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 EveryInc/garbage-mannpx agentmods add plugins/everyinc/garbage-man/email-cleanergit clone --depth 1 https://github.com/EveryInc/garbage-manGrade A, and why
email-cleaner 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": "email-cleaner",
"version": "0.2.0",
"description": "Provider-neutral email review and future-mail cleanup for AI agents",
"author": {
"name": "Every",
"url": "https://every.to/"
},
"homepage": "https://github.com/EveryInc/email-cleaner",
"repository": "https://github.com/EveryInc/email-cleaner",
"license": "MIT",
"keywords": ["email", "imap", "inbox-zero", "productivity"]
}
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 · 14 lines scan A 5cbe352049ea
email-cleaner is a plugin published in the GitHub repository EveryInc/garbage-man (5 stars, last pushed 22d 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
personal-corp-os
Personal Corp OS: run a one-person company through AI agents with a weekly rhythm, department repos, safe public releases, and open Claude Code and Codex skills.
openmapstack
Agentic GIS / geospatial workflows: source discovery and provenance (from open data sources first), vector/raster/point-cloud pipelines, CRS and metric analysis, spatial SQL, QGIS projects, tile generation, and web maps — compiled into reproducible projects.
input-repo
Fixture plugin manifest.
claude-shorts
Interactive longform-to-shortform video creator. Extracts viral-ready short clips from long videos with Remotion-rendered animated captions, AI segment scoring, and platform-optimized exports for YouTube Shorts, TikTok, and Instagram Reels.
threat-model
Produce threat models for open-source projects: the security contract between a project and its users, structured for downstream integrators and vulnerability triagers.
mainbranch
Plugin marketplace listing 1 plugin: mainbranch.