Orgo cloud computer:
orgo_computer_bash-- one shell command. Use this first for files, packages, git, opening a URL, starting a process.orgo_computer_screenshot-- photo of the desktop. No AI credits. Click coordinates are pixels in that image.orgo_computer_click/orgo_computer_type/orgo_computer_key-- direct mouse and keyboard. No AI credits. Screenshot after.orgo_computer_run-- only if this profile enabledhosted_run. Last resort hosted GUI agent. Spends plan credits.
Bash first, pixels second, hosted run last (measured 2026-08-25). Chrome to Google News: bash ~14s / $0; screenshot+click ~34s / $0; hosted run ~90s / ~12 cents.
Orgo Linux notes: Xvnc is DISPLAY=:99. Chrome as root needs
DISPLAY=:99 google-chrome --no-sandbox --disable-gpu --disable-dev-shm-usage URL.
Humans use the repo orgo-term script (WebSocket PTY, no credits).
Credentials and the computer UUID are not tool arguments. If no computer
is pinned, tell the user to run /computer. Do not retry that same turn.
One computer can run up to four screens. If this profile is pinned to a screen, screenshot/click/type/key touch only that screen; bash is shared by the whole machine.
Leave the computer clean
Other agents share this machine. When your task ends:
- Close the tabs and windows you opened. Leave what you found.
- Use the one browser profile that is already signed in. Never start a second profile.
- Never quit the 1Password app. Closing a browser window is fine.
- Do not leave downloads on the desktop. Move them or delete them.
- Take one last screenshot and confirm only your own windows are left.
Pairing the live view
The human watches the same VM in the computer-viewer pane. Pin the same machine there (per-bot endpoint).
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.
- 1mo ago Changed · +15 lines bc9f1a568023
- 1mo ago First seen · 44 lines · 19 tokens per session scan A 869ee2f55e56
computer-basics is a skill published in the GitHub repository thomasbek3/hermes-bot-kit (181 stars, last pushed 25d ago), licensed MIT. It adds 19 tokens to every session and 545 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
hermes-memory-providers
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
mnemosyne-memory-override
Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.
logion
Compact bootstrap skill for recall-first Logion discovery, inspection, install, update, and creator-course-management routing without loading the whole marketplace.
with-eval
Reviews code diffs against a structured checklist covering security (sql-injection, hardcoded-secret, unvalidated-input), reliability (missing-error-handling, resource-leak), and correctness (off-by-one, wrong-comparison). Use when reviewing PRs, audit diffs, or any code change where you want a categorised…
with-scripts
Bundled Gmail CLI example demonstrating the scripts/ entrypoint + src/ implementation split. Use as a template when your course ships real code that goes beyond a single shell script. Shows how to organize a course bundle that owns its codebase — no runtime package installation, all dependencies stdlib-only. Replaces…