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 agentmods add instructions/thomasbek3/hermes-bot-kit/agents-mdgit 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/instructions/thomasbek3/hermes-bot-kit/agents-md)<a href="https://agentmods.dev/instructions/thomasbek3/hermes-bot-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/thomasbek3/hermes-bot-kit/agents-md.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 | $0.01568 | $0.01568 |
| Opus 5 | $0.00784 | $0.00784 |
| Sonnet 5 | $0.00314 | $0.00314 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade E, and why
hermes-bot-kit AGENTS.md scanned grade E with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/thomasbek3/hermes-bot-kit/master/install.sh | bash Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.hermes/desktop-plugins/bubble-mode ~/.hermes/desktop-plugins/computer-viewer ~/.hermes/desktop-plugins/bot-sections Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/thomasbek3/hermes-bot-kit/master/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions for Hermes Bot Kit
You are installing desktop plugins for Hermes Desktop. Everything here is
safe to run unattended: no sudo, no prompts, idempotent, existing files are
backed up (*.bak.<timestamp>) before overwrite.
Install the desktop plugins (default)
curl -fsSL https://raw.githubusercontent.com/thomasbek3/hermes-bot-kit/master/install.sh | bash
Install just one:
KIT_SKIP_COMPUTER=1 KIT_SKIP_SECTIONS=1 bash -c "$(curl -fsSL https://raw.githubusercontent.com/thomasbek3/hermes-bot-kit/master/install.sh)" # Bubble Mode only
KIT_SKIP_BUBBLES=1 KIT_SKIP_SECTIONS=1 bash -c "$(curl -fsSL https://raw.githubusercontent.com/thomasbek3/hermes-bot-kit/master/install.sh)" # Computer viewer only
KIT_SKIP_BUBBLES=1 KIT_SKIP_COMPUTER=1 bash -c "$(curl -fsSL https://raw.githubusercontent.com/thomasbek3/hermes-bot-kit/master/install.sh)" # Bot Sections only
Into a named Hermes profile instead of the default home:
HERMES_HOME="$HOME/.hermes/profiles/<name>" bash -c "$(curl -fsSL https://raw.githubusercontent.com/thomasbek3/hermes-bot-kit/master/install.sh)"
The script exits non-zero and installs nothing if a downloaded plugin fails
its sanity check (node --check + content marker).
Verify the install
test -f ~/.hermes/desktop-plugins/bubble-mode/plugin.js && echo bubble-mode OK
test -f ~/.hermes/desktop-plugins/computer-viewer/plugin.js && echo computer-viewer OK
test -f ~/.hermes/desktop-plugins/bot-sections/plugin.js && echo bot-sections OK
Folder names must be exactly bubble-mode, computer-viewer, and
bot-sections (they must match the plugin ids). Do not rename them.
After installing — needs the human or a running app
Hermes Desktop loads disk plugins at startup and on plugin reload. One of:
- In Hermes Desktop: command palette (Cmd+Shift+P / Ctrl+Shift+P) → Reload plugins, or
- Restart the Hermes Desktop app.
An agent without GUI control cannot complete this step; tell the user to do it. Then:
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.
- 3d ago First seen · 136 lines · 1,568 tokens per session scan E 6190d2b8b6f9
hermes-bot-kit AGENTS.md is an instructions file published in the GitHub repository thomasbek3/hermes-bot-kit (50 stars, last pushed 4d ago), licensed MIT. It adds 1,568 tokens to every session, about $0.0078 per session on Opus 5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
logion AGENTS.md
Instructions for nicolasmelo1/logion, covering agents.md, protocol sources are mandatory, what logion is, hard rules (ci will reject violations) and working model.
open-computer-use CLAUDE.md
Claude Code instructions for Wide-Moat/open-computer-use, covering project instructions, branches and scope, global rules (apply to every branch), language and license headers.
silenthand-cua AGENTS.md
AGENTS.md instructions for edosulai/silenthand-cua, covering graphify and public repo hygiene.
silenthand-cua CLAUDE.md
Claude Code instructions for edosulai/silenthand-cua, covering graphify and public repo hygiene.
tiptour-macos CLAUDE.md
Claude Code instructions for milind-soni/tiptour-macos, a project described as: Open-Source alternative to Google's AI-enabled pointer.
hermes-agent-mt AGENTS.md
AGENTS.md instructions for cyborg-garden/hermes-agent-mt, covering hermes agent - development guide, what hermes is, contribution rubric — what we want / what we don't, what we want and what we don't want (rejected even when well-built).