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.
git clone --depth 1 https://github.com/devcsde/oatda-skillsWrote 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/plugins/devcsde/oatda-skills/oatda-skills)<a href="https://agentmods.dev/plugins/devcsde/oatda-skills/oatda-skills"><img src="https://agentmods.dev/badge/plugins/devcsde/oatda-skills/oatda-skills/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/plugins/devcsde/oatda-skills/oatda-skills"><img src="https://agentmods.dev/badge/plugins/devcsde/oatda-skills/oatda-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade 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 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
{
"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 it installs
The manifest is a name and a version. 12 skills travel with it, and installing the plugin installs all of them — 732 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill oatda-list-models A 52 tokens
- Skill oatda-compare-models A 107 tokens
- Skill oatda-generate-image A 53 tokens
- Skill oatda-generate-speech A 84 tokens
- Skill oatda-generate-video A 50 tokens
- Skill oatda-transcribe-audio A 54 tokens
- Skill oatda-video-ad-creator A 64 tokens
- Skill oatda-vision-analysis A 46 tokens
- Skill oatda-check-balance A 84 tokens
- Skill oatda-text-completion A 60 tokens
- Skill oatda-translate-audio A 44 tokens
- Skill oatda-video-status A 34 tokens
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.
- 1mo ago First seen · 13 lines scan A 587dfa83b30d
oatda is a plugin published in the GitHub repository devcsde/oatda-skills (1 stars, last pushed 1mo 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
data
Data science and data engineering agents for visualization (D3, Highcharts), notebooks (Jupyter, Google Colab), R, and Python data engineering.
genai
Generative AI development specialist focused on LangChain for building LLM applications, chains, and agents.
machine-learning
Machine learning framework specialists for PyTorch, TensorFlow, and scikit-learn. Expert guidance for ML model development and training.
bifrost-plugin
Bifrost MCP gateway plugin for Claude Code and Claude Desktop: skill discovery, agent-driven memory, one-command onboarding, signed admin policy, and opt-in browser sign-in.
commander-hud
Commander HUD: Fable state, running agents, tool-call budget and update pill above the prompt.
ai-toolkit
Skills for Deep Learning (Keras 3), Reinforcement Learning (Python & C++), Claude Prompt Optimization, x402 Web3 Payments, and OpenClaw Setup.