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/fo0/clawstash/settingsgit clone --depth 1 https://github.com/fo0/clawstashGrade B, and why
settings 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.
"command": "cmd=$(jq -r '.tool_input.command // empty'); if echo \"$cmd\" | grep -qE 'git commit'; then cd \"$CLAUDE_PROJECT_DIR\" || exit 0; staged=$(git diff --cached --name-only 2>/dev/null | grep -E '^(\\.claude/|CLA How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"$schema": "https://json.schemastore.org/claude-code-settings.json",
"permissions": {
"allow": [
"mcp__claude-code-remote__*",
"mcp__Claude_Code_Remote__*",
"mcp__claude_code_remote__*",
"mcp__github__subscribe_pr_activity",
"mcp__github__unsubscribe_pr_activity",
"Bash(npm run format)",
"Bash(npm run format:check)",
"Bash(npm run lint)",
"Bash(npx tsc --noEmit)",
"Bash(npm test)",
"Bash(npm run build)"
]
},
"hooks": {
"SessionStart": [
{
"hooks": [
{
"type": "command",
"command": "echo 'Session start -- read MEMORY.md and SCRATCHPAD.md to restore context. Check BACKLOG.md only if user references prior findings.'"
}
]
}
],
"PostToolUse": [
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "over=\"\"; for spec in \"CLAUDE.md 20000\" \"MEMORY.md 16000\" \"SCRATCHPAD.md 8000\"; do set -- $spec; f=\"$CLAUDE_PROJECT_DIR/$1\"; [ -f \"$f\" ] || continue; c=$(wc -c < \"$f\"); [ \"$c\" -gt \"$2\" ] && over=\"$over $1 $c/$2 chars;\"; done; if [ -n \"$over\" ]; then printf '%s' '{\"hookSpecificOutput\":{\"hookEventName\":\"PostToolUse\",\"additionalContext\":\"Context budget exceeded --'\"$over\"' offload now per agent_docs/context_budget.md: MOVE content out (CLAUDE.md sections to agent_docs/, memory entries to docs/adr/ or agent_docs/memory_archive/) and leave a one-line pointer. Never delete to fit.\"}}'; fi; exit 0"
}
]
}
],
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "cmd=$(jq -r '.tool_input.command // empty'); if echo \"$cmd\" | grep -qE 'git commit'; then cd \"$CLAUDE_PROJECT_DIR\" || exit 0; staged=$(git diff --cached --name-only 2>/dev/null | grep -E '^(\\.claude/|CLAUDE\\.md|AGENTS\\.md|agent_docs/|docs/wWhat 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 · 53 lines scan B 1ca82e1ee360
settings is a settings file published in the GitHub repository fo0/clawstash (1 stars, last pushed yesterday), 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 2026-08-31.
Other settings, from other repositories
mcp-server-woocommerce
An empty agent settings file, from a project described as: MCP server for managing WooCommerce stores through AI assistants.
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).