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/nwiizo/ccswarm/settingsgit clone --depth 1 https://github.com/nwiizo/ccswarmGrade C, and why
ccswarm scanned grade C 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"Bash(rm -rf /)*", What it actually says
{
"permissions": {
"allow": [
"Read",
"Glob",
"Grep",
"Bash(cargo *)",
"Bash(git status*)",
"Bash(git diff*)",
"Bash(git log*)",
"Bash(git branch*)",
"Bash(git worktree *)",
"Bash(ls *)",
"Bash(wc *)",
"Bash(similarity-rs *)",
"mcp__serena__*",
"Agent(Explore)",
"Agent(frontend-specialist)",
"Agent(backend-specialist)",
"Agent(devops-specialist)",
"Agent(qa-specialist)",
"Agent(rust-fix-agent)",
"Agent(code-refactor-agent)",
"Agent(architecture-reviewer)",
"Agent(all-reviewer)",
"Agent(review-fix-agent)"
],
"deny": [
"Bash(rm -rf /)*",
"Bash(cargo publish*)",
"Edit(.git/***)",
"Edit(.env*)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": ".claude/hooks/validate-agent-scope.sh"
}
]
}
],
"PostToolUse": [
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": ".claude/hooks/format-code.sh"
}
]
}
],
"SubagentStop": [
{
"hooks": [
{
"type": "command",
"command": ".claude/hooks/audit-trail.sh"
}
]
}
],
"Stop": [
{
"hooks": [
{
"type": "command",
"command": ".claude/hooks/audit-trail.sh"
}
]
}
]
},
"env": {
"RUST_LOG": "info",
"CCSWARM_AUDIT_ENABLED": "true"
}
}
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 · 84 lines scan C 591e7254790a
ccswarm is a settings file published in the GitHub repository nwiizo/ccswarm (149 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 C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other settings, from other repositories
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.
uv
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
ui-ux-pro-max-skill
Agent settings declaring 7 allowed tools.