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 5.5 | $0.00042 | $0.00649 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo 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 (229 stars, last pushed 3mo ago), licensed MIT. It adds 104 tokens to every session and 1,622 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 2026-08-30.
Other skills, from other repositories
img2threejs
Turn an object or character reference image into a quality-gated, animation-ready procedural Three.js model built in code. Use for image-to-3D reconstruction, detail-accurate object rebuilds, stylized/likeness-maximized human characters, sculpt specs, and staged code generation.
ai-research-writing-skill
End-to-end research paper generation, review, and revision for ML/AI/CV/NLP projects from repositories, notes, experiment logs, drafts, and conference templates. Use when building a paper story, mapping claims to evidence, writing or revising sections, producing figures and tables, verifying citations, acting as a…
speckit.game-embedded
Embedded Game & WASM Bridge Specialist - Unity WebGL, Godot 4 Web/WASM, PlayCanvas, 2-Way JS Bridge, COOP/COEP Headers, Brotli Streaming, and Shell UI Integration.
speckit.game-native-js
Native Web Game Developer - Phaser 3, PixiJS, Three.js/R3F, Babylon.js, 60 FPS Fixed Timestep loop, Object Pooling (Zero-GC), Hybrid DOM HUD, and Web Audio API.
roblox-creator-store-security-audit
Audit Roblox Creator Store, Toolbox, inventory, group, universe, package, model, UI, gameplay, plugin-like, and other third-party imported assets for malicious or risky scripts. Use whenever Claude imports, inserts, reviews, or trusts Creator Store assets, especially assets with Scripts, LocalScripts, ModuleScripts…
roblox-debugging-bugfix
Debug and fix Roblox bugs through Studio MCP. Use for repro steps, console errors, script search/read/edit flow, broken UI, failed gameplay systems, data issues, remotes, regressions, root-cause reports, and post-fix verification.