Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MilkyWay008/Hermes-OTGnpx agentmods add skills/milkyway008/hermes-otg/otg-mcpWrote 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-mcp)<a href="https://agentmods.dev/skills/milkyway008/hermes-otg/otg-mcp"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/otg-mcp/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-mcp"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/otg-mcp.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 | $0.00042 | $0.01825 |
| Opus 5 | $0.00021 | $0.00912 |
| Sonnet 5 | $0.00008 | $0.00365 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
otg-mcp 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 12d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Management on OTG Hermes
Trigger: any MCP server install/configure/troubleshoot on an OTG (portable,
USB) Hermes package — adding a server to config.yaml, fixing "uv trampoline
failed", fixing "home points to C:\Users..." in pyvenv.cfg, or MCP tools
not loading after the package moved to a different drive.
Mental model
OTG Hermes is a self-contained portable bundle. It carries its own real
CPython at <OTG_ROOT>\dependencies\python\ and one venv per MCP server
under <OTG_ROOT>\mcp_servers\<name>\.venv\. Everything must stay relative
to OTG_ROOT because the drive letter changes between insertions
(E:, D:, I:, ...). Venvs built with uv embed the build machine's paths and
ship 45 KB trampoline stubs — both break the moment the package moves.
HARD RULES
- NEVER use system python or system uv to create/repair OTG venvs. Only
<OTG_ROOT>\dependencies\python\python.exe(the bundled real CPython 3.12). - NEVER hardcode drive letters in
config.yaml,pyvenv.cfg, or commands. - NEVER point
config.yamlcommand:at a venv.exeentry point (uv trampoline) — usepython -mwith the module instead. - ALWAYS let
fix-otg-pathshandle path portability — it runs on every launch; never hand-editpyvenv.cfgon the target machine.
Resolving OTG paths at runtime
echo $HERMES_HOME→<OTG_ROOT>\data\(note the trailing backslash)dirname "$HERMES_HOME"→<OTG_ROOT>— the OTG package root
What fix-otg-paths does (runs on every launch, idempotent)
- rewrites each venv's
pyvenv.cfghome =line to the CURRENT<OTG_ROOT>\dependencies\python - de-trampolines
Scripts\python.exe/pythonw.exe: copies the real bundled python.exe + DLLs beside them; original stub kept as*.uv-orig - re-scans
mcp_servers\*\.venv\pyvenv.cfgfor NEW venvs and auto-registers them (so user-installed servers are picked up without a manifest edit) - manifest:
<OTG_ROOT>\dependencies\scripts\fix-otg-paths.json - zero writes when nothing changed (fast path)
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.
- 12d ago First seen · 127 lines · 42 tokens per session scan A 712645ea3e43
otg-mcp is a skill published in the GitHub repository MilkyWay008/Hermes-OTG (15 stars, last pushed 28d ago), licensed MIT. It adds 42 tokens to every session and 1,825 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 2026-08-31.
Other skills, from other repositories
acquiring-disk-image-with-dd-and-dcfldd
Create forensically sound bit-for-bit disk images with dd or dcfldd on a Linux forensic workstation, preserving evidence integrity through hash verification (MD5/SHA) during acquisition. Use when imaging a suspect drive, USB device, or memory card for investigation, preserving volatile disk evidence during incident…
analyzing-linux-kernel-rootkits
Detect kernel-level rootkits in Linux memory dumps using Volatility3 linux plugins (checksyscall, lsmod, hiddenmodules), rkhunter system scanning, and /proc vs /sys discrepancy analysis to identify hooked syscalls, hidden kernel modules, and tampered system structures.
implementing-cloud-trail-log-analysis
Implementing AWS CloudTrail log analysis for security monitoring, threat detection, and forensic investigation using Athena, CloudWatch Logs Insights, and SIEM integration to identify unauthorized access, privilege escalation, and suspicious API activity.
performing-cloud-log-forensics-with-athena
Uses AWS Athena to query CloudTrail, VPC Flow Logs, S3 access logs, and ALB logs for forensic investigation. Covers CREATE TABLE DDL with partition projection, forensic SQL queries for detecting unauthorized access, data exfiltration, lateral movement, and privilege escalation. Use when investigating AWS security…
subdomain-enumeration
Map subdomains via crt.sh and subfinder at recon kickoff.
hunt-django
Hunt Django-specific vulnerabilities: DRF permission gaps, ORM injection, and admin exploitation.