More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Claude Code Hooks Starter

    2

    Add a small, readable Claude Code hooks setup for formatting, checks and protection of sensitive files.

    Free

    1 useSecurity scanned
    Claude Code Hooks Starter

    Claude Code Hooks Starter

    Example session with this skill installed

    Set up Claude Code hooks for my TypeScript repo. Format edited files, run typecheck after changes and block edits to .env files.

    • Read your context and instructions
    • Compiled the claude code hooks
    HOOKS STARTER: INSTALLED AND TESTED
    
    Repository detected
    TypeScript, npm, Prettier and a typecheck script are already present. No new package is required.
    
    Files written
    • .claude/settings.json: three narrow hook matchers
    • scripts/hook-check.mjs: readable path guard with clear exit messages
    
    Hook map
    PreToolUse: blocks writes to .env, .env.*, *.pem and credential files.
    PostToolUse: runs the existing formatter only for supported edited files.
    Stop: runs npm run typecheck once after the agent finishes.
    
    Verification
    PASS: editing src/example.ts triggered the configured formatter.
    PASS: a simulated write to .env.local was blocked before the tool ran.
    PASS: npm run typecheck exited with code 0.
    PASS: the prior .claude settings entry remains present.
    
    Rollback
    Restore .claude/settings.json from its saved copy and remove scripts/hook-check.mjs.
    
    Good to know
    Commands are local to this repository. Review them before enabling the same configuration elsewhere.
    

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Claude Code Hooks Starter creates a small hooks configuration for one existing repository. It first discovers the package manager and available scripts, then adds only the requested guard, formatter and final check. Existing Claude settings are merged rather than replaced. The result includes readable local files, a command map and proof from one allowed action, one blocked action and the final check. No dependency is installed or command enabled without review.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.

    Hook support depends on current Claude Code. Commands must match your repo. Review every automated command before enabling.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 27 days ago

    • Free with an Agensi account

    Requires

    Nothing to install.

    Permissions

    Read Files
    Write Files
    Terminal / Shell

    Reads supplied evidence and writes requested local artifacts only. No account access, purchases, publishing or messaging.

    Listed27 days ago

    What's inside

    Frequently Asked Questions

    No. It uses commands already available in the repo.

    No. It reads and merges with user approval.

    New in Workflow Automation

    Free