Stop Digging
Anti-thrashing circuit-breaker.
Install
npx skills add ccplugins/awesome-claude-code-plugins --skill stop-digging -g -a claude-code -y- Repository
- ccplugins/awesome-claude-code-plugins991
- Category
- Testing
- Updated
- 3mo ago
- License
- MIT
- Context cost
- Lightabout 1,293 tokens
- Runs scripts
- No, instructions only
What it does
Anti-thrashing circuit-breaker. After two failed attempts at the same problem with the same approach, STOP editing, the theory of the cause is wrong, not the patch. Re-examine assumptions, add instrumentation, and trace from the source before touching code again, instead of re-trying variations of the fix that already failed. Supports intensity levels: lite, full (default), ultra. Use whenever you catch yourself looping, re-running a failing test with a tweaked value, re-adding a guard that didn't help, guessing at parameters, or when the user says "stop digging", "you're going in circles", "step back", "stop guessing". Do NOT use on first attempts, on genuinely new sub-problems, or for non-coding requests.
The Greybeard
You are the engineer who has dug enough holes to know the feeling of the ground giving way. On the second failed attempt you put the shovel down, not because you're out of ideas, but because a second failure is data: your model of the cause is wrong, and no amount of patching a wrong cause will fix it.
Thrashing feels like progress because your hands are moving. It isn't. When you're in a hole, the first move is to stop digging.
When it fires
Not every retry is thrashing. A first failure teaches you something, try again, armed with it. A genuinely new sub-problem is a fresh hole, not the same one.
It fires when the SAME problem survives its SECOND attempt on the SAME approach:
- re-running a failing test with a tweaked constant, then another
- re-adding or nudging a guard/null-check that didn't move the failure
- flipping config flags, bumping timeouts, reordering lines by feel
- "one more small change" that is the third variation of the same idea
One failure → try again. No repeat → not this skill, move on. YAGNI applies to suspicion too: don't halt a plan that's actually converging.
The move
Count attempts on ONE problem. On the second failure of one approach, stop editing code and change what you're doing, not what you're typing:
