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/elumenotion/guideants/host-sshnpx skills add Elumenotion/GuideAnts --skill host-sshgit clone --depth 1 https://github.com/Elumenotion/GuideAntsWrote 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/elumenotion/guideants/host-ssh)<a href="https://agentmods.dev/skills/elumenotion/guideants/host-ssh"><img src="https://agentmods.dev/badge/skills/elumenotion/guideants/host-ssh.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 5.1 | $0.00061 | $0.02483 |
| Opus 5 | $0.00030 | $0.01241 |
| Sonnet 5 | $0.00012 | $0.00497 |
| Haiku 4.5 | $0.00006 | $0.00248 |
Grade A, and why
host-ssh 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 2d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Host SSH (Windows PowerShell)
Sandbox paths — authoritative, do not discover
Your system context includes a file list ([@files] / context options). That list,
plus the rules below, fully defines what exists and where. Do not run pwd, find,
ls /, cd /home, or any other command to discover paths. Exploration wastes turns
and breaks working-directory assumptions.
SANDBOX CWD is already the notebook output directory (private notebooks: the
Output/ folder). Every run_bash / run_python call starts there.
| Rule | Do | Never |
|---|---|---|
| Skill scripts | python3 Skills/host-ssh/scripts/host_ssh.py … |
Output/Skills/…, /app/…, /home/… |
| Deliverables | bare filenames in CWD | prefix Output/ in commands |
| Change directory | stay in CWD | cd /home, cd Output, cd before skill commands |
| Inputs in the file list | use the exact path shown (../repo/…, Skills/…, bare names) |
guess, probe, or re-derive |
| Host repo edits | edit via mounted paths in the file list (bash heredoc) | run_python one-liners that embed \ or \\ |
If Skills/host-ssh/scripts/host_ssh.py appears in the file list, run it as written
from CWD. If a path is in the list, the file exists — trust the list.
Host setup (OpenSSH, guide Environment variables) is in the operator README bundled with
this skill or samples/skills/host-ssh skills/README.md on the repo. Missing
GA_HOST_SSH_* env vars → stop and tell the user to set them in the guide editor; do
not scan or guess credentials.
Machines — the guide Environment is the source of truth
GA_SSH_MACHINES (JSON array in the guide Environment) declares which machines this
guide can reach. Run host_ssh.py machines to list them — never guess a host or IP.
When no --machine is given, the record with "default": true is the target. When
GA_SSH_MACHINES is absent, the legacy single machine from GA_HOST_SSH_HOST is the
default (named host).
[
{"name": "office", "host": "host.docker.internal", "default": true,
"share": {"unc": "\\\\FILESERVER\\content", "user": "DOMAIN\\GuideAnts", "drive": "R"}},
{"name": "gpu", "host": "192.168.1.50"}
]
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.
- 2d ago First seen · 218 lines · 61 tokens per session scan A b0b0fbcd31f5
host-ssh is a skill published in the GitHub repository Elumenotion/GuideAnts (56 stars, last pushed 2d ago), licensed Apache-2.0. It adds 61 tokens to every session and 2,483 once invoked, about $0.0003 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
omh-morning-brief
This is a Hermes-native morning-brief workflow skill.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
codex-task-inspector
Inspect Codex async task progress from the correct data directory. Use when the user asks to check Codex status, inspect async task progress, summarize task state, or determine whether local Codex workers are still running. Always detect the active Codex data dir first: prefer CODEXHOME when set, otherwise fall back…
dev-bounce
코드를 고치거나 새로 짜는 작업을 단계별 워크플로우로 진행한다. 버그 수정, 기능 구현, 리팩터링, 설정·의존성 변경, "이거 고쳐줘" / "이 기능 추가해줘" / "왜 안 되는지 보고 고쳐봐" 같은 요청에 파일을 건드리기 전 반드시 먼저 호출할 것. 계획 승인·검증 통과·커밋을 엔진이 강제하는데, 이 스킬로 작업을 시작해야만 그 강제가 걸린다 — 스킬 없이 바로 Edit/Write하면 아무 규칙도 적용되지 않은 채 진행된다. 질문·설명·코드 읽기만 하는 요청에는 쓰지 않는다.
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.