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/oxidian/cc-plugins/settingsgit clone --depth 1 https://github.com/oxidian/cc-pluginsGrade A, and why
cc-plugins 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
{
"attribution": {
"commit": "",
"pr": ""
},
"permissions": {
"allow": [
"Bash(git add:*)",
"Bash(git commit:*)",
"Bash(git diff:*)",
"Bash(git log:*)",
"Bash(git mv:*)",
"Bash(git rm:*)",
"Bash(git show-branch:*)",
"Bash(git show:*)",
"Bash(gh api:*)",
"Bash(gh issue view:*)",
"Bash(gh pr checks:*)",
"Bash(gh pr diff:*)",
"Bash(gh pr list:*)",
"Bash(gh pr show:*)",
"Bash(gh pr view:*)",
"Bash(gh run list:*)",
"Bash(gh run view:*)",
"Bash(find:*)",
"Bash(grep:*)",
"Bash(ls:*)",
"Bash(tree:*)",
"Bash(make check)",
"Bash(make format)",
"WebFetch(domain:ai.pydantic.dev)",
"WebFetch(domain:docs.astral.sh)",
"WebFetch(domain:docs.github.com)",
"WebFetch(domain:gist.github.com)",
"WebFetch(domain:github.com)",
"WebFetch(domain:pypi.org)",
"WebSearch"
],
"deny": [
"Bash(rm)"
]
},
"enableAllProjectMcpServers": true,
"enabledMcpjsonServers": []
}
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 · 46 lines scan A b82e35157744
cc-plugins is a settings file published in the GitHub repository oxidian/cc-plugins (11 stars, last pushed 1mo ago), licensed Apache-2.0. 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 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.