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 MilkyWay008/Hermes-OTG --skill otg-windows-troubleshootinggit clone --depth 1 https://github.com/MilkyWay008/Hermes-OTGWrote 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/milkyway008/hermes-otg/otg-windows-troubleshooting)<a href="https://agentmods.dev/skills/milkyway008/hermes-otg/otg-windows-troubleshooting"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/otg-windows-troubleshooting/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/milkyway008/hermes-otg/otg-windows-troubleshooting"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/otg-windows-troubleshooting.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 | $0.02074 |
| Opus 5 | $0.00009 | $0.01037 |
| Sonnet 5 | $0.00003 | $0.00415 |
| Haiku 4.5 | $0.00002 | $0.00207 |
Grade C, and why
otg-windows-troubleshooting scanned grade C with 1 finding 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 9d 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.
Encoded or obfuscated payloadhighSupply chain
base64 or hex that is decoded and executed hides what actually runs from anyone reading the file.
code = marshal.loads(open(r'..._extracted\\PYZ.pyz_extracted\\tools\\code_execution_tool.pyc','rb').read()[16:]) How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OTG Windows Troubleshooting
TRIGGER: Work on the OTG Hermes build on Windows — editing .cmd/.bat launchers, debugging execute_code, tracing env vars into the frozen backend, or needing to know what Hermes-OTG.exe actually does internally.
Hard Rule: Diagnose First, Get Approval Before Patching
The user runs a diagnose-first discipline (also in SOUL.md Hasty-Action Rule). Report findings, let the user decide, then act. Do NOT jump to patching/fixing when asked to "check the log" or "test" — that is a diagnosis request, not a fix mandate. Mid-session I patched without approval and got called out: "I asked you to check the log for errors, but I didn't ask you to fix any errors."
- Asked to investigate → investigate, report, propose. Do not modify.
- Asked to fix → backup first (
.bak-YYYYMMDD-HHMM), state exactly what you'll change, get agreement. - Every edit to a file that matters: make a backup copy first. No exceptions.
Companion Skill: Env-Safe Execution
When troubleshooting Windows systems FROM inside the OTG and the work involves running
executables (updaters, installers, CLIs, host-Hermes commands), ALSO load
skill_view(name='env-safe-execution') as a companion — the OTG env
(HERMES_HOME=E:\...) leaks into every subprocess spawned for host-machine work and can
redirect an app to the wrong install. This is exactly how the host updater grabbed the OTG
install (2026-08-06 incident): a subprocess inherited HERMES_HOME and the updater
targeted E: instead of C:.
Pitfall 1: CRLF Corruption — the #1 .cmd/.bat gotcha
patch and write_file tools write LF (\n) line endings into Windows batch files. cmd.exe silently SKIPS lines after a bare LF, so a set VAR=... line placed after an LF-ending comment never executes — and there is NO error message.
Symptom pattern that identifies this: env vars set EARLIER in the launcher (e.g. HERMES_HOME) reach the process, but a var added later in the file does not — even though the file "looks right" and propagation tests pass.
What ships with it
2 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.
- 9d ago First seen · 109 lines · 17 tokens per session scan C f4d52251b37d
otg-windows-troubleshooting is a skill published in the GitHub repository MilkyWay008/Hermes-OTG (15 stars, last pushed 28d ago), licensed MIT. It adds 17 tokens to every session and 2,074 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (encoded or obfuscated payload). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
flask-werkzeug-attack
Exploit Flask/Werkzeug debugger exposure for traceback and SECRET leaks.
nsm-session-pivot
Pivot through Zeek session and protocol metadata from a packet capture (read-only) — connection listing, service filtering, and following a connection uid into dns/http/ssl logs. Use when reconstructing what sessions occurred in a capture, following a connection across protocols, or investigating retrospectively.
hermes-plugin-development
Use when: creating, debugging, or integrating Hermes Agent plugins, including Python backend plugins (tools, hooks, routers, middleware) and JavaScript Hermes Desktop runtime plugins.
node-inspect-debugger
Debug Node.js with node inspect, inspector attach, breakpoints, Chrome DevTools Protocol, heap snapshots, and CPU profiles.
incident-commander
Autonomous incident detection, root-cause analysis, and self-healing for Linux/Docker production environments. Activate when the user mentions: server down, high CPU, memory leak, disk full, service crash, deployment failure, alert firing, on-call page, or any infrastructure emergency. Also activates on scheduled…
analyzing-slack-space-and-file-system-artifacts
Examine file system slack space, MFT entries, USN journal, and alternate data streams to recover hidden data and reconstruct file activity on NTFS volumes.