A command for checking or messaging the Hermes assistant running in WSL and connected to Discord. It can report the service status, inspect its configuration, check authentication, post a message, or send a question.

Use it to check whether Hermes is running, see its active model and services, verify its Anthropic token, send Discord information without an LLM turn, or ask Hermes a question. An authentication token is a secret credential that lets software use a service.

It keeps routine checks and messages separate from questions that consume language-model quota. It also helps identify when the assistant's authentication token is missing or has stopped working.

hermes — Command for Claude Code by Ertinox7711

Install

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.

Clone the repo

git clone --depth 1 https://github.com/Ertinox7711/SGRR-AGI-V2

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/hermes/github.svg)](https://agentmods.dev/commands/ertinox7711/sgrr-agi-v2/hermes)

Your own site

<a href="https://agentmods.dev/commands/ertinox7711/sgrr-agi-v2/hermes"><img src="https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/hermes/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/ertinox7711/sgrr-agi-v2/hermes"><img src="https://agentmods.dev/badge/commands/ertinox7711/sgrr-agi-v2/hermes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 654 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00041	$0.00654
Opus 5	$0.00020	$0.00327
Sonnet 5	$0.00008	$0.00131
Haiku 4.5	$0.00004	$0.00065

Measured 2d ago against content hash e388dfadc79e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hermes 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 2d 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.

commands/hermes.md · 42 lines

What it actually says

NeverGiveUp est l'assistant personnel de the operator : Hermes Agent dans WSL Ubuntu, modele claude-sonnet-5 via l'abonnement Max, canal Discord #<AGENT_CHANNEL>. Il connait les projets, le kanban et les memoires de the operator. Chaque question lui coute un tour de quota Max — groupe tes demandes, ne le spamme pas.

Argument recu : $ARGUMENTS

Ce que tu fais selon l'argument

status → est-il en vie ? wsl -u YOU -- bash -lc 'systemctl --user is-active hermes-gateway; systemctl --user show hermes-gateway -p MainPID'
self → son portrait derive du disque (modele reel, replis, services, skills, crons) : wsl -u YOU -- bash -lc 'hermes-self'
auth → controle de la regle 9 (le jeton Anthropic qui meurt en silence) : wsl -u YOU -- bash -lc 'grep -c "^ANTHROPIC_TOKEN=" ~/.hermes/.env' Si c'est 0, la reparation ne peut etre faite que par the operator : claude setup-token sous Windows, puis bash ~/.hermes/scripts/hermes-set-anthropic-token.sh dans WSL.
dis: <message> → poste sur Discord sans consommer de tour LLM : wsl -u YOU -- bash -lc 'tell-hermes "<message>"'
toute autre chose → une vraie question. Ecris-la d'abord dans un fichier (les caracteres speciaux ne survivent pas a la ligne de commande) puis : wsl -u YOU -- bash -lc 'ask-hermes -f /mnt/c/Users/YOU/AppData/Local/Temp/hermes-prompt.txt'

Regles

ANTHROPIC_API_KEY doit rester absente de l'environnement WSL : sa presence detruit le jeton OAuth de Hermes. Les wrappers la retirent seuls — ne l'exporte jamais a la main.
Ne relance jamais les daemons Discord archives (responder.py, presence_bot.py, discord_poller.py, watchdog.py, auto_executor.py, ni les crons trio-*). Claude Code n'a plus de voix dans Discord.
Avant de demander quoi que ce soit a the operator, cherche d'abord : wsl -u YOU -- bash -lic 'brain-rag "<la question>"'.

Changes

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.

2d ago First seen · 42 lines · 41 tokens per session scan A e388dfadc79e

Subscribe to this mod's changes

hermes is a command published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 654 once invoked, about $0.0002 per session on Opus 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 2026-09-09.

Building agents Productivity ai automation claude developer-tools

hermes

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Ce que tu fais selon l'argument

Regles

What this file has done since we first saw it

Other commands, from other repositories

evolve

suggest-automation

instinct-import

instinct-export

handover

rewind-summary