Debug Mantra

A debugging framework that makes Claude recite a four-step mantra at the start of every debug session, then enforce it. The steps are: reproduce reliably, trace the fail path (debugger first, then knobs, then instrumentation), falsify your hypothesis before testing it, and cross-reference every experiment against a running ledger. It triggers automatically when you mention a bug or paste an error. The discipline is rigid by design. Claude won't let you theorize without a repro, won't let you fix without knowing the fail path, and maintains a breadcrumb log to catch contradictions. Honestly, it's heavy process, but if you've ever spent two hours chasing a ghost because you skipped the boring parts, this keeps you honest.

skills.sh installs: 5K
GitHub stars: 3.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add thananon/9arm-skills --skill debug-mantra --agent claude-code

Installs into .claude/skills of the current project.

Files

Debug Mantra

Four-step discipline for any debug session. Recite verbatim, then apply in order.

Recite this — verbatim, as the first thing in your first response

Mantra:

First is reproducibility. Can the issue be reproduced reliably?

Know the fail path. Debugger first; then source trace + knob enumeration; then in-code instrumentation.

Question your hypothesis. What would disprove it?

Every run is a breadcrumb. Cross-reference all of them.

Then begin work.

1. Reproduce reliably

Build a runnable repro before anything else.

Reliable repro → capture the exact steps, inputs, and environment as a runnable artifact: failing test, curl script, CLI invocation, replay harness.
Flaky repro → the bug is not yet debuggable. Raise the rate first: loop the trigger, parallelise, add stress, narrow timing windows, inject sleeps. 50% flake is debuggable; 1% is not.
No repro at all → stop. Say so explicitly. Ask the user for env access, captured artifacts (HAR, log dump, core), or permission to instrument. Do not proceed to hypothesise.

SKILL.md on GitHub