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 skills add VersoXBT/claude-initial-setup --skill hook-recipesgit clone --depth 1 https://github.com/VersoXBT/claude-initial-setupWrote 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/skills/versoxbt/claude-initial-setup/hook-recipes)<a href="https://agentmods.dev/skills/versoxbt/claude-initial-setup/hook-recipes"><img src="https://agentmods.dev/badge/skills/versoxbt/claude-initial-setup/hook-recipes/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/skills/versoxbt/claude-initial-setup/hook-recipes"><img src="https://agentmods.dev/badge/skills/versoxbt/claude-initial-setup/hook-recipes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.02229 |
| Opus 5.5 | $0.00027 | $0.00892 |
| Sonnet 5.5 | $0.00014 | $0.00446 |
| Haiku 4.5 | $0.00007 | $0.00223 |
Grade B, and why
hook-recipes scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
A collection of battle-tested hook configurations for Claude Code. Copy these directly into `~/.claude/settings.json` under the `hooks` key. How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hook Recipes
A collection of battle-tested hook configurations for Claude Code. Copy these directly into ~/.claude/settings.json under the hooks key.
When to Use
- User asks for a specific hook recipe or example
- User wants to auto-format code after edits
- User wants to block certain file types from being created
- User wants warnings about console.log, TODO, or debug statements
- User needs a git push review gate
- User asks "how do I set up hooks for X"
Core Recipes
Recipe 1: Prettier Auto-Format on Edit
Formats JavaScript, TypeScript, CSS, and JSON files after every edit or write:
{
"hooks": {
"PostToolUse": [
{
"matcher": "Edit|Write",
"command": "if echo \"$CLAUDE_FILE_PATH\" | grep -qE '\\.(js|ts|jsx|tsx|css|scss|json|md)$'; then npx prettier --write \"$CLAUDE_FILE_PATH\" 2>/dev/null; fi",
"description": "Prettier auto-format"
}
]
}
}
Recipe 2: TypeScript Type-Check After Edit
Runs tsc --noEmit after editing TypeScript files to catch type errors immediately:
{
"matcher": "Edit|Write",
"command": "if echo \"$CLAUDE_FILE_PATH\" | grep -qE '\\.tsx?$'; then npx tsc --noEmit --pretty 2>&1 | tail -20; fi",
"description": "TypeScript type-check"
}
Recipe 3: Console.log Warning
Warns when a file containing console.log is edited. Does not block, just informs:
{
"matcher": "Edit|Write",
"command": "if echo \"$CLAUDE_FILE_PATH\" | grep -qE '\\.(js|ts|jsx|tsx)$'; then MATCHES=$(grep -n 'console\\.log' \"$CLAUDE_FILE_PATH\" 2>/dev/null); if [ -n \"$MATCHES\" ]; then echo \"WARNING: console.log found in $CLAUDE_FILE_PATH:\"; echo \"$MATCHES\" | head -5; fi; fi",
"description": "Warn about console.log in edited files"
}
Recipe 4: Git Push Review Gate
Opens the diff for review before allowing a git push. Blocks the push so the user can inspect:
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"command": "if echo \"$CLAUDE_TOOL_INPUT\" | grep -q 'git push'; then echo '=== FILES TO BE PUSHED ===' && git diff --stat HEAD~1 && echo '' && echo 'Review the above changes. This hook will allow the push to proceed.'; fi",
"description": "Show diff summary before git push"
}
]
}
}
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 · 233 lines · 68 tokens per session scan B 81a45e591757
hook-recipes is a skill published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 2,229 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
commit-trailers
Structured commit trailers — adds Constraint, Rejected, Scope-risk, and Not-tested metadata to commit messages. Captures architectural decisions and known gaps in git history.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
what-did-i-get-done
Summarize authored commits over a user-specified time period into a concise update.
block-no-verify-hook
Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.
cross-repo-cache
Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches. Compares peer repo git hashes against stored hashes from last coordinator run. Triggers on: entering Phase 1.4.1, checking cross-repo cache, before discovering peers. Returns CROSSREPOCACHEHIT with cached status or…