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 cat-xierluo/legal-skills --skill video-screenshotgit clone --depth 1 https://github.com/cat-xierluo/legal-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/cat-xierluo/legal-skills/video-screenshot)<a href="https://agentmods.dev/skills/cat-xierluo/legal-skills/video-screenshot"><img src="https://agentmods.dev/badge/skills/cat-xierluo/legal-skills/video-screenshot/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/cat-xierluo/legal-skills/video-screenshot"><img src="https://agentmods.dev/badge/skills/cat-xierluo/legal-skills/video-screenshot.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 | $0.00291 | $0.05726 |
| Opus 5.5 | $0.00116 | $0.02290 |
| Sonnet 5.5 | $0.00058 | $0.01145 |
| Haiku 4.5 | $0.00029 | $0.00573 |
Grade B, and why
video-screenshot scanned grade B with 1 finding 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 22d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| ffmpeg ≥ 5.0 | macOS: `brew install ffmpeg`<br>Linux: `sudo apt-get install ffmpeg` | The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
45 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.
- assets/stability/benchmark-overclaim.json 674 B
- assets/stability/benchmark-valid.json 656 B
- assets/stability/coverage-frame-does-not-survive.json 651 B
- assets/stability/evidence-leads-modify-base.json 659 B
- assets/stability/pipeline-valid.json 660 B
- assets/stability/scroll-approximate-cache-historical.json 1.5 KB
- assets/stability/scroll-collapses-true-repetition.json 1.5 KB
- assets/stability/scroll-error-success.json 1.5 KB
- assets/stability/scroll-exceeds-budget.json 1.5 KB
- assets/stability/scroll-valid.json 1.5 KB
- assets/stability/short-motion-group-lost.json 649 B
- assets/stability/transaction-cleanup-before-probe-historical.json 666 B
- assets/stability/transaction-modifies-old-on-failure.json 659 B
- assets/stability/vision-restores-frame.json 684 B
- CHANGELOG.md 27 KB
- config/.env.example 177 B
- config/evidence-lead-taxonomy.json 3.0 KB
- config/instruction-stability-contract.json 15 KB
- config/rapidocr-requirements.txt 155 B
- LICENSE.txt 1.1 KB
- references/benchmarking.md 6.5 KB
- references/evidence-leads.md 4.6 KB
- references/scroll-text.md 20 KB
- references/setup.md 4.8 KB
- references/strategy-and-params.md 19 KB
- references/vision-audit.md 6.7 KB
- scripts/apply_evidence_review.py 10 KB runs code
- scripts/apply_vision_review.py 24 KB runs code
- scripts/benchmark.py 38 KB runs code
- scripts/check_benchmark_summary.py 3.3 KB runs code
- scripts/check_pipeline.py 71 KB runs code
- scripts/check_scroll_artifact.py 3.1 KB runs code
- scripts/check_scroll_env.py 8.0 KB runs code
- scripts/check_scroll_text.py 44 KB runs code
- scripts/check_stability_artifact.py 6.0 KB runs code
- scripts/extract.py 66 KB runs code
- scripts/lib.py 71 KB runs code
- scripts/ocr_runtime.py 2.2 KB runs code
- scripts/prepare_evidence_leads.py 24 KB runs code
- scripts/prepare_ocr.py 5.7 KB runs code
- scripts/prepare_vision_audit.py 32 KB runs code
- scripts/run_scroll.py 920 B runs code
- scripts/scroll_ocr.py 9.4 KB runs code
- scripts/scroll_text.py 45 KB runs code
- scripts/scroll_vision.swift 1.6 KB
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.
- 22d ago Changed 9e62c59bd4b5
- 23d ago Changed · +44 lines · +60 tokens per session f455a294c0fe
- 24d ago Changed · +16 lines · +15 tokens per session b8bc7593fa7d
- 2mo ago First seen · 192 lines · 216 tokens per session scan B ae97da220a83
video-screenshot is a skill published in the GitHub repository cat-xierluo/legal-skills (778 stars, last pushed yesterday), with no licence file. It adds 291 tokens to every session and 5,726 once invoked, about $0.0012 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
video-screenshot compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| video-screenshotcat-xierluo/legal-skills | Skill | 778 | yesterday | none | B | 291 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |