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 agentmods add skills/proxy2021/enso/media_processingnpx skills add Proxy2021/Enso --skill media_processinggit clone --depth 1 https://github.com/Proxy2021/EnsoWhat 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 | $0.00028 | $0.00731 |
| Opus 5 | $0.00014 | $0.00365 |
| Sonnet 5 | $0.00006 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
media_processing 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 yesterday.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media Processing
Media processing tools: video intelligence (inspect, scene detection, frame extraction), contact sheets, AI upscaling, background removal
Available Tools
enso_media_processing_inspect (primary)
Inspect a video file: get duration, resolution, codec, fps, bitrate, audio info. Use when user says: 'inspect this video', 'video details', 'what format is this video'.
Parameters:
path(string): Path to the video file
enso_media_processing_frames
Extract frames from a video at intervals, keyframes, or a specific count. Use when user says: 'extract frames', 'grab stills from video', 'get screenshots from video'.
Parameters:
path(string): Path to the video filemode(string): Extraction mode: interval (every N seconds), keyframes (I-frames only), or count (N evenly-spaced frames). Default: countvalue(number): Seconds for interval mode, or frame count for count mode. Default: 10
enso_media_processing_scenes
Detect scene changes/boundaries in a video using frame difference analysis. Use when user says: 'detect scenes', 'find scene changes', 'scene boundaries'.
Parameters:
path(string): Path to the video filethreshold(number): Scene change sensitivity (0.0-1.0, lower = more sensitive). Default: 0.3
enso_media_processing_thumbnail
Generate a thumbnail image from a video at a specific timestamp. Use when user says: 'video thumbnail', 'generate preview image', 'screenshot at timestamp'.
Parameters:
path(string): Path to the video filetime(number): Timestamp in seconds to capture. Default: 1size(string): Output size (e.g., '640x480', '1280x720'). Default: 320x240
enso_media_processing_sheet
Generate a contact sheet (thumbnail grid) from a folder of photos with filename and EXIF metadata overlay. Use when user says: 'contact sheet', 'thumbnail grid', 'proof sheet', 'photo grid'.
Parameters:
path(string): Path to folder containing photoscolumns(number): Number of columns in grid. Default: 5showExif(boolean): Show EXIF metadata overlay. Default: truethumbSize(number): Size of each thumbnail in pixels. Default: 300
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.
- yesterday First seen · 70 lines · 28 tokens per session scan A 0e9ebe073d73
media_processing is a skill published in the GitHub repository Proxy2021/Enso (5 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 731 once invoked, about $0.0001 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
oauth-expert
OAuth 2.0 and OpenID Connect expert for authorization flows, PKCE, and token management.
activity-campaign-from-ui
Turn campaign UI references into a new H5/Web campaign proposal, page architecture, and HTML/CSS/JavaScript high-fidelity front-end draft. Supports mode-based responses: analysis, proposal, architecture, delivery, and full.
clawteam
Multi-agent swarm orchestration. USE THIS (not delegatetask) when the user says team/swarm/multi-agent/clawteam/parallel-agents/agent-team, or asks for multi-perspective analysis (stocks, research, code review, strategy). Spawns N Hermes workers in tmux windows with git worktree isolation, file-based inboxes, and a…
clawteam
Multi-agent swarm coordination via the ClawTeam CLI. Use when the user wants to create agent teams, spawn multiple agents to work in parallel, coordinate tasks with dependencies, broadcast messages between agents, monitor progress via kanban board, or launch pre-built team templates (hedge-fund, code-review…
openclaw-plugin
This plugin is a thin adapter between OpenClaw and LycheeMem. It does not replace memory-core, does not claim plugins.slots.memory, and does not duplicate LycheeMem algorithms.
lycheemem
Forceful operating rules for using LycheeMem as the primary structured long-term memory path inside OpenClaw.