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 Ertinox7711/SGRR-AGI-V2 --skill talk-to-hermesgit clone --depth 1 https://github.com/Ertinox7711/SGRR-AGI-V2Wrote 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/ertinox7711/sgrr-agi-v2/talk-to-hermes)<a href="https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/talk-to-hermes"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/talk-to-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.
<a href="https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/talk-to-hermes"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/talk-to-hermes.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 | $0.00196 | $0.00973 |
| Opus 5 | $0.00098 | $0.00487 |
| Sonnet 5 | $0.00039 | $0.00195 |
| Haiku 4.5 | $0.00020 | $0.00097 |
Grade A, and why
talk-to-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 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.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
talk-to-hermes — direct bridge to the Hermes agent (no Discord)
Hermes = the NeverGiveUp agent (Nous Research Hermes fork) in WSL Ubuntu-22.04. It runs on the operator's Claude Max OAuth. Same agent that answers his Discord DMs, but here you reach it directly from a shell — no Discord round-trip.
The command
wsl -- bash -lc 'ask-hermes "your prompt here"'
ask-hermes wraps hermes -z (oneshot): it loads Hermes's tools, memory, rules,
SOUL.md persona, and any AGENTS.md in the CWD, auto-bypasses approvals, and prints
only the final response text to stdout. Wrapper lives at
~/.local/bin/ask-hermes in WSL (on the login PATH).
Check it's installed:
wsl -- bash -lc 'command -v ask-hermes'
Long or tricky prompts → use a file (-f)
WSL invoked through Windows mangles $, backticks, parens, and nested quotes.
For anything beyond a short single-quoted sentence, write the prompt to a temp
file and pass -f — no escaping headaches:
Writethe prompt toC:\Users\YOU\AppData\Local\Temp\hermes-prompt.txt- Run:
wsl -- bash -lc 'ask-hermes -f /mnt/c/Users/YOU/AppData/Local/Temp/hermes-prompt.txt'
(Windows C:\...\Temp\x.txt → WSL /mnt/c/.../Temp/x.txt.) Stdin also works:
echo "..." | ask-hermes.
Gotchas (read before every call)
- Quota. Each call = one LLM turn billed to the operator's Claude Max. Don't spam; batch your question into one well-formed prompt.
- Approvals are auto-bypassed — Hermes CAN act. Be explicit about intent:
- Info only → start the prompt with
Réponds seulement, n'agis pas : - Action wanted → say plainly what to do (e.g.
Ajoute une tâche kanban : ...).
- Info only → start the prompt with
- No conversation thread. Each call is independent (oneshot ignores
--continue/--resume). But Hermes's persistentmemories/+kanban.dbload every time — that's the shared brain. Put needed context IN the prompt. - Never set
ANTHROPIC_API_KEY. It would make Hermes prune its OAuth credential and break the gateway. The wrapper unsets it defensively; just never pass one. - French. Hermes + the operator operate in French; write prompts in French.
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 · 89 lines · 196 tokens per session scan A c13a442605a8
talk-to-hermes is a skill published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 4d ago), licensed MIT. It adds 196 tokens to every session and 973 once invoked, about $0.0010 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.
Other skills, from other repositories
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
taiyi-diagram-c4
A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.
retrospective-audit
Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…
docs
Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…
tmux-lane-orchestrator
Manage one tmux agent lane from its matching ops pane, inspect live pane state and Codex logs on cold start, and produce concise manager summaries for OpenClaw and adjacent project work.