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 mthines/agent-skills --skill screen-recordergit clone --depth 1 https://github.com/mthines/agent-skillsWrote 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/mthines/agent-skills/screen-recorder)<a href="https://agentmods.dev/skills/mthines/agent-skills/screen-recorder"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/screen-recorder/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/mthines/agent-skills/screen-recorder"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/screen-recorder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 107 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 270 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 287 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00210 | $0.03602 |
| Opus 5 | $0.00105 | $0.01801 |
| Sonnet 5 | $0.00042 | $0.00720 |
| Haiku 4.5 | $0.00021 | $0.00360 |
Grade A, and why
screen-recorder 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screen Recorder
Produces a short .webm clip of a specific page section so an agent —
or a reviewer reading a PR — can see motion that a static screenshot
hides.
Not a test suite, not a permanent fixture: every recording is a
throwaway artifact written to .agent/recordings/ for one-shot visual
review.
This
SKILL.mdis a thin index. Detailed rules live inrules/*.mdand load on demand. Literal Playwright andffmpegboilerplate the skill emits lives intemplates/*.md. Do not preload everything — load only what the current phase asks for.
When to use
Reach for this skill when any of the following is true:
- A diff changes animation, transition, or interactive motion code
(
@keyframes,transition,View Transitions, Motionlayout,@starting-style, scroll-driven timelines). - A still screenshot would not falsify the bug or feature claim — the proof requires at least two frames.
- A reviewer asks "what does this look like?" on a PR whose answer is a moving image, not a description.
- The
animationsskill has produced an animation and wants visual evidence it hits 60 fps and respectsprefers-reduced-motion. - The
uxskill flagged a flow (drag, focus ring, hover reveal, expanding nav, modal entrance) where the asserted UX claim is about timing, not layout.
Do not reach for this skill when:
- A static screenshot is sufficient — capture a still directly (the
pr-revieweragent's visual pass reads stills locally; it never attaches them to the PR). - The task is to author a durable Playwright test — use the
e2e-testingskill. - The input is an existing
trace.zip— useplaywright-trace-analyzer. - The input is an existing screen recording (e.g., a user bug report) —
use
video-analyser.
Phase 0 — Preflight (mandatory gate)
Before recording anything, verify the environment. Halt and ask the user before installing tools.
Run these checks (read-only):
What ships with it
9 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 · 313 lines · 210 tokens per session scan A 74e605a5b400
screen-recorder is a skill published in the GitHub repository mthines/agent-skills (13 stars, last pushed yesterday), licensed MIT. It adds 210 tokens to every session and 3,602 once invoked, about $0.0011 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
ego-browser
Skill "ego-browser" from citrolabs/ego-lite, covering ego-browser, quick start, common helpers, task spaces and control handoff.
motion-canvas-agent
Agent tooling for Motion Canvas — seek, screenshot, scene graph inspection, settings control, and rendering via HTTP API. Requires a browser with the editor open.
laohan-luping
A screen-recording workflow that turns a spoken script or recording brief into an ffmpeg recording script and an MP4 video. It can coordinate visible terminal commands, browser actions, and timed pauses.
custom-icons
Create or refine custom icon assets as native or traced SVGs and transparent PNG/WebP files. Use when the user asks for a bespoke icon or cohesive icon set, wants an image traced into a clean vector, or needs a detailed or 3D icon with transparency.
creating-explainers
Use when creating an interactive explainer - a single self-contained HTML page with hand-built Canvas figures. Handles source-file explainers, topic-driven research explainers, and mixed intake where files provide the spine and research adds support. Trigger phrases include "make an explainer", "turn this paper into…
content-engine-autopilot
Browser Orchestration — Playwright-driven generation at scale. Claude Code runs your entire content pipeline in the browser. Saves authentication sessions per tool, executes batch generation using compiled identity, and organizes output automatically. Supports Higgsfield, Weavy, Artlist, and extensible to any…