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 skills/aojdevstudio/hermes-satellite/hermes-dispatchnpx skills add AojdevStudio/hermes-satellite --skill hermes-dispatchgit clone --depth 1 https://github.com/AojdevStudio/hermes-satelliteWrote 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/aojdevstudio/hermes-satellite/hermes-dispatch)<a href="https://agentmods.dev/skills/aojdevstudio/hermes-satellite/hermes-dispatch"><img src="https://agentmods.dev/badge/skills/aojdevstudio/hermes-satellite/hermes-dispatch.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 | $0.00085 | $0.03015 |
| Opus 5 | $0.00043 | $0.01507 |
| Sonnet 5 | $0.00017 | $0.00603 |
| Haiku 4.5 | $0.00009 | $0.00301 |
Grade A, and why
hermes-dispatch 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 4d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the dispatcher and the satellite verifier, never the worker. Hermes on the bridge host executes; you write a checkable prompt, poll, then oracle every claim Hermes makes against tool evidence before you trust a word of it. Two leading ideas govern the whole skill:
- Scoped dispatch: you do NOT do the task locally in parallel. You craft the prompt so Hermes can finish it, then you verify. No "I'll just edit this here while Hermes also runs."
- Evidence tier: the final result text is a claim, not proof. Confidence is capped by the strength of evidence you can actually inspect (T0 text only is weak; T2 full transcript is strong). A verify pass that stops at the result paragraph grades PARTIAL at best.
The loop is: submit -> poll -> pull evidence -> oracle -> report -> reloop or finish. Run it in order.
Step 0: Preflight the bridge
- Endpoint: set
$HERMES_MCP_URLto your bridge's MCP URL, e.g.http://<bridge-host>:8081/mcp. Bind the bridge to a private tailnet or VPN address, never a public interface; any stale LAN address is dead by design. - Auth:
Authorization: Bearer $HERMES_MCP_TOKEN, required. Keep the token value in your secret manager or a local.env(never commit it). - This client drops to relay/offline sometimes, so preflight in order:
tailscale statusup, then/healthzreturnsok, then the MCPinitializereturns the tool list. (/healthzis unauthenticated and does NOT prove tool auth; the initialize is the real check.) - Tool names carry a per-harness prefix (Claude Code
mcp__hermes-async__hermes_submit, Hermes Agentmcp_hermes_async_*, others connect by URL). Base names are constant. Confirm exact arg names against the livetools/liston connect.
Done when: initialize succeeded and the hermes_* tools are visible.
Step 1: Submit with a ## Acceptance block
Keep the dispatched task small and scoped; large multi-part prompts hit the 600s hard timeout. The prompt MUST contain a ## Acceptance section:
What ships with it
3 files 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.
- 4d ago First seen · 152 lines · 85 tokens per session scan A 85a9d573ee99
hermes-dispatch is a skill published in the GitHub repository AojdevStudio/hermes-satellite (2 stars, last pushed 3d ago), licensed MIT. It adds 85 tokens to every session and 3,015 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
scarf-template-author
Scaffold a new Scarf project OR enrich an existing one after a Scarf "Upgrade Project" — dashboard, optional configuration schema, optional cron job, AGENTS.md, and (via the scarf-miniapp-author skill) a starter mini-app — from a short conversational interview. Output is immediately usable locally and cleanly…
scarf-miniapp-author
Author a Scarf mini-app — a small sandboxed web surface (HTML/CSS/JS) that renders inside a project's cockpit and talks to the bound Hermes session + project data through the versioned window.scarf bridge. Use to build a bespoke panel (a task board, an approval queue, a chart, a data table) for a project.
safe-update-restart
Safe update/restart procedure for a production Hermes VPS that runs many live APIs, services, and multiple agent gateways sharing one venv. Full backup → controlled window → restart → verify every service and endpoint after. Never blind-restart.
computer-use
Control local Mac apps through Computer Use. Use for tasks that require reading or operating app UI by clicking, typing, scrolling, dragging, pressing keys, or setting values.
record-and-replay
Record the user's actions on their Mac with Record & Replay, and turn it into a reusable ChatGPT skill from the captured event stream.
silenthand
Use for SilentHand CUA, Computer Use MCP, silenthanddoctor, getappstate, click/type without stealing focus, or attaching the local mcp-wrapper. Unofficial research host on ChatGPT CUA binaries — never Raise, never open -a, never invent tools. Not Hermes computeruse / CuaDriver.app.