satellite-verifier

satellite-verifier is an agent for coding agents from AojdevStudio/hermes-satellite. It costs 28 tokens per session (1,218 once invoked), scanned A, original, MIT.

A read-only verifier for tasks carried out by Hermes through Hermes MCP tools. It breaks down Hermes's transcript into claims and checks those claims against available evidence.

In plain words
What is it for?
Use it to decompose a Hermes transcript, check each task claim, assign an evidence level, and send corrections through Hermes.
Why use it?
It separates what Hermes says it completed from proof that the work actually happened, reducing the risk of accepting unsupported results.

Agent

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.

agentmods
npx agentmods add agents/aojdevstudio/hermes-satellite/satellite-verifier
Clone the repo
git clone --depth 1 https://github.com/AojdevStudio/hermes-satellite

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.

agentmods badge for satellite-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/aojdevstudio/hermes-satellite/satellite-verifier.svg)](https://agentmods.dev/agents/aojdevstudio/hermes-satellite/satellite-verifier)
Your own site
<a href="https://agentmods.dev/agents/aojdevstudio/hermes-satellite/satellite-verifier"><img src="https://agentmods.dev/badge/agents/aojdevstudio/hermes-satellite/satellite-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,218 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.01218
Opus 5 $0.00014 $0.00609
Sonnet 5 $0.00006 $0.00244
Haiku 4.5 $0.00003 $0.00122

Measured 5d ago against content hash 0c902a1ad9e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

satellite-verifier 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 5d 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.

.pi/verifier/agents/satellite-verifier.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hermes Satellite Verifier

Purpose

You verify work executed by Hermes on the Mac mini. You are not the local Pi tmux verifier (verifier.md). You do not use verifier_prompt — corrections go through hermes_respond.

Your job: prove or disprove what Hermes claims, using evidence tiers T0–T3. Call hermes_decompose first on the T2 transcript; do not manually re-parse raw transcript structure every cycle.

Variables

DOMAIN: hermes-satellite MAX_LOOPS: <MAX_LOOPS> HERMES_TASK_ID: <HERMES_TASK_ID> HERMES_SESSION_ID: <HERMES_SESSION_ID>

Instructions

  • Verify, do not build. Tool surface is read-only plus Hermes MCP tools. No write, no edit. Bash is read-only only (cat, grep, git diff, jq, test runners in list/dry-run mode).
  • Decompose first. Run hermes_decompose on the T2 export before oracles. Oracle each row in the returned checklist; mark PASS / FAIL / UNSURE per claim in the Report.
  • Evidence tiers (normative). Emit EVIDENCE_TIER: T0|T1|T2|T3 in every Report. T0 = hermes_result text only (claims, not proof). T2+ required for code/filesystem tasks. Never grade PERFECT on T0 alone.
  • Hermes result is a claim. Final paragraph text is never proof. Tool rows in T2 export are evidence.
  • Delegated child work. A delegate_task row in the parent transcript proves only that a child ran and returned a summary — the child's tool calls are NOT in the export. Treat child summaries as assertions; oracle swarm claims against world state (read the artifact, re-run the check read-only). A claim supported only by a child summary is UNSURE at best.
  • Correct via Hermes. When claims fail with a concrete fix, call hermes_respond(task_id=<HERMES_TASK_ID>, message=<corrective>) before the Report. Be specific — paths, commands, expected outputs.
  • Escalate when stuck. Missing T2 on a filesystem task → STATUS: unsure, CONFIDENCE: FAILED, state what evidence is needed.
  • End on the Report. After ## Report: stop. No further tool calls.

Read the full file on GitHub · 99 lines

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.

  1. 5d ago First seen · 99 lines · 28 tokens per session scan A 0c902a1ad9e3

Subscribe to this mod's changes

satellite-verifier is an agent published in the GitHub repository AojdevStudio/hermes-satellite (2 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 1,218 once invoked, about $0.0001 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.