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/adamw7/tools/settingsgit clone --depth 1 https://github.com/adamw7/toolsGrade A, and why
tools 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 2d ago.
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.
This is a copy
81% identical to cva — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"permissions": {
"allow": [
"Bash(unzip -p *)",
"Bash(unzip -l *)",
"Bash(mvn dependency:tree *)",
"Bash(mvn dependency:analyze *)",
"Bash(mvn *)",
"PowerShell(mvn *)",
"Edit"
]
},
"hooks": {
"SessionStart": [
{
"hooks": [
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/session-start.sh"
}
]
}
]
}
}
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.
- 2d ago First seen · 26 lines scan A 44f79bf6e411
tools is a settings file published in the GitHub repository adamw7/tools (11 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. It is 81% identical to cva, differing in 13 lines, and is treated as a copy.
Other settings, from other repositories
jhelm
Agent settings declaring 39 allowed tools.
agent-skills
Claude Code plugin for Java Spring backend — 21 skills, 9 agents, 17 hooks, TDD workflow enforcement. Hook-bootstrapped harness with skill auto-routing, verify/fix loops, multi-agent spawning, and session memory.
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.