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/connorads/remobi/remobi-setupnpx skills add connorads/remobi --skill remobi-setupgit clone --depth 1 https://github.com/connorads/remobiWhat 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 | $0.00127 | $0.08705 |
| Opus 5 | $0.00063 | $0.04352 |
| Sonnet 5 | $0.00025 | $0.01741 |
| Haiku 4.5 | $0.00013 | $0.00870 |
Grade A, and why
remobi-setup 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 — 734 lines — stays where its author put it; the contents beside it link to each section on GitHub.
remobi-setup
Interactive onboarding skill for remobi — monitor and control tmux (or zellij, herdr) from your phone.
This skill walks the user through setup in one conversation. The guiding principle: detect everything possible, default everything sensible, ask only what requires human intent. Most users answer 1-3 questions total.
Workflow
Phase 1: Welcome and understand (1 question)
Open with a one-liner confirming what they're getting, then ask what brings them here:
"remobi puts your tmux session on your phone — same panes, same windows, touch controls on top. Everything we set up here you can change later."
"What brings you to remobi? For example: monitoring coding agents from your phone, getting phone access to your dev sessions, or just curious to try it out."
Map the answer to a persona internally (don't tell the user their "persona"):
| Persona | Signals | Downstream effect |
|---|---|---|
| Agent Watcher | Mentions coding agents, Claude Code, Codex, AI, monitoring | Auto-zoom on, floating zoom button, double-tap zoom enabled, lean config, minimal questions |
| Remote Dev | Mentions tmux, SSH, dev workflow, existing setup | Inspect config thoroughly, offer popup drawer buttons, ask about auto-zoom |
| Newcomer | Says curious, trying it out, heard about it, no specific use case | Offer tmux setup, explain concepts, auto-zoom on, sensible defaults |
If the answer is ambiguous, lean towards Agent Watcher — it's the most common path and the defaults work well for everyone.
Phase 2: Environment and tmux setup
Check prerequisites
Run silently, then report what's present vs missing:
node --version # need >= 22
tmux -V # default target multiplexer
which zellij # alternative multiplexer (see zellij path below)
which herdr # alternative multiplexer (see herdr path below)
which remobi # npm install -g remobi
What ships with it
7 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 · 734 lines · 127 tokens per session scan A ad0a4b72e5cc
remobi-setup is a skill published in the GitHub repository connorads/remobi (55 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 8,705 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
build-and-verify
Build, test, and end-to-end verify the Multiplex visionOS/iPadOS SSH-tmux terminal app. Use this whenever you need to compile the app, run its unit tests, regenerate the Xcode project after editing project.yml or adding/ removing source files, or confirm a change works in the real app on the visionOS or iPad…
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
animation-vocabulary
Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and…
review-animations
Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.
improve-animations
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the…
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…