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.
npx agentmods add settings/floor/vlist/settingsgit clone --depth 1 https://github.com/floor/vlistGrade A, and why
vlist 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
{
"hooks": {
"PostToolUse": [
{
"matcher": "Edit",
"hooks": [
{
"type": "command",
"command": "set -o pipefail && cd $CLAUDE_PROJECT_DIR && bun run typecheck 2>&1 | tail -5",
"timeout": 30000
}
]
},
{
"matcher": "Write",
"hooks": [
{
"type": "command",
"command": "set -o pipefail && cd $CLAUDE_PROJECT_DIR && bun run typecheck 2>&1 | tail -5",
"timeout": 30000
}
]
}
],
"PreToolUse": [
{
"matcher": "Bash(git commit*)",
"hooks": [
{
"type": "command",
"command": "set -o pipefail && cd $CLAUDE_PROJECT_DIR && bun run typecheck 2>&1 | tail -10 && echo 'Typecheck passed' || (echo 'BLOCKED: typecheck failed — fix type errors before committing' >&2; exit 2)",
"timeout": 30000
}
]
},
{
"matcher": "Bash(git push*)",
"hooks": [
{
"type": "command",
"command": "set -o pipefail && cd $CLAUDE_PROJECT_DIR && (bun run typecheck 2>&1 | tail -5) && (bun test 2>&1 | tail -10) && echo 'All checks passed' || (echo 'BLOCKED: tests or typecheck failed — fix before pushing' >&2; exit 2)",
"timeout": 120000
}
]
}
]
}
}
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 · 49 lines scan A f21a007f6773
vlist is a settings file published in the GitHub repository floor/vlist (16 stars, last pushed 1mo 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 2026-09-01.
Other settings, from other repositories
js2
Agent settings declaring 8 hook events (TeammateIdle, SessionStart, Stop, Notification) and 1 allowed tools.
nextjs-template-mongodb
Agent settings configuring enabledPlugins.
supabase
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
claude-cookbooks
Agent settings declaring 2 hook events (SessionStart, PreToolUse).
claude-code-best-practice
Agent settings declaring 30 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 24 allowed tools.
electron
Agent settings declaring 17 allowed tools.