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 minghinmatthewlam/agent-guards --skill record-screengit clone --depth 1 https://github.com/minghinmatthewlam/agent-guardsWrote 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/minghinmatthewlam/agent-guards/record-screen)<a href="https://agentmods.dev/skills/minghinmatthewlam/agent-guards/record-screen"><img src="https://agentmods.dev/badge/skills/minghinmatthewlam/agent-guards/record-screen/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/minghinmatthewlam/agent-guards/record-screen"><img src="https://agentmods.dev/badge/skills/minghinmatthewlam/agent-guards/record-screen.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 | $0.00056 | $0.01451 |
| Opus 5.5 | $0.00022 | $0.00580 |
| Sonnet 5 | $0.00011 | $0.00290 |
| Haiku 4.5 | $0.00006 | $0.00145 |
Grade A, and why
record-screen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record screen
Video is the reviewer's main evidence for UI work. Record around the part of the run that shows the change, then attach the MP4.
- Linux cloud session: record the whole virtual X display with sections 1–3. Nothing else runs on it, so the whole display is safe to capture.
- macOS: the screen is the user's real desktop, with personal windows and notifications. Never record the full display. Use the macOS section, then continue at section 4.
Linux: 1. Start (just before the app launches)
Run as one command. It reuses a running display, else starts Xvfb on :99; installs ffmpeg if missing (about 30s with apt); records at 15 fps in the background.
REC=/tmp/record-screen; mkdir -p "$REC"; SUDO=$([ "$(id -u)" = 0 ] || echo sudo)
export DISPLAY=${DISPLAY:-:99}; d=${DISPLAY#*:}; d=${d%%.*}
if [ ! -S "/tmp/.X11-unix/X$d" ]; then
command -v Xvfb >/dev/null || { $SUDO apt-get update -q || true; $SUDO apt-get install -y -q --no-install-recommends xvfb; }
setsid nohup Xvfb "$DISPLAY" -screen 0 1920x1080x24 -nolisten tcp >"$REC/xvfb.log" 2>&1 &
timeout 10 sh -c "until [ -S /tmp/.X11-unix/X$d ]; do sleep 0.2; done"
fi
command -v ffmpeg >/dev/null || { $SUDO apt-get update -q || true; $SUDO apt-get install -y -q --no-install-recommends ffmpeg; }
rm -f "$REC/raw.mkv"
setsid nohup ffmpeg -loglevel error -f x11grab -framerate 15 -draw_mouse 0 -i "$DISPLAY" \
-c:v libx264 -preset ultrafast -crf 18 "$REC/raw.mkv" >"$REC/ffmpeg.log" 2>&1 &
echo $! >"$REC/ffmpeg.pid"; echo "recording $DISPLAY (pid $(cat "$REC/ffmpeg.pid"))"
The app under test must use the same DISPLAY. If you started Xvfb here, prefix later commands with DISPLAY=:99, since shell exports do not carry across tool calls.
Linux: 2. Demonstrate
Drive the app so the change is visible: open the affected screens, pause about 2 seconds on each (waitForTimeout in Playwright is fine for pacing), and show the before and after state where it applies. Nothing but the app appears on a virtual display, and Playwright clicks do not move a pointer, so screens change without a visible cursor.
What ships with it
1 file 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 · 72 lines · 56 tokens per session scan A 72439d5ff319
record-screen is a skill published in the GitHub repository minghinmatthewlam/agent-guards (45 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 1,451 once invoked, about $0.0002 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 2026-09-25.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.