Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/luckiday/vibe-hardwarenpx agentmods add skills/luckiday/vibe-hardware/vibe-uiflowWrote 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/luckiday/vibe-hardware/vibe-uiflow)<a href="https://agentmods.dev/skills/luckiday/vibe-hardware/vibe-uiflow"><img src="https://agentmods.dev/badge/skills/luckiday/vibe-hardware/vibe-uiflow/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/luckiday/vibe-hardware/vibe-uiflow"><img src="https://agentmods.dev/badge/skills/luckiday/vibe-hardware/vibe-uiflow.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 | $0.00445 | $0.03175 |
| Opus 5 | $0.00222 | $0.01588 |
| Sonnet 5 | $0.00089 | $0.00635 |
| Haiku 4.5 | $0.00044 | $0.00317 |
Grade A, and why
vibe-uiflow 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 8d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UIFlow2 → a device with a screen (agent-driven, seconds per iteration)
Companion to
vibe-firmware, not a replacement. That skill is C/ESP-IDF: layered components, pinned Docker builds, OTA. This one is the same philosophy at a different operating point — MicroPython on the M5 stack, where a change reaches the screen in seconds and you give up compile-time checking, tight memory control and OTA to get it. Pick this for a panel-and-buttons device, a bench instrument, a demo, a shape you are still finding. Pickvibe-firmwarewhen you need determinism, power discipline, or to ship a fleet.
Why this operating point exists
The expensive step in firmware is not compiling — it is finding out what the change did. Flash, unplug, look, guess: 30–60 seconds with a human in the loop, which means an agent cannot run it at all. UIFlow2 removes the compile, and the two loops below remove the human. What is left is an agent that can see what it drew.
The loop
host loop device loop
───────── ───────────
edit ─► render the app's OWN draw calls edit ─► mpy-cross every module
─► PNG per screen state ─► upload (flat, to /flash)
─► the AGENT LOOKS at the PNGs ─► run selftest.py ON THE BOARD
─► critique ─► edit ─► … ─► it PRINTS what a human would
otherwise read off the screen
sub-second, no hardware ~30 s, proves it on silicon
geometry · typography · RGB565 dispatch · timing · memory · peripherals
make shots # host loop: render every screen state, then LOOK at the PNGs
make check # device loop: compile + upload + selftest on hardware
make probe # what this firmware actually exposes — before you call it
make run # run live, tracebacks come back to the terminal
make deploy # install as main.py, start on power-up
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.
- 8d ago First seen · 201 lines · 445 tokens per session scan A 6a006eae0e43
vibe-uiflow is a skill published in the GitHub repository luckiday/vibe-hardware (5 stars, last pushed 16d ago), licensed MIT. It adds 445 tokens to every session and 3,175 once invoked, about $0.0022 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 2026-08-31.
Other skills, from other repositories
cardputer-buddy
Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add an app", "push to…
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
HA Integration Dev
Home Assistant custom integration development in Python. Covers customcomponents, DataUpdateCoordinator, configflow, OAuth2, conversation agent, HACS publishing, device registry, entity platforms, services, repair issues, diagnostics, Bluetooth integrations, and multi-coordinator patterns.
triton-ascend
A guide to writing Triton kernels for Ascend NPUs. Triton is a Python-based language for describing parallel operations that run in blocks across the device.
triton-ascend-case-index-put
An optimization pattern for indexed assignment, which writes values into positions chosen by index arrays. It loads index data into fast on-chip memory so a loop can reuse it.
xpu-port
Execute a single-target CUDA-to-XPU port of a PyTorch repo with libcst-based scan, mechanical rewrite, and CPU FP64 vs target-dtype correctness verify on one forward pass. Use when the request says "port" — "port my repo to XPU", "port my repo at to XPU", "rewrite the CUDA calls to XPU", "apply the mechanical…