ClaudeHack

Popular Hacks

Most helpful workflows, ranked by community

  1. 1.

    Schedule an early Claude Code run so your usage window resets around lunch instead of mid-afternoon.

    1 point·12 hours ago·Usage & Limits·easy·1 comment
  2. 2.

    Proactively run `/compact` with focus instructions so summaries keep the work that matters instead of stale debugging.

    0 points·12 hours ago·Context Management·easy·discuss
  3. 3.

    When Claude repeats a project gotcha, end your prompt with an instruction to write a CLAUDE.md rule so it never happens again.

    0 points·12 hours ago·Claude Code / CLAUDE.md·easy·discuss
  4. 4.

    Spin up a subagent for codebase search or verification so only the conclusion returns to your main context.

    0 points·12 hours ago·MCP / Agents·medium·discuss
  5. 5.

    Use `claude --worktree` (or git worktrees) so multiple agents edit isolated checkouts without colliding.

    0 points·12 hours ago·Git & GitHub / Pull Requests·medium·discuss
  6. 6.

    Trim project memory to under ~200 lines so Claude follows critical rules instead of drowning them in noise.

    0 points·12 hours ago·Claude Code / CLAUDE.md·easy·discuss
  7. 7.

    Write the plan in one session, then open a fresh Claude with no context and ask it to review the plan like a staff engineer.

    0 points·12 hours ago·Claude Code / CLAUDE.md·easy·discuss
  8. 8.

    Double-Esc /rewind back to after useful file reads, then re-prompt with what you learned—without the failed approach still in context.

    0 points·12 hours ago·Context Management·easy·discuss
  9. 9.

    Shift specialized playbooks into on-demand skills so every session does not pay for instructions you rarely need.

    0 points·12 hours ago·Terminal / Productivity / Cost Optimization·medium·discuss
  10. 10.

    Save repeatable workflows as SKILL.md (or .claude/commands) so you slash-invoke consistent PR reviews, releases, or checklists.

    0 points·12 hours ago·Terminal / Productivity / Cost Optimization·medium·discuss
  11. 11.

    Use /init to generate a starter CLAUDE.md, then delete anything inaccurate or obvious before committing.

    0 points·12 hours ago·Claude Code / CLAUDE.md·easy·discuss
  12. 12.

    Cycle into plan mode (Shift+Tab) so Claude explores and proposes an approach for approval before editing.

  13. 13.

    Check in project settings so every teammate gets the same allow/deny rules, hooks, and env defaults without redoing /permissions.

    0 points·12 hours ago·Claude Code / CLAUDE.md·intermediate·discuss
  14. 14.

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

    0 points·12 hours ago·Testing / Debugging·hard·discuss
  15. 15.

    Create a skill that forces a red→green verification loop so Claude cannot claim done without running the suite.

    0 points·12 hours ago·Testing / Debugging·medium·discuss
  16. 16.

    Use /clear between unrelated tasks so leftover debugging does not bias the next feature.

    0 points·12 hours ago·Context Management·easy·discuss
  17. 17.

    Add a top-level cache_control ephemeral flag so growing conversation prefixes reuse cached tokens and cut API cost and latency.

    0 points·12 hours ago·Usage & Limits·intermediate·discuss
  18. 18.

    Turn off MCP servers unrelated to the current project—their tool schemas still consume context at session start.

    0 points·12 hours ago·MCP / Agents·easy·discuss
  19. 19.

    Build slash skills that accept issue numbers, branch names, or formats via $ARGUMENTS / $0 so one command covers many cases.

  20. 20.

    Run /context to break down token consumers—CLAUDE.md, MCP tools, conversation—and prune the expensive ones.

    0 points·12 hours ago·Context Management·easy·discuss
  21. 21.

    Add the GitHub MCP server so Claude can cross-reference issues, PRs, and repo state without leaving the session.

    0 points·12 hours ago·Git & GitHub / Pull Requests·medium·discuss
  22. 22.

    Define custom subagents with `isolation: worktree` so delegated edits happen on a temporary branch checkout.

    0 points·12 hours ago·MCP / Agents·medium·discuss
  23. 23.

    Mark deploy/ship/destructive skills so only an explicit /command runs them—Claude cannot auto-trigger them mid-session.

  24. 24.

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

    0 points·12 hours ago·Terminal / Productivity / Cost Optimization·medium·discuss