~ / rigs / malaysherasia-ai / claude-never-again

malaysherasia-ai/claude-never-again

Your coding agent keeps repeating the same bug. never-again turns each fix into a hook that blocks the mistake before it happens, or one short line in LESSONS.md when a script can't make the call. Claude Code, Codex, Gemini CLI, Copilot, An

↗ GitHub ★ 1 MIT updated 15d ago project Claude Code
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~246 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
2/5
Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit malaysherasia-ai/claude-never-again/.claude ./rig-claude-never-again  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit malaysherasia-ai/claude-never-again/.claude/skills/never-again .claude/skills/never-again

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/na/dispatch"
          }
        ]
      }
    ]
  }
}

Skills (1)

Hooks (3)

eventmatcherruns
PostToolUseBash"$CLAUDE_PROJECT_DIR"/.claude/hooks/na/_after.sh
PostToolUseFailureBash"$CLAUDE_PROJECT_DIR"/.claude/hooks/na/_after.sh
PreToolUseBash"$CLAUDE_PROJECT_DIR"/.claude/hooks/na/dispatch

Similar rigs

copied ✓