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/garavitgabriel/claude-remote-kit/remote-setupnpx skills add garavitgabriel/claude-remote-kit --skill remote-setupgit clone --depth 1 https://github.com/garavitgabriel/claude-remote-kitWrote 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/garavitgabriel/claude-remote-kit/remote-setup)<a href="https://agentmods.dev/skills/garavitgabriel/claude-remote-kit/remote-setup"><img src="https://agentmods.dev/badge/skills/garavitgabriel/claude-remote-kit/remote-setup.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 | $0.00148 | $0.03098 |
| Opus 5 | $0.00074 | $0.01549 |
| Sonnet 5 | $0.00030 | $0.00620 |
| Haiku 4.5 | $0.00015 | $0.00310 |
Grade C, and why
remote-setup scanned grade C with 3 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 5d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
nothing. Never tell the user something works that you haven't checked. Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Missing tmux or jq → offer to install (`brew install tmux jq` / `sudo apt Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
executable; `grep statusline ~/.claude/settings.json`. Remind them their How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
remote-setup — guided install of claude-remote-kit
You are guiding a real person through turning this machine into an always-on Claude Code workspace they can reach from their phone or laptop. Be interactive: ask before acting when a step touches their existing config, adapts to hardware you can't see (their phone), or needs an account (Tailscale). One question at a time. Never dump the whole plan and ask "ok?".
Modes (pick from the user's words):
- no args / "set up" → Setup (full flow below)
doctor/ any breakage complaint → Doctor (jump to §Doctor)phone→ §Step 5 onlyusage→ print §Usage guide only
Throughout: resolve the kit repo root — call it $KIT — in this order:
- If this skill file sits inside the cloned repo,
$KITis../../..from it (the folder containinginstall.sh). - If running from the global copy (
~/.claude/skills/remote-setup), read~/.config/claude-remote-kit/kit-path(written byinstall.sh). - Neither → ask where they cloned the repo, or offer to
git clone https://github.com/garavitgabriel/claude-remote-kit.git.
Rules (all modes)
- Back up before overwrite, always.
install.shalready does; if you edit anything by hand (e.g.settings.json), copy it to*.bak-<timestamp>first. - Verify postconditions in the vocabulary of the task, not exit codes.
"Installed tmux" is proven by
tmux -V; "SSH works" is proven by an actual connection or an answering port; a success message from an installer proves nothing. Never tell the user something works that you haven't checked. - Never touch SSH private keys. You may read/write
~/.ssh/config(aliases only) and suggestssh-copy-id; you never generate, move, or read key material without the user explicitly asking. - Things you cannot do — sign in to Tailscale (GUI/browser auth), install apps on their phone, toggle macOS System Settings. For those, give the exact steps, then wait for the user to say done, then verify from your side.
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.
- 5d ago First seen · 235 lines · 148 tokens per session scan C 144e9c9b9f25
remote-setup is a skill published in the GitHub repository garavitgabriel/claude-remote-kit (10 stars, last pushed 1mo ago), licensed MIT. It adds 148 tokens to every session and 3,098 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 3 findings (subtle steering, asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ccal
Chinese Calendar with Lunar-Solar Conversion.
x-theme
Change terminal command line prompt theme. Globally manage the display style of all x-cmd interactive components. Supports multiple theme vendors: theme, starship, ohmyposh. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
loop
Schedule recurring tasks with notifications. Triggered by "/loop " to set up periodic monitoring.
skill0
Root index of x-cmd skill0 sub-skills. Defines the OKR-style agent workflow (goal → rule-verified results → execute), skill discovery, and agent tooling preferences. Style: principle-first, concise, delegate specifics to authoritative external sources.
atmos-custom-commands
Custom CLI commands: command definition in atmos.yaml, arguments, flags, shared native step types, when: conditions, output/UI steps, env vars, custom component types.
x-starship
Starship.rs cross-shell prompt with theme management. Minimal, blazing-fast, and infinitely customizable prompt. Auto-downloads starship binary if not available. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.