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 computer-rescue-workflowgit 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/computer-rescue-workflow)<a href="https://agentmods.dev/skills/milkyway008/hermes-otg/computer-rescue-workflow"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/computer-rescue-workflow/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/computer-rescue-workflow"><img src="https://agentmods.dev/badge/skills/milkyway008/hermes-otg/computer-rescue-workflow.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 | $0.01317 |
| Opus 5 | $0.00009 | $0.00659 |
| Sonnet 5 | $0.00003 | $0.00263 |
| Haiku 4.5 | $0.00002 | $0.00132 |
Grade A, and why
computer-rescue-workflow 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 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.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computer Rescue Workflow — Discipline Rules
Trigger: ANY hands-on repair / rescue / troubleshooting session on the user's machine — VM recovery, disk repair, config patching, path fixing, MCP server repair, log analysis that may lead to changes.
These rules were learned the hard way in a VMware VM rescue + OTG build session. The user (Ringo) was burned by hasty, unapproved, unreported edits. Follow them EVERY time.
The 5 Commandments
-
Diagnose first, report, THEN fix. A request to "check the logs for errors" is NOT a request to fix them. Report findings and wait for an explicit "go ahead" / "fix it" before running any repair command. Jumping to patching without approval erodes trust fast and can make things worse (this user will call it out).
-
Backup BEFORE any change — never after. A backup created after the edits is worthless for rollback. Confirm the user's backup exists up front; make your own
.bak-YYYYMMDD-HHMMcopy before touching anything you edit. A.bakmade after the fact is NOT a backup — the user knows this and will ask. -
Keep a running ledger of every file you modify. Path + what changed + why. When a session involves many edits, the user WILL ask "what did you change in the past 30 minutes?" — you must answer precisely, without reconstructing it from memory. A visible todo list updated per-edit satisfies this.
-
Stop changing things that already work. If the user says a fix was tested and working earlier, VERIFY the timeline before "improving" it. Unapproved rework of a working state is how you break it. Check log timestamps before concluding a past fix failed.
-
Async delegation by default; sync only on request. Spawn subagents for heavy work so the user is never blocked. Wait for their result, then report. (Exception: user says "wait for it".)
Typical sequence for a rescue
- Ask/confirm backup exists. Record the backup path.
- Read the relevant log(s) FIRST (
vmware.log,errors.log,mcp-stderr.log). Quote the exact error lines back to the user. - Report diagnosis + proposed fix. STOP. Wait for approval.
- On approval: backup every file you'll touch, then make surgical changes.
- Verify the fix end-to-end (boot the VM, restart Hermes, run the tool).
- Update the file-change ledger and report the full timeline of what changed.
What ships with it
1 file 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 · 104 lines · 17 tokens per session scan A 252ccec91e4b
computer-rescue-workflow 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 1,317 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 2026-09-03.
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.
python-debugpy
Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote or headless attach.
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…