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 neurocod/llm-loopnpx agentmods add plugins/neurocod/llm-loop/ask-user-gategit clone --depth 1 https://github.com/neurocod/llm-loopGrade A, and why
ask-user-gate 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": "ask-user-gate",
"version": "1.1.0",
"description": "Refuse shell commands that would stop the session on a permission prompt, and name the replacement for each one.",
"author": {
"name": "neurocod"
},
"homepage": "https://github.com/neurocod/llm-loop"
}
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 · 10 lines scan A 55a904d8f64f
ask-user-gate is a plugin published in the GitHub repository neurocod/llm-loop (2 stars, last pushed 4d 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
unknowns
Skills for discovering and closing knowledge gaps across the dev lifecycle, from Thariq's 'Know Your Unknowns'.
codex-bridge
Give Claude Code a GPT subagent, backed by the local Codex CLI.
research-papers
Annotated research paper collection management — retrieve, read, extract, cross-reference scientific papers.
claude-to-codex
Switch from Claude Code to Codex without losing context with one /handoff command.
programmator
Plugin marketplace listing 1 plugin: programmator.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.