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/pengzhangzhi/superpowers-mlWrote 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/pengzhangzhi/superpowers-ml/gemini-extension)<a href="https://agentmods.dev/plugins/pengzhangzhi/superpowers-ml/gemini-extension"><img src="https://agentmods.dev/badge/plugins/pengzhangzhi/superpowers-ml/gemini-extension/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/pengzhangzhi/superpowers-ml/gemini-extension"><img src="https://agentmods.dev/badge/plugins/pengzhangzhi/superpowers-ml/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
superpowers-ml 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": "superpowers-ml",
"description": "Superpowers core skills plus a conservative ML-research layer. Fork of obra/superpowers.",
"version": "5.1.0-ml.0",
"contextFileName": "GEMINI.md"
}
What ships with it
4 files beside gemini-extension.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 · 7 lines scan A 6124139c25f5
superpowers-ml is a plugin published in the GitHub repository pengzhangzhi/superpowers-ml (8 stars, last pushed 3d ago), licensed MIT. 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 2026-09-08.
Other plugins, from other repositories
nixtla-plugins marketplace
Plugin marketplace listing 3 plugins: nixtla-baseline-lab, nixtla-bigquery-forecaster, nixtla-search-to-slack.
nixtla-baseline-lab
Run Nixtla-style baseline forecasting models (AutoETS, AutoTheta, SeasonalNaive) on M4 / custom CSV datasets from inside Claude Code. Pure statsforecast — no API keys.
ai-sdk-agents
Multi-agent orchestration with AI SDK v5 - handoffs, routing, and coordination for any AI provider (OpenAI, Anthropic, Google).
accessibility-test-scanner
A11y compliance testing with WCAG 2.1/2.2 validation, screen reader compatibility, and automated accessibility audits.
access-control-auditor
Audit access control implementations.
api-batch-processor
Implement batch API operations with bulk processing and job queues.