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 media_gallerygit 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/media_gallery)<a href="https://agentmods.dev/skills/proxy2021/enso/media_gallery"><img src="https://agentmods.dev/badge/skills/proxy2021/enso/media_gallery/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/media_gallery"><img src="https://agentmods.dev/badge/skills/proxy2021/enso/media_gallery.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 | $0.00019 | $0.00508 |
| Opus 5.5 | $0.00008 | $0.00203 |
| Sonnet 5.5 | $0.00004 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
media_gallery 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.
What it actually says
Media Gallery
Comprehensive media gallery for browsing, viewing, organizing, and searching photos and videos
Available Tools
enso_media_gallery_browse (primary)
Browse a folder for photos and videos with sorting, filtering, and subfolder navigation
Parameters:
path(string): Directory path to browse (defaults to ~/Pictures)filter(string): Media type filter: all, image, or video (default: all)sortBy(string): Sort field: name, date, or size (default: name)sortDir(string): Sort direction: asc or desc (default: asc)
enso_media_gallery_view
View a single photo or video with full EXIF metadata, AI description, and rating
Parameters:
path(string): Full path to the photo or video file
enso_media_gallery_favorite
Toggle the favorite status of a photo
Parameters:
path(string): Path to the photo filefavorite(boolean): Set true or false, or omit to toggle
enso_media_gallery_rate
Set a 1-5 star rating on a photo (0 to clear the rating)
Parameters:
path(string): Path to the photo filerating(number): Star rating from 0 to 5 (0 clears the rating)
enso_media_gallery_collection
Manage photo collections: create, view, add/remove photos, rename, delete, or list all collections
Parameters:
action(string): Action: create, add, remove, list, view, rename, or deletecollectionName(string): Name of the collectionphotoPath(string): Photo path for add/remove operationsnewName(string): New name for rename operation
enso_media_gallery_search
Search photos by natural language query against AI descriptions and tags
Parameters:
path(string): Directory to search withinquery(string): Natural language search querylimit(number): Maximum number of results (default: 30)
enso_media_gallery_inspect
Inspect detailed file metadata including EXIF data for a media file
Parameters:
path(string): Path to the file to inspect
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 · 70 lines · 19 tokens per session scan A 242b702c7655
media_gallery is a skill published in the GitHub repository Proxy2021/Enso (6 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 508 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.
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.
research
Use when the user asks you to research, compare, fact-check or find current information, and the answer should come with sources.