systematic-debugging

name	systematic-debugging
description	Investigate root cause before fixing bugs or unexpected behavior. Requires the Mnemosyne knowledge backend through advise and fails closed when it cannot be prepared.
argument-hint	<description of the bug or failure>
allowed-tools	["Read","Write","Edit","Bash","Grep","Glob","Agent"]

Systematic Debugging

Overview

Random fixes waste time and create new bugs. Quick patches mask underlying issues.

Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure.

Violating the letter of this process is violating the spirit of debugging.

Before Starting

Run advise with the error description. Failure to prepare the required knowledge backend is a blocking error, not permission to skip prior-knowledge search.

The Iron Law

NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST

If you haven't completed Phase 1, you cannot propose fixes.

When to Use

Use for ANY technical issue:

• Test failures
• Bugs in production
• Unexpected behavior
• Performance problems
• Build failures
• Integration issues

Use this ESPECIALLY when:

• Under time pressure (emergencies make guessing tempting)
• "Just one quick fix" seems obvious
• You've already tried multiple fixes
• Previous fix didn't work
• You don't fully understand the issue

The Four Phases

You MUST complete each phase before proceeding to the next.

Phase 1: Root Cause Investigation

BEFORE attempting ANY fix:

1. Read Error Messages Carefully

   • Don't skip past errors or warnings
   • They often contain the exact solution
   • Read stack traces completely
   • Note line numbers, file paths, error codes

2. Reproduce Consistently

   • Can you trigger it reliably?
   • What are the exact steps?
   • Does it happen every time?
   • If not reproducible → gather more data, don't guess

3. Check Recent Changes

   • What changed that could cause this?
   • git diff, recent commits
   • New dependencies, config changes
   • Environmental differences

4. Gather Evidence in Multi-Component Systems

   WHEN system has multiple components:

   BEFORE proposing fixes, add diagnostic instrumentation:

   For EACH component boundary:
     - Log what data enters component
     - Log what data exits component
     - Verify environment/config propagation
     - Check state at each layer
   
   Run once to gather evidence showing WHERE it breaks
   THEN analyze evidence to identify failing component
   THEN investigate that specific component
   

5. Trace Data Flow

   When error is deep in call stack:

   • Where does the bad value originate?
   • What called this with the bad value?
   • Keep tracing up until you find the source
   • Fix at source, not at symptom

Phase 2: Pattern Analysis

Find the pattern before fixing:

1. Find working examples of similar code in the same codebase
2. Read reference implementations completely — don't skim
3. List every difference between working and broken code
4. Identify all dependencies, config, environment assumptions

Phase 3: Hypothesis and Testing

Scientific method:

1. Form single hypothesis: "I think X is the root cause because Y"
2. Test minimally: Make the SMALLEST possible change to test the hypothesis
3. One variable at a time: Don't fix multiple things at once
4. Verify before continuing: If it worked → Phase 4. Didn't work → new hypothesis
5. When stuck: Say "I don't understand X" — don't pretend to know

Phase 4: Implementation

Fix the root cause, not the symptom:

1. Create failing test case using the test-driven-development skill — it must exist before fixing

2. Implement single fix addressing the root cause

3. Verify fix: Test passes? No other tests broken? Issue actually resolved?

4. If fix doesn't work:

   • STOP
   • Count: How many fixes have you tried?
   • If < 3: Return to Phase 1 with new information
   • If ≥ 3: STOP and question the architecture

5. If 3+ fixes failed — Question Architecture:

   Pattern indicating architectural problem:

   • Each fix reveals new shared state/coupling/problem elsewhere
   • Fixes require massive refactoring to implement
   • Each fix creates new symptoms elsewhere

   STOP and discuss with user before attempting more fixes. This is not a failed hypothesis — this is a wrong architecture.

Red Flags — STOP and Follow Process

• "Quick fix for now, investigate later"
• "Just try changing X and see if it works"
• "Add multiple changes, run tests"
• "It's probably X, let me fix that"
• "I don't fully understand but this might work"
• "One more fix attempt" (when already tried 2+)
• Each fix reveals a new problem in a different place

ALL of these mean: STOP. Return to Phase 1.

Common Rationalizations

Excuse	Reality
"Issue is simple, don't need process"	Simple issues have root causes too.
"Emergency, no time for process"	Systematic debugging is FASTER than guess-and-check.
"Just try this first, then investigate"	First fix sets the pattern. Do it right from the start.
"Multiple fixes at once saves time"	Can't isolate what worked. Causes new bugs.
"One more fix attempt" (after 2+ failures)	3+ failures = architectural problem. Don't fix again.

Repository command discovery

Before running a check, discover the target repository's commands from AGENTS.md, task runners, manifests, lockfiles, and CI. Prefer the command used by required CI. If sources conflict or no safe command is discoverable, ask the user rather than substituting Athena's own tooling.

Keep the target repository as the current working directory. Resolve scripts/repository_evidence.py against this installed skill directory and invoke that absolute helper path with PATTERN --source-root SOURCE_ROOT to collect the latest ten commits, a diff bounded to that revision window, and matching source locations as JSON. Run the discovered repository-focused test and type-check commands directly through the host execution tool, retaining their complete output as evidence.

After Resolution

Verify with fresh runnable evidence per the evidence-integrity policy before claiming the bug is fixed; rerun the failing reproduction and the repository-defined checks.

Offer to invoke learn when the session produced durable debugging knowledge. An indirect Learn invocation does not authorize its branch, commit, push, or pull-request writes; follow Learn's external-write checkpoint and obtain explicit authority before mutation. Useful lessons include:

• Root cause category and symptoms
• What diagnostic steps revealed it
• The fix pattern
• Any architectural issues uncovered

This prevents the same debugging session from being repeated by another agent.

---

Adapted from obra/superpowers under the MIT License. Copyright (c) 2025 Jesse Vincent.