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 Cambrionic/winnownpx agentmods add plugins/cambrionic/winnow/plugingit clone --depth 1 https://github.com/Cambrionic/winnowGrade A, and why
winnow 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 today.
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": "winnow",
"displayName": "Winnow",
"version": "0.1.0",
"description": "Use many MCP servers without context bloat. Winnow hides all your MCP servers behind one gateway exposing just 4 tools (search_tools / load_tool / call_tool / run_code), so the model spends a fraction of the context.",
"author": { "name": "Cambrionic", "url": "https://github.com/Cambrionic" },
"homepage": "https://github.com/Cambrionic/winnow",
"repository": "https://github.com/Cambrionic/winnow",
"keywords": ["mcp", "context", "gateway", "tools", "token-efficiency"]
}
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.
- today First seen · 11 lines scan A e984193eb3f1
winnow is a plugin published in the GitHub repository Cambrionic/winnow (0 stars, last pushed 18d 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 2026-08-31.
Other plugins, from other repositories
cx-devassist-marketplace
Checkmarx CxOne security scanning plugins for Claude Code.
cx-devassist
Checkmarx-powered security scanning and fixing inside your coding loop. Checks the code you write and the code AI generates for vulnerabilities and risky dependencies, then returns precise, engine-backed fixes. Best invoked after writing or changing code, before commits, and around security-sensitive logic. Applies…
identity-forge
Identity Forge tools and agent guidance for design systems and brand work.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
nextjs
Official Claude Code plugin marketplace for Next.js, serving the skills that ship in the vercel/next.js repository.
claude-plugins-official
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.