DEV Community

brian austin
brian austin

Posted on

Claude Code hooks: auto-format, lint, and test on every save

#claudecode #ai #devtools #productivity

Claude Code hooks: auto-format, lint, and test on every save

Claude Code hooks let you run shell commands automatically at specific points in Claude's workflow — before a tool runs, after a file is written, when a session starts or ends.

Most developers discover hooks when they're tired of Claude writing code that doesn't match their formatter settings. Here's how to stop that permanently.

Where hooks live

Hooks go in your CLAUDE.md or in .claude/settings.json at the project root:

{
  "hooks": {
    "afterFileWrite": "prettier --write $FILE",
    "afterFileWrite": "eslint --fix $FILE",
    "afterSessionEnd": "npm test -- --passWithNoTests"
  }
}
Enter fullscreen mode Exit fullscreen mode

The $FILE variable is the path of the file Claude just wrote. $SESSION_ID is available if you want to log by session.

The four hook points

Hook When it fires Common use
beforeToolRun Before any tool executes Log what Claude is about to do
afterFileWrite After Claude writes or edits a file Format, lint, type-check
afterBashRun After a bash command completes Capture output, trigger CI
afterSessionEnd When the session closes Run test suite, commit

Auto-format on write

This is the most common hook. Claude writes a file → it gets formatted immediately:

{
  "hooks": {
    "afterFileWrite": "npx prettier --write $FILE 2>/dev/null || true"
  }
}
Enter fullscreen mode Exit fullscreen mode

The || true prevents Claude from seeing a non-zero exit code as an error. If the file isn't JS/TS/CSS, prettier skips it silently.

Auto-lint and auto-fix 

{
  "hooks": {
    "afterFileWrite": "npx eslint --fix $FILE 2>/dev/null || true"
  }
}
Enter fullscreen mode Exit fullscreen mode

Problem: you can only have one afterFileWrite hook per settings block. Chain them with &&:

{
  "hooks": {
    "afterFileWrite": "npx prettier --write $FILE 2>/dev/null; npx eslint --fix $FILE 2>/dev/null; true"
  }
}
Enter fullscreen mode Exit fullscreen mode

Auto-test after session

Run your test suite every time Claude finishes a session:

{
  "hooks": {
    "afterSessionEnd": "npm test -- --passWithNoTests 2>&1 | tail -20"
  }
}
Enter fullscreen mode Exit fullscreen mode

Claude sees the test output and can immediately fix failures in the next session.

Self-healing loop pattern

This is where hooks get powerful. Combine afterSessionEnd with a script that reruns Claude if tests fail:

#!/bin/bash
# run-with-tests.sh
npm test 2>&1 > /tmp/test-output.txt
if [ $? -ne 0 ]; then
  echo "Tests failed, asking Claude to fix..."
  claude --print "Fix the failing tests. Output:\n$(cat /tmp/test-output.txt)" \
    --allowedTools Edit,Bash
fi
Enter fullscreen mode Exit fullscreen mode

Then set:

{
  "hooks": {
    "afterSessionEnd": "./run-with-tests.sh"
  }
}
Enter fullscreen mode Exit fullscreen mode

Claude writes code → session ends → tests run → if red, Claude is called again with the failure output → it fixes → tests run again. This loop continues until green (or you hit rate limits).

Rate limits break the loop

The self-healing loop is great until Claude hits its hourly rate limit mid-loop. When that happens:

  • The loop stalls
  • Your terminal hangs waiting for a Claude response
  • You have to manually restart

One way around this: point ANTHROPIC_BASE_URL at a proxy that removes the rate limit ceiling:

export ANTHROPIC_BASE_URL=https://simplylouie.com/api/proxy
npm run claude-loop
Enter fullscreen mode Exit fullscreen mode

SimplyLouie is a $2/month Claude proxy that removes rate limits — useful when you have a self-healing hook loop running overnight.

beforeToolRun: audit what Claude does

If you want a log of every tool Claude runs:

{
  "hooks": {
    "beforeToolRun": "echo \"$(date): $TOOL_NAME $TOOL_INPUT\" >> ~/.claude-audit.log"
  }
}
Enter fullscreen mode Exit fullscreen mode

This creates an append-only audit log at ~/.claude-audit.log. Useful for understanding what Claude actually does in long sessions.

Hooks vs CLAUDE.md

Hooks handle behavior (what happens after actions). CLAUDE.md handles knowledge (what Claude should know and follow).

They work best together:

  • CLAUDE.md: "Always use Prettier for formatting, never manual spaces"
  • Hook: afterFileWrite: prettier --write $FILE

CLAUDE.md tells Claude the rule. The hook enforces it automatically even if Claude forgets.

Summary

Hooks are Claude Code's automation layer. The most useful combos:

  1. afterFileWrite → prettier + eslint (keeps code clean without reminders)
  2. afterSessionEnd → test suite (catches regressions immediately)
  3. beforeToolRun → audit log (understand what's happening in long sessions)
  4. afterSessionEnd → self-healing script (autonomous fix loops)

Start with the formatter hook. Once you've run a session without manually formatting anything, you'll add the rest.

Top comments (0)