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/termio-sh/termio/app-screenshot-debugnpx skills add termio-sh/termio --skill app-screenshot-debuggit clone --depth 1 https://github.com/termio-sh/termioWrote 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/termio-sh/termio/app-screenshot-debug)<a href="https://agentmods.dev/skills/termio-sh/termio/app-screenshot-debug"><img src="https://agentmods.dev/badge/skills/termio-sh/termio/app-screenshot-debug.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 | $0.00161 | $0.01227 |
| Opus 5 | $0.00081 | $0.00613 |
| Sonnet 5 | $0.00032 | $0.00245 |
| Haiku 4.5 | $0.00016 | $0.00123 |
Grade A, and why
app-screenshot-debug 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 4d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screenshot-driven UI debugging (AppleScript + screencapture)
The loop for seeing a termio UI change instead of guessing from code:
(rebuild if code changed) → drive app into the target state → capture the window → Read the PNG → judge / iterate
You cannot evaluate spacing, alignment, overlap, ghosting, or "this looks ugly" from source. Get a real screenshot, Read it, then decide.
Prerequisites
- The app must be running and built. If you just changed code, run the
macos-rebuild-devskill first. The process name for System Events istermioand the main window's title istermio. - These calls need macOS Accessibility + Screen Recording permission for
the terminal / Claude Code host. If
System Eventserrors with-25211or the capture is black, that permission is missing — tell the user to grant it in System Settings → Privacy & Security. - termio is a single-window app (sidebar + terminal panes); there is no Settings
window. Everything you need is in
window 1.
The two helper scripts (in scripts/)
Run them with bash; they take the app name from $TERMIO_APP_NAME (default
termio).
-
capture-window.sh [out.png]— screenshot just the frontmost termio window (-ono shadow,-xsilent), reading its live bounds first. Prints the window origin + size. Captures the region 1:1 in points, so a point you read off the resulting image is window-relative: image (dx,dy) == screen (originX+dx, originY+dy). -
click-in-window.sh <dx> <dy>— click at a window-relative point: it re-reads the live window origin and adds your offset. Use the exact (dx,dy) you measured on acapture-window.shimage — this survives the window moving or reopening on a different display.
Canonical recipe
SK=skills/app-screenshot-debug/scripts
osascript -e 'tell application "System Events" to tell process "termio" to set frontmost to true'
bash $SK/capture-window.sh /tmp/shot.png
# → Read /tmp/shot.png with the Read tool, find the control you want at (dx,dy)
bash $SK/click-in-window.sh 120 180 # e.g. click a sidebar project row
bash $SK/capture-window.sh /tmp/shot2.png # Read again to see the result
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.
- 4d ago First seen · 88 lines · 161 tokens per session scan A 2d4b3415e2a6
app-screenshot-debug is a skill published in the GitHub repository termio-sh/termio (395 stars, last pushed today), licensed MIT. It adds 161 tokens to every session and 1,227 once invoked, about $0.0008 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
workflows
Execute a workflow script that orchestrates multiple subagents deterministically. Use when the user explicitly requests a workflow, multi-agent orchestration, parallel or sequential agent pipelines, structured agent outputs, or a durable background workflow run.
frame-macos-notification
拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
deck-pitch
10 页融资 deck, 白底 + 蓝紫渐变 hero, traction 柱状, $X.XM ask.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.