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 chipi/agentic-ai-homelab --skill host-rungit clone --depth 1 https://github.com/chipi/agentic-ai-homelabWrote 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/chipi/agentic-ai-homelab/host-run)<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/host-run"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/host-run/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/chipi/agentic-ai-homelab/host-run"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/host-run.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 | $0.00104 | $0.00744 |
| Opus 5.5 | $0.00042 | $0.00298 |
| Sonnet 5.5 | $0.00021 | $0.00149 |
| Haiku 4.5 | $0.00010 | $0.00074 |
Grade A, and why
host-run 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 17d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
host-run
Inline commands over ssh break in ways that look like real failures:
- zsh on the laptop expands
=word(echo =====→zsh: ==== not found); - nested quotes corrupt JSON bodies silently (
Invalid JSON); - inline Python f-strings can't contain backslashes;
- non-interactive shells on the mini lack
/usr/local/bin, sodockerisn't found.
All of these hit this repo's sessions repeatedly (2026-10-16/17). A script file has none of them.
Run
# write the commands to a file in your scratchpad, then:
~/.claude/skills/host-run/scripts/run.sh <host> <file.sh|file.py> [args...]
| Host | Reaches |
|---|---|
homelab (or mini) |
the Mac mini, operator account (ssh -i ~/.ssh/homelab_mini -o IdentitiesOnly=yes markodragoljevic@homelab) |
homelab-claude |
the mini's claude account (ssh homelab-claude) |
dgx |
dgx-llm-1 |
prod |
deploy@prod-podcast |
.pyfiles run withpython3, anything else withbash./usr/local/binand/opt/homebrew/binare put onPATH, sodockerworks on the mini.- Arguments are passed literally (each one
%q-quoted). - The exit status is the remote script's: 2 means bad usage, 3 means the host is unreachable.
- The remote copy lives in
/tmp/host-run.XXXXXX(mode 700) and is removed on exit.
Rules
- Secrets never go in the file or the arguments. The script loads them on the host
(
set -a; . ~/…/.env; set +a), the way the handbook's recipes do. - Read-only by default. A script that writes (deletes, restarts, mints) needs the same approval as running those commands by hand.
- Keep the file in your scratchpad, not in a repo.
Verified
2026-10-17 on homelab and dgx:
- arguments
"arg one" '$HOME' '=x'arrived literally; - JSON with spaces round-tripped;
echo =====printed;- an f-string with a backslash ran;
dockerresolved;exit 7came back as 7, and an unknown host exited 2;- no
/tmp/host-run.*files were left on either host.
Not covered
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.
- 17d ago First seen · 61 lines · 104 tokens per session scan A cfccd17e682e
host-run is a skill published in the GitHub repository chipi/agentic-ai-homelab (3 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 744 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-18.
Other skills, from other repositories
flow-nexus-platform
Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges.
agent-resource-allocator
Agent skill for resource-allocator - invoke with $agent-resource-allocator.
cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.
linkerd-patterns
Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking with minimal overhead.
tcapi
A helper for managing Tencent Cloud resources through Tencent Cloud's command-line API tool. Tencent Cloud is a cloud-services provider offering products such as virtual servers, storage, networks, and containers.