codex-systematic-debugging

---
name: codex-systematic-debugging
description: Use for bugs, test failures, broken behavior, or unexpected results; enforces 4-phase root-cause debugging before fixes.
load_priority: on-demand
---

## TL;DR
4-phase process: Root Cause Investigation → Pattern Analysis → Hypothesis & Testing → Implementation. No fixes without root cause. 3+ failed fixes = question architecture. Use `$root-cause` or `$trace` to activate.

# Systematic Debugging

## Activation

1. Activate on `$codex-systematic-debugging`, `$root-cause`, or `$trace`.
2. Activate when encountering any bug, test failure, or unexpected behavior.
3. Activate when `codex-workflow-autopilot` routes to `debug` or `fix` workflow.
4. Activate when `codex-intent-context-analyzer` detects debug intent.
5. Activate when previous fix attempts failed.

**Announce at start:** "I'm using codex-systematic-debugging to investigate root cause."

## The Iron Law

```
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
```

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

**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.**

## 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

**Don't skip when:**
- Issue seems simple (simple bugs have root causes too)
- You're in a hurry (rushing guarantees rework)
- Deadline is tight (systematic is faster than thrashing)

## 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 (CI → build → signing, API → service → database):**

   **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
   ```

   **Example (multi-layer system):**
   ```bash
   # Layer 1: Environment
   echo "=== ENV check ==="
   echo "DB_HOST: ${DB_HOST:+SET}${DB_HOST:-UNSET}"

   # Layer 2: Application config
   echo "=== Config loaded ==="
   node -e "console.log(require('./config').database)"

   # Layer 3: Connection
   echo "=== DB connection test ==="
   node -e "require('./db').ping().then(r => console.log(r))"

   # Layer 4: Query
   echo "=== Query test ==="
   node -e "require('./db').query('SELECT 1').then(r => console.log(r))"
   ```

   **This reveals:** Which layer fails (env → config ✓, config → connection ✗)

5. **Trace Data Flow**

   **WHEN error is deep in call stack:**

   See `references/root-cause-tracing.md` for the complete backward tracing technique.

   **Quick version:**
   - Where does bad value originate?
   - What called this with 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**
   - Locate similar working code in same codebase
   - What works that's similar to what's broken?

2. **Compare Against References**
   - If implementing pattern, read reference implementation COMPLETELY
   - Don't skim — read every line
   - Understand the pattern fully before applying

3. **Identify Differences**
   - What's different between working and broken?
   - List every difference, however small
   - Don't assume "that can't matter"

4. **Understand Dependencies**
   - What other components does this need?
   - What settings, config, environment?
   - What assumptions does it make?

### Phase 3: Hypothesis and Testing

**Scientific method:**

1. **Form Single Hypothesis**
   - State clearly: "I think X is the root cause because Y"
   - Write it down
   - Be specific, not vague

2. **Test Minimally**
   - Make the SMALLEST possible change to test hypothesis
   - One variable at a time
   - Don't fix multiple things at once

3. **Verify Before Continuing**
   - Did it work? Yes → Phase 4
   - Didn't work? Form NEW hypothesis
   - DON'T add more fixes on top

4. **When You Don't Know**
   - Say "I don't understand X"
   - Don't pretend to know
   - Ask for help
   - Research more

### Phase 4: Implementation

**Fix the root cause, not the symptom:**

1. **Create Failing Test Case**
   - Simplest possible reproduction
   - Automated test if possible
   - Use `codex-test-driven-development` skill for writing proper failing tests
   - MUST have before fixing

2. **Implement Single Fix**
   - Address the root cause identified
   - ONE change at a time
   - No "while I'm here" improvements
   - No bundled refactoring

3. **Verify Fix**
   - Test passes now?
   - No other tests broken?
   - Issue actually resolved?
   - Run `$gate` or `$check` for full verification

4. **If Fix Doesn't Work**
   - STOP
   - Count: How many fixes have you tried?
   - If < 3: Return to Phase 1, re-analyze with new information
   - **If ≥ 3: STOP and question the architecture (Phase 4.5 below)**
   - DON'T attempt Fix #4 without architectural discussion

### Phase 4.5: Question Architecture (3+ Failed Fixes)

**Pattern indicating architectural problem:**
- Each fix reveals new shared state/coupling/problem in different place
- Fixes require "massive refactoring" to implement
- Each fix creates new symptoms elsewhere

**STOP and question fundamentals:**
- Is this pattern fundamentally sound?
- Are we "sticking with it through sheer inertia"?
- Should we refactor architecture vs. continue fixing symptoms?

**Discuss with the human before attempting more fixes.**

This is NOT a failed hypothesis — this is a wrong architecture.

## Red Flags — STOP and Follow Process

If you catch yourself thinking:
- "Quick fix for now, investigate later"
- "Just try changing X and see if it works"
- "Add multiple changes, run tests"
- "Skip the test, I'll manually verify"
- "It's probably X, let me fix that"
- "I don't fully understand but this might work"
- "Pattern says X but I'll adapt it differently"
- "Here are the main problems: [lists fixes without investigation]"
- Proposing solutions before tracing data flow
- **"One more fix attempt" (when already tried 2+)**
- **Each fix reveals new problem in different place**

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

**If 3+ fixes failed:** Question the architecture (see Phase 4.5)

## Common Rationalizations

| Excuse | Reality |
|--------|---------|
| "Issue is simple, don't need process" | Simple issues have root causes too. Process is fast for simple bugs. |
| "Emergency, no time for process" | Systematic debugging is FASTER than guess-and-check thrashing. |
| "Just try this first, then investigate" | First fix sets the pattern. Do it right from the start. |
| "I'll write test after confirming fix works" | Untested fixes don't stick. Test first proves it. |
| "Multiple fixes at once saves time" | Can't isolate what worked. Causes new bugs. |
| "Reference too long, I'll adapt the pattern" | Partial understanding guarantees bugs. Read it completely. |
| "I see the problem, let me fix it" | Seeing symptoms ≠ understanding root cause. |
| "One more fix attempt" (after 2+ failures) | 3+ failures = architectural problem. Question pattern, don't fix again. |

## Quick Reference

| Phase | Key Activities | Success Criteria |
|-------|---------------|------------------|
| **1. Root Cause** | Read errors, reproduce, check changes, gather evidence | Understand WHAT and WHY |
| **2. Pattern** | Find working examples, compare | Identify differences |
| **3. Hypothesis** | Form theory, test minimally | Confirmed or new hypothesis |
| **4. Implementation** | Create test, fix, verify | Bug resolved, tests pass, gate green |

## CodexAI Integration

### Gate Integration

After Phase 4 fix, verify through quality gate:

```bash
# Quick verification
python codex-execution-quality-gate/scripts/auto_gate.py --mode quick --project-root <repo>

# Smart test selection
python codex-execution-quality-gate/scripts/smart_test_selector.py --project-root <repo>
```

### Workflow Integration

| Alias | Behavior |
|-------|----------|
| `$debug` | Activates `.workflows/debug.md` + this skill |
| `$root-cause` | Jump directly to Phase 1 |
| `$trace` | Jump to data flow tracing (Phase 1, Step 5) |

## Supporting Techniques

Available in `references/` directory:

- **`root-cause-tracing.md`** — Trace bugs backward through call stack to find original trigger
- **`defense-in-depth.md`** — Add validation at multiple layers after finding root cause
- **`condition-based-waiting.md`** — Replace arbitrary timeouts with condition polling

## Smallest Complete Change While Fixing

After the root cause is known, choose the fix with the [6-rung precision ladder](../codex-reasoning-rigor/references/precision-ladder.md).

- Grep every caller before changing a signature or patching a symptom. Fix the shared function once. A check added to only one caller fails when the second caller runs.
- Moved code keeps its validation.
- Do not cut trust-boundary validation, error handling that prevents data loss, security controls, accessibility, hardware or sensor calibration, or an explanation the user explicitly requested.
- If the fix is intentionally bounded, leave a code comment in the form `shortcut: <ceiling>, <when to upgrade>`.

## Related Skills

- **`codex-test-driven-development`** — For creating failing test case (Phase 4, Step 1)
- **`codex-execution-quality-gate`** — Verify fix via `$gate` before claiming success

## Real-World Impact

From debugging sessions:
- Systematic approach: 15-30 minutes to fix
- Random fixes approach: 2-3 hours of thrashing
- First-time fix rate: 95% vs 40%
- New bugs introduced: Near zero vs common

• SKILL.md 11 KB
• agents/openai.yaml 1 KB
• references/condition-based-waiting.md 4 KB
• references/defense-in-depth.md 3 KB
• references/root-cause-tracing.md 4 KB