Hermes Agent is an AI assistant that learns from its use by creating and improving skills, retaining knowledge, searching past conversations, and adapting to its users. It is for people who want to run an agent through a terminal or messaging platforms while connecting it to different AI models and scheduled tasks.
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 NousResearch/hermes-agent --skill initiate-setupgit clone --depth 1 https://github.com/NousResearch/hermes-agentWrote 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/nousresearch/hermes-agent/initiate-setup)<a href="https://agentmods.dev/skills/nousresearch/hermes-agent/initiate-setup"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/initiate-setup/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/nousresearch/hermes-agent/initiate-setup"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/initiate-setup.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.02352 |
| Opus 5.5 | $0.00007 | $0.00941 |
| Sonnet 5.5 | $0.00003 | $0.00470 |
| Haiku 4.5 | $0.00002 | $0.00235 |
Grade A, and why
initiate-setup 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 8d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initiate Setup Skill
Runs a new user's first conversation with Hermes. On desktop the app plays the opening (welcome, name, accent); you take over from the accent answer: apps, plugins, layout, the tour offer, the fork, then one first task in its own chat with start_chat. You do not do the task, install anything, or read the machine: the task chat does that, guided by the first-task skill.
When to Use
- The
/initiate-setupcommand started this turn. - The user asks to run setup again from the setup chat.
Never inside a task chat. When setup_completed_at is set, or start_chat already started a task here, setup is done: say so in one line and go to beat 5 for a new task.
Prerequisites
The setup profile's desktop tools:
setup_chooseshows one card and blocks until the user answers. Always sendoptions: at most 12{id, label, detail}, or[]for the app's own list (free text forquestion). Returns{outcome, picked, label, said, next, handoff}: name a pick by itslabel, never its id;typedmeans the user wrote words that name no row (said), so nothing was picked; do whatnextsays in the same turn; the fork's result carrieshandofffor beat 7.start_chatstarts a visible chat inprofilewhose first user message is yourmessage. Returns{status: "started", ...}or{status: "rejected", reason}.apply_layout,gui_tour, andmanage_connections(connect shows the sign-in card).
No terminal, file, web, browser, memory or clarify tools here.
How to Run
Facts follow the skill as one JSON block. Read them as they are; a missing key means unknown, so never guess it. Never recite machine. The facts describe the machine Hermes runs on; when the user disagrees, believe the user. The app fills the apps, plugins, tour, fork and machine_use rows itself.
Work one beat at a time. When the history holds the name and accent answers, start at beat 1; otherwise run the Opening.
Quick Reference
| # | Beat | Tool call |
|---|---|---|
| - | Welcome, name, accent | played by the app |
| 1 | Apps they use | card apps |
| 2 | Plugins | card plugins (records only) |
| 3 | Layout | card layout |
| 4 | Tour offer | card tour; one gui_tour |
| 5 | The fork | card fork |
| 6 | Narrow to one task | card machine_use only for machine |
| 7 | Handoff | start_chat, once |
| 8 | After the handoff | one line, then stop |
What ships with it
1 file beside SKILL.md 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.
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.
- 8d ago First seen · 148 lines · 17 tokens per session scan A 7ddd8fb3002e
initiate-setup is a skill published in the GitHub repository NousResearch/hermes-agent (254,120 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 2,352 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 2026-10-08.
Other skills, from other repositories
content-hash-cache-pattern
Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".
manage-settings
Any explicit Muse Code setting question or change (model, reasoning effort, /settings) requires a silent readskill call for bundled:manage-settings as FIRST ACTION—no assistant text or other tool first. Never use for repository, app, eval, or other non-Muse configuration.
Read or triage email, clean up an inbox, draft or send messages, and check delivery. Use for the user's connected mailbox or your own email, including questions about its availability; choose the correct sender and follow the confirmation policy.
read-session
Locate and read Muse Code's OWN session logs — the current session or a prior one. Use when the user asks to pull context from, continue, summarize, or inspect a previous Muse Code session, asks to restore or recover work that was lost, wiped, or overwritten and might survive in an earlier session's log, references an…
device_data
Read cached contacts and calendar events from Muse storage. Delete Muse's local copy of either source without modifying paired devices.