Ce Debug

Debug and Fix

Find root causes, then fix them. This skill investigates bugs systematically — tracing the full causal chain before proposing a fix — and optionally implements the fix with test-first discipline.

#$ARGUMENTS

Core Principles

1. Investigate before fixing. Do not propose a fix until you can explain the full causal chain from trigger to symptom with no gaps. "Somehow X leads to Y" is a gap.
2. Predictions for uncertain links. When the causal chain has uncertain or non-obvious links, form a prediction — something in a different code path or scenario that must also be true. If the prediction is wrong but a fix "works," you found a symptom, not the cause. When the chain is obvious (missing import, clear null reference), the chain explanation itself is sufficient.
3. One change at a time. Test one hypothesis, change one thing. If you're changing multiple things to "see if it helps," stop — that is shotgun debugging.
4. When stuck, diagnose why — don't just try harder.

Execution Flow

Phase 0: Triage

Parse the input and reach a clear problem statement.

If the input references an issue tracker (GitHub, Linear, Jira, any tracker URL), fetch the issue with the available tool (gh, MCP, or URL fetch) and read the entire thread — the latest comments often supersede the opening description with updated repro steps, narrowed scope, prior failed attempts, or a pivot to a different suspected cause. If the fetch fails, ask the user to paste the issue content. Extract symptoms, expected behavior, reproduction steps, and environment details from the combined thread.

Everything else (stack traces, test paths, error messages, descriptions of broken behavior): the problem statement is the input itself.

Trivial-bug fast-path: When the cause is immediately readable from the input and needs no deep tracing, present the cause and the one-line fix and run Phase 2's Fix it now / Diagnosis only gate before editing — the fast-path saves investigation ceremony, not the user's choice. On fix, run Phase 3's workspace and branch check, apply, and skip to Phase 4's summary. When in doubt, run the full framework; a wrong root cause costs more than the ceremony.

Otherwise, proceed to Phase 1.

Questions:

• Do not ask questions by default — investigate first (read code, run tests, trace errors)
• Only ask when a genuine ambiguity blocks investigation and cannot be resolved by reading code or running tests
• When asking, ask one specific question

Prior-attempt awareness: If the user indicates prior failed attempts ("I've been trying", "keeps failing", "stuck"), ask what they have already tried before investigating. This avoids repeating failed approaches and is one of the few cases where asking first is the right call.

Phase 1: Investigate

1.1 Reproduce the bug

Confirm the bug exists and understand its behavior. Run the test, trigger the error, follow reported reproduction steps — whatever matches the input.

• Browser bugs: use available browser tooling — whatever reproduces the reported behavior.
• Manual setup required: when reproduction needs conditions the agent cannot create alone, document the exact setup steps and guide the user through them.
• Does not reproduce after 2-3 attempts: read references/investigation-techniques.md for intermittent-bug techniques. If it cannot reproduce at all here, document what was tried and what conditions appear missing.
• Writing the reproduction test: follow the project's testing conventions when they exist; otherwise write a minimal isolated test that fails on the bug and passes once fixed, named so the failure message explains the bug.

1.2 Verify environment sanity

Before deep code tracing, confirm the environment is what you think it is:

• Correct branch checked out; no unintended uncommitted changes
• Dependencies installed and up to date (bun install, npm install, bundle install, etc.) — stale node_modules/vendor is a frequent false lead
• Expected interpreter or runtime version (check .tool-versions, .nvmrc, Gemfile, etc. against what's actually active)
• Required env vars present and non-empty
• No stale build artifacts (dist/, .next/, compiled binaries from an earlier branch)
• Dependent local services (database, cache, queue) running at expected versions when the bug plausibly involves them

1.2b Retrieve cross-cutting evidence when needed

Use qmd-knowledge-base when the failing symbol, error, expected behavior, or relevant subsystem is unclear, or when prior reasoning could change the hypothesis. Verify the hypothesis against the live system and source.

1.3 Trace the code path

Trace data flow backward from the symptom to where valid state first became invalid. Read code-shape to form a hypothesis, then verify with observed values — do not theorize from code alone.

Concrete recipe:

1. Read the stack trace bottom-to-top, opening each frame's source. The bottom frame is the symptom; the root cause is somewhere upstream.
2. Identify the first frame where the input data is already invalid — that's the upper bound on where to look.
3. Instrument the boundaries around that frame: targeted log/print statements, debugger breakpoints, or test assertions that capture actual values at function entry/exit. Assumed values lie; observed values don't.
4. Walk the boundaries until valid input becomes invalid output. That transition is the root cause site.

Do not stop at the first function that looks wrong — the root cause is where bad state originates, not where it is first observed.

As you trace: check recent changes in the files you are reading (git log --oneline -10 -- [file]); if the bug looks like a regression, use git bisect (see references/investigation-techniques.md); and pull additional evidence from whatever observability the project has — error trackers, application logs, browser console, database state.

Phase 2: Root Cause

Reminder: investigate before fixing. Do not propose a fix until you can explain the full causal chain from trigger to symptom with no gaps.

Read references/anti-patterns.md before forming hypotheses. As a load-time preview of the rationalizations it covers, stop and re-examine if the internal monologue contains any of these:

• "Quick fix for now, investigate later"
• "This should work" (without a tested prediction)
• "Let me just try..." (without a hypothesis)

These phrases mark mode-drift toward symptom patches, not progress on the root cause. ("One more attempt" after a failed fix and "works on my machine" are covered at the points they fire — Phase 3's invalidation step and the Smart Escalation table below.)

Assumption audit (before hypothesis formation): List the concrete "this must be true" beliefs your understanding depends on — the framework behaves as expected here, this function returns what its name implies, the config loads before this runs, the caller passes a non-null value, the database is in the state the test implies. For each, mark verified (you read the code, checked state, or ran it) or assumed. Assumptions are the most common source of stuck debugging. Many "wrong hypotheses" are actually correct hypotheses tested against a wrong assumption.

Form hypotheses ranked by likelihood. For each, state:

• What is wrong and where (file:line)
• At least one concrete observation that supports it — a runtime variable value, a log line, an instrumented boundary capture, a behavior delta against a working comparison case, or a specific code reference. "X seems off" is not evidence; "X equals null at line 42 because Y was never initialized in the constructor path that runs under condition Z" is. Hypotheses without grounding observations are theorizing — go back to Phase 1 and instrument.
• The causal chain: how the trigger leads to the observed symptom, step by step
• For uncertain links in the chain: a prediction — something in a different code path or scenario that must also be true if this link is correct

When the causal chain is obvious and has no uncertain links (missing import, clear type error, explicit null dereference), the chain explanation itself is the gate — no prediction required. Predictions are a tool for testing uncertain links, not a ritual for every hypothesis.

Before forming a new hypothesis, review what has already been ruled out and why.

Causal chain gate: Do not proceed to Phase 3 until you can explain the full causal chain — from the original trigger through every step to the observed symptom — with no gaps. The user can explicitly authorize proceeding with the best-available hypothesis if investigation is stuck.

Reminder: if a prediction was wrong but the fix appears to work, you found a symptom. The real cause is still active.

Present findings

Once the root cause is confirmed, present:

• The root cause (causal chain summary with file:line references)
• The proposed fix and which files would change
• Which tests to add or modify to prevent recurrence (specific test file, test case description, what the assertion should verify)
• Whether existing tests should have caught this and why they did not

Then offer next steps.

Use the platform's blocking question tool (see ../ce-conventions/SKILL.md). Never silently skip the question.

Options to offer:

1. Fix it now — proceed to Phase 3
2. Diagnosis only — I'll take it from here — skip the fix, proceed to Phase 4's summary, and end the skill
3. Rethink the design (/ce-brainstorm) — only when the root cause reveals a design problem (see below)

Do not assume the user wants action right now. The test recommendations are part of the diagnosis regardless of which path is chosen.

When to suggest brainstorm: Only when investigation reveals the bug cannot be properly fixed within the current design — the design itself needs to change. Concrete signals observable during debugging:

• The root cause is a wrong responsibility or interface, not wrong logic. The module should not be doing this at all, or the boundary between components is in the wrong place. (Observable: the fix requires moving responsibility between modules, not correcting code within one.)
• The requirements are wrong or incomplete. The system behaves as designed, but the design does not match what users actually need. The "bug" is really a product gap. (Observable: the code is doing exactly what it was written to do — the spec is the problem.)
• fix is a workaround. You can patch the symptom, but cannot articulate a clean fix because the surrounding code was built on an assumption that no longer holds. (Observable: you keep wanting to add special cases or flags rather than a direct correction.)

Do not suggest brainstorm for bugs that are large but have a clear fix — size alone does not make something a design problem.

Smart escalation

If 2-3 hypotheses are exhausted without confirmation, diagnose why:

Parallel investigation option: When hypotheses are evidence-bottlenecked across clearly independent subsystems, dispatch read-only sub-agents in parallel, each with an explicit hypothesis and structured evidence-return format. No code edits by sub-agents, and skip this when hypotheses depend on each other's outcomes. If the platform does not support parallel sub-agent dispatch, run the same hypothesis probes sequentially in ranked-likelihood order instead — the parallelism is a latency optimization, not a correctness requirement.

Present the diagnosis to the user before proceeding.

Phase 3: Fix

Reminder: one change at a time. If you are changing multiple things, stop.

If the user chose "Diagnosis only" at the end of Phase 2, skip this phase and go straight to Phase 4 for the summary — the skill's job was the diagnosis. If they chose "Rethink the design", control has transferred to /ce-brainstorm and this skill ends.

Workspace and branch check: Before editing files:

• Check for uncommitted changes (git status). If the user has unstaged work in files that need modification, confirm before editing — do not overwrite in-progress changes.
• If the current branch is the default branch, ask whether to create a feature branch first using the platform's blocking question tool. Default to creating one; derive a name from the bug and run git checkout -b <name>. On any other branch, proceed.

Test-first:

1. Write a failing test that captures the bug (or use the existing failing test)
2. Verify it fails for the right reason — the root cause, not unrelated setup
3. Implement the minimal fix — address the root cause and nothing else. Do not bundle drive-by refactors, formatting, or unrelated cleanup into a bug-fix change; those belong in separate commits.
4. Verify the test passes
5. Run the broader test suite for regressions
6. Self-review the diff before declaring the fix done: read every changed line and check for style violations, missed edge cases, regressions in adjacent behavior, and missing test coverage for the fix. For non-trivial fixes (multiple files, risky surface area), also run the harness's lightweight review tool (e.g., /review in Claude Code; the equivalent in other harnesses) — not the full ce-review multi-agent flow, which is PR-tier and over-sized for a single bug fix.

On a failed fix: return to Phase 2 and explicitly invalidate the current hypothesis before forming a new one. State out loud what evidence ruled out the prior hypothesis, then form a new one with its own grounding observation and prediction. Do not retry variants of the same theory ("maybe it was the other branch", "let me also catch this case") — that is the rationalization spiral, not iteration.

3 failed fix attempts = smart escalation. Diagnose using the same table from Phase 2. If fixes keep failing, the root cause identification was likely wrong. Return to Phase 2.

Conditional defense-in-depth (trigger: grep for the root-cause pattern found it in 3+ other files, OR the bug would have been catastrophic if it reached production): Read references/defense-in-depth.md for the four-layer model (entry validation, invariant check, environment guard, diagnostic breadcrumb) and choose which layers apply. Skip when the root cause is a one-off error with no realistic recurrence path.

Conditional post-mortem (trigger: the bug was in production, OR the pattern appears in 3+ locations): Analyze how this was introduced and what allowed it to survive. Note any systemic gap or repeated pattern found — it informs Phase 4's decision on whether to offer learning capture.

Phase 4: Handoff

Structured summary — always write this first:

## Debug Summary
**Problem**: [What was broken]
**Root Cause**: [Full causal chain, with file:line references]
**Recommended Tests**: [Tests to add/modify to prevent recurrence, with specific file and assertion guidance]
**Fix**: [What was changed — or "diagnosis only" if Phase 3 was skipped]
**Prevention**: [Test coverage added; defense-in-depth if applicable]
**Confidence**: [High/Medium/Low]

If Phase 3 was skipped (user chose "Diagnosis only" in Phase 2), stop after the summary — the user already told you they were taking it from here. Do not prompt.

If Phase 3 ran: on a branch this skill created, briefly preview what will be committed (the preview exists so the user can interrupt, not as a blocking question), then run /git-commit-push-pr — including the tracker's auto-close syntax in the place that tracker parses it (e.g., Fixes #N in the PR body for GitHub, Smart Commits in the commit message for Jira) — and surface the PR URL. Honor any explicit user or repo instruction that conflicts with auto-PR. On a pre-existing branch, ask via the platform's blocking question tool (see ../ce-conventions/SKILL.md): commit and PR, local commit only, or stop here.

After a PR is open: consider offering learning capture

Most bugs are localized mechanical fixes (typo, missed null check, missing import) where the only "lesson" is the bug itself. Compounding those clutters .ai/solutions/ without adding value. Decide which path applies:

• Skip silently when the fix is mechanical and there's no generalizable insight. Default to this when in doubt.
• Offer neutrally when the lesson can be stated in one sentence — e.g., "X.foo() returns T | undefined when Y, not just T", or "the diagnostic path was non-obvious and worth recording." If you cannot articulate the lesson, skip rather than offer.
• Lean into the offer when the pattern appears in 3+ locations OR the root cause reveals a wrong assumption about a shared dependency, framework, or convention that other code is likely to repeat.

When offering, use the blocking question tool described above. If the user accepts, run /ce-compound, then commit the resulting learning doc to the same branch and push so the open PR picks up the new commit.