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 bearlike/Assistantnpx agentmods add plugins/bearlike/assistant/widget_buildergit clone --depth 1 https://github.com/bearlike/AssistantGrade A, and why
widget-builder 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": "widget-builder",
"display_name": "Custom Widgets",
"description": "st-widget-builder sub-agent for stlite console widgets.",
"version": "0.1.0",
"author": "Mewbo",
"requires-capabilities": ["stlite"],
"session_tools": [
{
"tool_id": "submit_widget",
"module": "mewbo_core.builtin_plugins.widget_builder.submit_widget",
"class": "SubmitWidgetTool"
}
]
}
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 · 16 lines scan A cda707d04be7
widget-builder is a plugin published in the GitHub repository bearlike/Assistant (41 stars, last pushed 7d 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 2026-08-30.
Other plugins, from other repositories
awesome-chatgpt-repositories
Search and discover 2500+ curated open-source GitHub repositories related to ChatGPT and LLMs.
claude-dynamic-workflows-codex
Run Claude Code dynamic-workflow scripts on a local Codex App Server — fan out Codex/GPT agents with the agent/parallel/pipeline DSL, sessionful steerable workers, supervised fleets (--multi), live viewers, and run analytics.
darkroom
Darkroom Engineering AI coding standards. Layered config with portable AGENTS.md, progressive complexity, and two-tier knowledge system.
webfetch
Self-hosted web search for LLM agents - same accuracy as hosted websearch at a third of the cost.
ls-browser
Browser automation skills.
microsoft-webui
Microsoft WebUI skillset for building and debugging server-first, island-hydrated Web Components with compiled protocol-based SSR, routing workflows, and production-ready .NET host integration.