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/nizos/probity/settingsgit clone --depth 1 https://github.com/nizos/probityGrade B, and why
probity scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
"Edit(**/.claude/settings*.json)", What it actually says
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash|Write|Edit|NotebookEdit",
"hooks": [
{
"type": "command",
"command": "npx @nizos/probity --agent claude-code --debug ${CLAUDE_PROJECT_DIR}/.claude/probity.jsonl"
}
]
}
]
},
"permissions": {
"deny": [
"Edit(**/probity.config.ts)",
"Write(**/probity.config.ts)",
"Edit(**/.claude/settings*.json)",
"Write(**/.claude/settings*.json)"
]
}
}
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 · 24 lines scan B 8b13d5a2cacc
probity is a settings file published in the GitHub repository nizos/probity (186 stars, last pushed 16d 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 B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other settings, from other repositories
dev-flow
An empty agent settings file, from a project described as: Engineering discipline for AI coding agents — from requirements through delivery.
settings
Agent settings declaring 2 hook events (PreToolUse, PostToolUse).
second-brain-health-check
Your Claude Code setup has 45 things that could be better. This finds them in 2 seconds.
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.