ClaudeHack

Popular Hacks

Page 2 of 3

  1. 25.

    Every installed skill spends context just being listed, before you invoke anything. Sort the list by cost, then set the ones you never use to name-only.

    0.00 points·1 month ago·Context Management·easy·discuss
  2. 26.

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

    0.00 points·1 month ago·Claude Code / CLAUDE.md·easy·discuss
  3. 27.

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

    0.00 points·1 month ago·Terminal / Productivity / Cost Optimization·easy·discuss
  4. 28.

    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·1 month ago·Terminal / Productivity / Cost Optimization·easy·discuss
  5. 29.

    Declare a Compact Instructions section in CLAUDE.md so both manual /compact and autocompact preserve the project’s critical decisions by default.

    0.00 points·1 month ago·Context Management·easy·discuss
  6. 30.

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

    0.00 points·1 month ago·Claude Code / CLAUDE.md·intermediate·discuss
  7. 31.

    Install the GitHub app and mention @claude in review comments so corrections become durable CLAUDE.md rules for every future session.

    0.00 points·1 month ago·Git & GitHub / Pull Requests·intermediate·discuss
  8. 32.

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

    0.00 points·1 month ago·Testing / Debugging·hard·discuss
  9. 33.

    Auto-compact waits until your context is nearly full, which is well past the point where answer quality starts sliding. Set the window lower and compact while the session is still sharp.

    0.00 points·1 month ago·Context Management·easy·discuss
  10. 34.

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

    0.00 points·1 month ago·Testing / Debugging·medium·discuss
  11. 35.

    Run claude remote-control on your machine, then connect from the Claude mobile app to approve builds, poke CI failures, and keep coding with full local tools.

    0.00 points·1 month ago·Terminal / Productivity / Cost Optimization·easy·discuss
  12. 36.

    A skill that checks a link or reformats a file does not need your session model. Set model, effort and context: fork in the frontmatter so cheap skills stay cheap.

    0.00 points·1 month ago·MCP / Agents·intermediate·discuss
  13. 37.

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

    0.00 points·1 month ago·Context Management·easy·discuss
  14. 38.

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

    0.00 points·1 month ago·Usage & Limits·intermediate·discuss
  15. 39.

    Add a Notification hook that plays a short sound when Claude is idle or waiting on permission so you can multitask without staring at the terminal.

    0.00 points·1 month ago·Terminal / Productivity / Cost Optimization·easy·discuss
  16. 40.

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

    0.00 points·1 month ago·MCP / Agents·easy·discuss
  17. 41.

    "Never add comments" in CLAUDE.md plus "make this readable" in your prompt is a contradiction Claude has to resolve before it writes a line. Find those pairs and pick one.

    0.00 points·1 month ago·Claude Code / CLAUDE.md·easy·discuss
  18. 42.

    Enable /voice and hold Space to speak complex requirements into the prompt instead of typing walls of text.

    0.00 points·1 month ago·Terminal / Productivity / Cost Optimization·easy·discuss
  19. 43.

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

    0.00 points·1 month ago·Terminal / Productivity / Cost Optimization·easy·discuss
  20. 44.

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

    0.00 points·1 month ago·Context Management·easy·discuss
  21. 45.

    When a skill hits an edge case, append it to a gotchas section in that skill rather than to CLAUDE.md. The lesson then loads only when the skill runs.

    0.00 points·1 month ago·MCP / Agents·easy·discuss
  22. 46.

    Use bundled /loop and /schedule skills for recurring health checks, log watches, or periodic repo tasks without external cron wiring.

    0.00 points·1 month ago·Scheduled Tasks / Automation·intermediate·discuss
  23. 47.

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

    0.00 points·1 month ago·Git & GitHub / Pull Requests·medium·discuss
  24. 48.

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

    0.00 points·1 month ago·MCP / Agents·medium·discuss