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 WU-HAOTIAN34/2dimg2motion --skill img2mo-learngit clone --depth 1 https://github.com/WU-HAOTIAN34/2dimg2motionWrote 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/wu-haotian34/2dimg2motion/img2mo-learn)<a href="https://agentmods.dev/skills/wu-haotian34/2dimg2motion/img2mo-learn"><img src="https://agentmods.dev/badge/skills/wu-haotian34/2dimg2motion/img2mo-learn/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/wu-haotian34/2dimg2motion/img2mo-learn"><img src="https://agentmods.dev/badge/skills/wu-haotian34/2dimg2motion/img2mo-learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium System Prompt Leakage · line 79 Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.Fix: Guard against indirect extraction by refusing to summarize, translate, or rephrase system instructions. Add explicit anti-extraction clauses.
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 | $0.00104 | $0.01622 |
| Opus 5 | $0.00052 | $0.00811 |
| Sonnet 5 | $0.00021 | $0.00324 |
| Haiku 4.5 | $0.00010 | $0.00162 |
Grade A, and why
img2mo-learn 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 11d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Img2mo-learn
Overview
Use this skill when the user invokes:
/img2mo-learn <resource-path-or-folder>
img2mo-learn <resource-path-or-folder>
The goal is to turn finished or reference motion assets into reusable project knowledge. Store learned knowledge in the project-level img2mo-knowledge/ folder, never in the installed Codex skill directory during normal work.
Input Resolution
Resolve the argument after img2mo-learn as follows:
- If it is an existing relative or absolute path, use it directly.
- If it is a bare name, first try
sample\<name>, thenoutput\<name>, thenmotion\<name>. - If it is a folder, inspect likely assets in this order:
manifest.json,preview.gif,contact-sheet.*,spritesheet.*,fullframe/,frames/, Spine.json/.atlas/.skel, then videos. - If no matching resource exists, report the missing path and ask for the correct path.
Supported resources:
- video files such as
.mp4,.mov,.webm; - PNG frame folders, spritesheets, contact sheets, or GIF previews;
- project outputs from this skill such as
output/<action-id>/; - Spine-style assets such as
.json,.atlas,.skel, texture folders; - local reference-library folders under
motion/.
Knowledge Location
Create this structure if missing:
img2mo-knowledge/
|-- index.md
|-- learnings.jsonl
|-- action-patterns.md
|-- style-patterns.md
|-- prompt-patterns.md
`-- failures.md
Append one JSON object per learning session to img2mo-knowledge/learnings.jsonl. Keep Markdown files concise and curated; do not paste huge logs, full prompts, or complete frame listings.
Learning Workflow
- Identify the resource type.
- For video: read frame size, fps, duration, and frame count with
ffprobewhen available. - For frame sequences: count frames, inspect canvas sizes, alpha/background, and contact sheet if present.
- For spritesheets: infer grid/cell count when possible; otherwise describe visible beats.
- For Spine assets: inspect animation names, bone/slot names, skins, attachments, timeline names, and texture organization without assuming rendered motion if frames are not available.
- For video: read frame size, fps, duration, and frame count with
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.
- 11d ago First seen · 144 lines · 104 tokens per session scan A bed5970054e9
img2mo-learn is a skill published in the GitHub repository WU-HAOTIAN34/2dimg2motion (190 stars, last pushed 2mo ago), licensed MIT. It adds 104 tokens to every session and 1,622 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
roblox-asset-pipeline
Plan and execute Roblox asset workflows. Use for Creator Store search, inventory/group/universe assets, inserting assets, generated meshes, generated materials, procedural models, uploaded images, thumbnails, icons, decals, style consistency, import security audits, and asset performance budgets.
roblox-animation-audio-feedback
Improve Roblox feel through animation, audio, VFX, haptics-like feedback, reward juice, movement feel, combat feedback, UI transitions, emotes, and satisfying loop feedback without hurting mobile performance.
asset-gen
Generate visual assets from text prompts: PNG images (Gemini / xAI Grok), GLB 3D models (Tripo3D), rigged biped characters, retargeted animations, and frame-by-frame animated sprites, plus background removal. Use whenever a game needs generated art.
screenshot-isolated
Render a target GameObject from a chosen camera angle with optional layer-based isolation, configurable background (solid/skybox/transparent), multi-light setup via JSON, and Composite (2x2 Front/Right/Back/Top) mode. Returns a PNG image. When isolated=true, inactive children may briefly fire OnEnable — see the body…
screenshot-camera
Capture a screenshot from a Unity Camera and return it as a PNG image for direct LLM inspection. Falls back to Camera.main (then any active camera) when cameraRef is null. Width and height are capped to keep response size manageable.
screenshot-game-view
Capture a screenshot of the Unity Editor's Game View by reading its internal render texture directly. Image size matches the current Game View resolution; the tool corrects Y-flip on DirectX / Metal so the output is always upright. Requires an open Game View window.