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 cyuanxv/agent-cockpit --skill gemini-video-analyzergit clone --depth 1 https://github.com/cyuanxv/agent-cockpitWrote 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/cyuanxv/agent-cockpit/gemini-video-analyzer)<a href="https://agentmods.dev/skills/cyuanxv/agent-cockpit/gemini-video-analyzer"><img src="https://agentmods.dev/badge/skills/cyuanxv/agent-cockpit/gemini-video-analyzer/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/cyuanxv/agent-cockpit/gemini-video-analyzer"><img src="https://agentmods.dev/badge/skills/cyuanxv/agent-cockpit/gemini-video-analyzer.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 | $0.00105 | $0.00990 |
| Opus 5.5 | $0.00042 | $0.00396 |
| Sonnet 5.5 | $0.00021 | $0.00198 |
| Haiku 4.5 | $0.00011 | $0.00099 |
Grade A, and why
gemini-video-analyzer 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 2mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Video Analyzer
Analyze local video files with Gemini API while keeping Codex as the local harness. The main contract is: fixed JSON first, Markdown report second, and timestamp evidence that a human can replay.
Inputs
Ask for a local video path if the user did not provide one. Accept only .mp4, .mov, .m4v, and .webm.
Default analysis goal:
- Chinese output.
- One-sentence conclusion.
- Content summary.
- Timeline with reviewable timestamps.
- Key visuals, audio, subtitles, narration, UI flow, and actions.
- Key moments, editing suggestions, follow-up suggestions, and uncertainties.
Procedure
-
Verify that the video file exists.
-
Tell the user that the video will be uploaded to Gemini API for analysis.
-
Run a cost estimate before analysis when the user has not already approved the run:
python3 skills/gemini-video-analyzer/scripts/gemini_video_analyze.py estimate "<video_path>" -
Analyze with the recommended model and explicit confirmation:
python3 skills/gemini-video-analyzer/scripts/gemini_video_analyze.py analyze "<video_path>" --goal "<analysis_goal>"For non-interactive approved runs, pass
--yes. -
If the user names a model, pass it explicitly:
python3 skills/gemini-video-analyzer/scripts/gemini_video_analyze.py analyze "<video_path>" --model gemini-3.5-flash --goal "<analysis_goal>" --yes -
Transfer mode defaults to
auto: videos up to 20 MB use inline Gemini content parts; larger videos use Gemini Files API. Override only when needed:python3 skills/gemini-video-analyzer/scripts/gemini_video_analyze.py analyze "<video_path>" --transport inline --yes python3 skills/gemini-video-analyzer/scripts/gemini_video_analyze.py analyze "<video_path>" --transport files --yes -
Read the printed run directory. Validate it if needed:
python3 skills/gemini-video-analyzer/scripts/gemini_video_analyze.py validate "<run_dir>"
What ships with it
16 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.
- agents/openai.yaml 239 B
- references/model-routing.en.md 849 B
- references/model-routing.md 1.9 KB
- references/model-routing.zh.md 782 B
- references/output-schema.en.md 849 B
- references/output-schema.md 1.0 KB
- references/output-schema.zh.md 782 B
- references/prompt-templates.en.md 864 B
- references/prompt-templates.md 752 B
- references/prompt-templates.zh.md 797 B
- references/validation.en.md 834 B
- references/validation.md 1.4 KB
- references/validation.zh.md 767 B
- scripts/gemini_video_analyze.py 43 KB runs code
- SKILL.en.md 776 B
- SKILL.zh.md 709 B
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.
- 2mo ago First seen · 98 lines · 105 tokens per session scan A ba5c86ec6474
gemini-video-analyzer is a skill published in the GitHub repository cyuanxv/agent-cockpit (2 stars, last pushed 25d ago), licensed MIT. It adds 105 tokens to every session and 990 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
skillgrade-graders
Authors deterministic, LLM rubric, and human graders for skillgrade evaluations. Use when creating scoring scripts, writing evaluation rubrics, setting up human review workflows, or combining multiple graders with weighted scoring. Don't use for setting up eval pipelines, configuring eval.yaml defaults, or general…
angular-modern-apis
Guidelines for using modern Angular APIs (signals, inject, control flow).
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.
skillgrade-setup
Sets up and runs skillgrade evaluation pipelines for AI agents and Agent Skills. Use when initializing eval configurations, running trials, reviewing results, exporting reports, or integrating with CI. Don't use for writing grader scripts, general test authoring, or non-agentic documentation.
self-improvement
บันทึกการเรียนรู้ ข้อผิดพลาด และการแก้ไขเพื่อการปรับปรุงอย่างต่อเนื่อง ใช้เมื่อ: (1) คำสั่งหรือการทำงานล้มเหลว (2) ผู้ใช้แก้ไขข้อมูล (3) ผู้ใช้ร้องขอความสามารถที่ไม่มี (4) API หรือเครื่องมือภายนอกล้มเหลว (5) พบแนวทางที่ดีกว่าสำหรับงานที่ทำซ้ำ หรือต้องการทบทวนการเรียนรู้ก่อนเริ่มงานสำคัญ.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.