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 Proxy2021/Enso --skill video_highlight_pipelinegit clone --depth 1 https://github.com/Proxy2021/EnsoWrote 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/proxy2021/enso/video_highlight_pipeline)<a href="https://agentmods.dev/skills/proxy2021/enso/video_highlight_pipeline"><img src="https://agentmods.dev/badge/skills/proxy2021/enso/video_highlight_pipeline/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/proxy2021/enso/video_highlight_pipeline"><img src="https://agentmods.dev/badge/skills/proxy2021/enso/video_highlight_pipeline.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 | $0.00027 | $0.00713 |
| Opus 5.5 | $0.00011 | $0.00285 |
| Sonnet 5.5 | $0.00005 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
video_highlight_pipeline 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 1mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Highlight Pipeline
Video highlight studio for scene detection, best-frame extraction, scoring, and highlight reel assembly from event/wedding videos
Available Tools
enso_video_highlight_pipeline_analyze_video (primary)
Analyze a video file: probe metadata and detect scene change boundaries. Use when: 'analyze this video', 'detect scenes', 'inspect video', 'what's in this video'.
Parameters:
path(string): Path to the video filethreshold(number): Scene detection sensitivity (0.0-1.0, lower = more sensitive, default: 0.3)
enso_video_highlight_pipeline_extract_frames
Extract the N best still frames from the video based on scene boundaries and a scoring strategy (sharpness, face-priority, or balanced).
Parameters:
path(string): Path to the video fileframeCount(number): Number of best frames to extract (default: 20)scoringStrategy(string): Scoring strategy: sharpness, face-priority, or balanced (default: balanced)outputDir(string): Output directory for extracted frames (default: auto)
enso_video_highlight_pipeline_preview_frames
Display extracted frames as a gallery with quality scores and timestamps for review. Allows approve/reject toggling before highlight reel generation.
Parameters:
path(string): Path to the video file (used to load stored frame data)outputDir(string): Directory containing extracted framessortBy(string): Sort frames by: score, timestamp, or rank (default: rank)
enso_video_highlight_pipeline_generate_highlight_reel
Assemble a highlight reel video from approved frames/clips with configurable duration, transition style, and audio handling.
Parameters:
path(string): Path to the source video fileduration(number): Target reel duration in seconds (default: 60)clipDuration(number): Duration of each clip segment in seconds (default: 4.5)transitionStyle(string): Transition style: dissolve, fadewhite, smoothleft, mixed (default: mixed)outputDir(string): Output directory for the highlight reel
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.
- 1mo ago First seen · 63 lines · 27 tokens per session scan A cefdb918482f
video_highlight_pipeline is a skill published in the GitHub repository Proxy2021/Enso (6 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 713 once invoked, about $0.0001 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
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
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…
manage-prs
Create, review, and merge GitHub pull requests and publish releases using repository Git rules. Use for requests to open a PR, push and create a PR, review PRs, merge a PR, or tag a release and write release notes.
flutter-feature-based-clean-architecture
Organize Flutter apps with modular feature-based clean architecture. Use when creating features under lib/features/ with domain, data, and presentation layers. Do not use for test-only, BlocBuilder, navigation, or spinner requests.
database-redis
Optimize Redis as cache and coordination infrastructure with TTL, eviction, and latency-aware key design. Use when implementing Redis caching, key invalidation, or Redis performance work.
init-project
Turn this boilerplate into a new app by renaming it, removing sample files, and linking it to EAS. Use when starting a new app from this template, or when asked to init, bootstrap, or rename the project.