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.
/plugin marketplace add devcsde/oatda-skillsnpx agentmods add plugins/devcsde/oatda-skills/oatda-skillsgit clone --depth 1 https://github.com/devcsde/oatda-skillsGrade A, and why
oatda 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.
What it actually says
{
"name": "oatda",
"description": "OATDA (One API To Direct All) — Unified access to 10+ LLM providers (OpenAI, Anthropic, Google, Deepseek, Mistral, xAI, Alibaba, MiniMax, ZAI, Moonshot, Bytedance) for text generation, vision analysis, image generation, video generation, audio generation/transcription/translation, model comparison, and balance checking through a single API.",
"version": "1.3.1",
"author": {
"name": "devcsde",
"url": "https://github.com/devcsde"
},
"repository": "https://github.com/devcsde/oatda-skills",
"homepage": "https://oatda.com",
"license": "Apache-2.0"
}
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 13 lines scan A 587dfa83b30d
oatda is a plugin published in the GitHub repository devcsde/oatda-skills (0 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
vgv-ai-flutter-plugin
Best-practice skills for Flutter and Dart covering accessibility, animations, BLoC, testing, theming, navigation, security, internationalization, layered architecture, license compliance, UI packages, project creation, SDK/lint upgrades, and an autonomous quality-gate loop that drives analyze, format, test, and…
perso-ai
Perso AI agent plugins — AI dubbing (video voice translation with lip-sync & audio separation) and SRT subtitle extraction & translation.
perso-dubbing
Auto-dub videos into other languages with lip-sync via the Perso AI Dubbing API, plus voice/background audio separation and SRT subtitle extraction & translation (/srt). Handles single files, folders, URLs, oversized/long media (auto split & merge), multi-language output, and resume.
inkstone
Custom Claude Code skills by Augustin Chan — ink painting, UI/UX audits, media kits, arXiv search, and more.
50k-website-builder
Build cinematic, scroll-animated marketing sites that look like they cost $50,000 or more. A reference-and-taste phase, a design token system, a GSAP motion system, a signature-move library, a brand-to-build workflow, and in-browser QA.
media-generation
Generate images, videos, speech, and transcriptions through 13 AI providers (OpenAI, Google, Azure, ElevenLabs, Deepgram, Fal.ai, Luma, Replicate, Stability, Runway, OpenRouter, MiniMax, Edge TTS). Supports 100+ models with structured JSON output for agent integration.