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 0xBrewing/ui-evidencenpx agentmods add plugins/0xbrewing/ui-evidence/marketplacegit clone --depth 1 https://github.com/0xBrewing/ui-evidenceGrade A, and why
ui-evidence 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 2d 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
{
"metadata": {
"pluginRoot": "./plugins"
},
"plugins": [
{
"name": "ui-evidence",
"source": "ui-evidence",
"skills": [
"./skills/ui-evidence"
]
}
]
}
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.
- 2d ago First seen · 15 lines scan A 99f836a546cf
ui-evidence is a plugin published in the GitHub repository 0xBrewing/ui-evidence (5 stars, last pushed 5mo 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
ubrowser-marketplace
Plugin marketplace listing 1 plugin: ubrowser.
ubrowser
Ultra-fast browser automation with 98% token reduction via batch execution and compact snapshots.
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.
personal-corp-os
Personal Corp framework: run your business with AI agents through GitHub, department repos, safe public releases, Telegram, agent gateways, html-draft diagrams, and media/art-direction workflows.
playwright-bot-bypass
Stealth browser automation — bypass bot detection with rebrowser-playwright / undetected-chromedriver.
tlive
tlive hooks + skill + commands — IM approvals, session monitoring, web terminal.