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 hooks/cfrs2005/claude-init/stopgit clone --depth 1 https://github.com/cfrs2005/claude-initGrade A, and why
Stop 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 commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.
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
{
"Stop": [
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "#!/bin/bash\n# Final check for console.logs in modified files\ninput=$(cat)\n\nif git rev-parse --git-dir > /dev/null 2>&1; then\n modified_files=$(git diff --name-only HEAD 2>/dev/null | grep -E '\\.(ts|tsx|js|jsx)$' || true)\n \n if [ -n \"$modified_files\" ]; then\n has_console=false\n while IFS= read -r file; do\n if [ -f \"$file\" ]; then\n if grep -q \"console\\.log\" \"$file\" 2>/dev/null; then\n echo \"[Hook] 警告: 在 $file 中发现 console.log\" >&2\n has_console=true\n fi\n fi\n done <<< \"$modified_files\"\n \n if [ \"$has_console\" = true ]; then\n echo \"[Hook] 提交前请移除 console.log 语句\" >&2\n fi\n fi\nfi\n\necho \"$input\""
}
],
"description": "会话结束前对修改文件中的 console.log 进行最终审计"
},
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "~/.claude/hooks/memory-persistence/session-end.sh"
}
],
"description": "结束时持久化会话状态"
},
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "~/.claude/skills/continuous-learning/evaluate-session.sh"
}
],
"description": "评估会话以提取模式"
}
]
}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 · 34 lines scan A 54e600fdfa7f
Stop is a hook published in the GitHub repository cfrs2005/claude-init (1,365 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. 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 hooks, from other repositories
PostToolUse
Runs after a tool call finishes for Write and Edit tool calls, executing format_and_lint.sh. From supabase/supabase.
SessionStart
Runs when a session starts on startup, executing install_pkgs.sh. From supabase/supabase.
SessionStart
Runs when a session starts, executing on-start.js via node. From google-gemini/gemini-cli.
PreToolUse
Runs before the agent uses a tool, executing pre-write.sh and pre-bash.sh (2 commands). From anthropics/claude-cookbooks.
SessionStart
Runs when a session starts, executing session-start.sh. From anthropics/claude-cookbooks.
SessionStart
Runs when a session starts on startup, clear and compact, executing run-hook.cmd. From obra/superpowers.