ClaudeHack

#security

5 hacks

  1. 1.
    Enable Bash sandboxing to auto-allow contained commands(code.claude.com)

    Turn on `/sandbox` so OS-level filesystem and network boundaries replace many per-command Bash prompts.

    0.00 points·14 hours ago·Terminal / Productivity / Cost Optimization·medium·discuss
  2. 2.
    Prefer auto mode over --dangerously-skip-permissions(claude.com)

    Enable auto mode so a classifier approves safe tool calls and blocks destructive ones — fewer prompts without a full permission bypass.

    0.00 points·14 hours ago·Terminal / Productivity / Cost Optimization·easy·discuss
  3. 3.
    Block dangerous Bash with a PreToolUse hook(code.claude.com)

    Add a deterministic PreToolUse hook that rejects destructive shell patterns before Claude can run them.

    0.00 points·14 hours ago·Testing / Debugging·hard·discuss
  4. 4.
    Run /fewer-permission-prompts to build an allowlist from your own transcripts(youtube.com)

    Instead of guessing which commands to allowlist or giving up and skipping permissions entirely, let Claude read your past sessions and propose the rules you have already been approving.

    0.00 points·14 hours ago·Terminal / Productivity / Cost Optimization·easy·discuss
  5. 5.
    Allowlist safe Bash commands to stop approval fatigue(code.claude.com)

    Use /permissions to allowlist read-only and trusted commands so you stop mindlessly clicking Approve.

    0.00 points·14 hours ago·Terminal / Productivity / Cost Optimization·medium·discuss