claude-init is an archived project template for initializing Claude Code development environments, with Chinese-localized configuration and workflows. Developers on macOS or Linux use it to set up agents, skills, commands, rules, hooks, and development contexts for Claude Code. Its catalogue entries provide the included commands, agents, hooks, and skills.
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.
git clone --depth 1 https://github.com/cfrs2005/claude-initWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/hooks/cfrs2005/claude-init/post-tool-use)<a href="https://agentmods.dev/hooks/cfrs2005/claude-init/post-tool-use"><img src="https://agentmods.dev/badge/hooks/cfrs2005/claude-init/post-tool-use/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/hooks/cfrs2005/claude-init/post-tool-use"><img src="https://agentmods.dev/badge/hooks/cfrs2005/claude-init/post-tool-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
PostToolUse 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 1mo ago.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- PostToolUse — 91% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"PostToolUse": [
{
"matcher": "tool == \"Bash\"",
"hooks": [
{
"type": "command",
"command": "#!/bin/bash\n# Auto-detect PR creation and log useful info\ninput=$(cat)\ncmd=$(echo \"$input\" | jq -r '.tool_input.command')\n\nif echo \"$cmd\" | grep -qE 'gh pr create'; then\n output=$(echo \"$input\" | jq -r '.tool_output.output // \"\"')\n pr_url=$(echo \"$output\" | grep -oE 'https://github.com/[^/]+/[^/]+/pull/[0-9]+')\n \n if [ -n \"$pr_url\" ]; then\n echo \"[Hook] PR 已创建: $pr_url\" >&2\n echo \"[Hook] 正在检查 GitHub Actions 状态...\" >&2\n repo=$(echo \"$pr_url\" | sed -E 's|https://github.com/([^/]+/[^/]+)/pull/[0-9]+|\\1|')\n pr_num=$(echo \"$pr_url\" | sed -E 's|.*/pull/([0-9]+)|\\1|')\n echo \"[Hook] 审查 PR: gh pr review $pr_num --repo $repo\" >&2\n fi\nfi\n\necho \"$input\""
}
],
"description": "PR 创建后记录 URL 并提供审查命令"
},
{
"matcher": "tool == \"Edit\" && tool_input.file_path matches \"\\\\.(ts|tsx|js|jsx)$\"",
"hooks": [
{
"type": "command",
"command": "#!/bin/bash\n# Auto-format with Prettier after editing JS/TS files\ninput=$(cat)\nfile_path=$(echo \"$input\" | jq -r '.tool_input.file_path // \"\"')\n\nif [ -n \"$file_path\" ] && [ -f \"$file_path\" ]; then\n if command -v prettier >/dev/null 2>&1; then\n prettier --write \"$file_path\" 2>&1 | head -5 >&2\n fi\nfi\n\necho \"$input\""
}
],
"description": "编辑后使用 Prettier 自动格式化 JS/TS 文件"
},
{
"matcher": "tool == \"Edit\" && tool_input.file_path matches \"\\\\.(ts|tsx)$\"",
"hooks": [
{
"type": "command",
"command": "#!/bin/bash\n# Run TypeScript check after editing TS files\ninput=$(cat)\nfile_path=$(echo \"$input\" | jq -r '.tool_input.file_path // \"\"')\n\nif [ -n \"$file_path\" ] && [ -f \"$file_path\" ]; then\n dir=$(dirname \"$file_path\")\n project_root=\"$dir\"\n while [ \"$project_root\" != \"/\" ]What else hooks.json configures
This page is one entry in a file that holds 5. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 1mo ago First seen · 44 lines scan A e687d937fc0e
PostToolUse is a hook published in the GitHub repository cfrs2005/claude-init (1,361 stars, last pushed 7mo 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
PreToolUse
Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From apache/superset.
PreToolUse
Runs before the agent uses a tool, executing pre-write.sh and pre-bash.sh (2 commands). From anthropics/claude-cookbooks.
PostToolUse
Runs after a tool call finishes for Bash tool calls, executing hooks.sh via sh (3 commands). From anthropics/claude-plugins-official.
PreCompact
Runs before the context is compacted for manual and auto tool calls, executing hook-handler.cjs via node (4 commands). From ruvnet/RuView.
SessionStart
Runs when a session starts on startup, executing worktree-setup.mjs via bash with --show-toplevel. From openclaw/openclaw.
SessionStart
Runs when a session starts, executing hook-handler.cjs and auto-memory-hook.mjs via node (2 commands). From ruvnet/RuView.