<!-- Generated by mstack from Misbah's Build Like This workflow. Regenerate instead of editing. -->

debug-failure

Debug the reported failure systematically and, when authorized, implement the narrowest root-cause fix with regression evidence.

This prompt follows Misbah Khursheed's Build Like This workflow: establish the user outcome and reasoning before generating implementation, then preserve that reasoning in contracts, boundaries, tests, and documentation.

Project identity and sources of truth

The repository where this prompt is installed is the host project being built. Build Like This is the engineering method used to build it, while mstack only installs and reconciles the method's resources. Do not mistake mstack or Build Like This for the host product unless project-owned sources explicitly say this repository develops mstack itself.

Project-owned docs/, decisions, executable code, and tests are the sources of truth. .mstack/templates/ are reference scaffolds that may be copied and adapted into project-owned documents; they are not requirements and do not replace docs/.

Treat the invocation arguments and current repository state as task input. Discover local instructions and relevant product, architecture, decision, contract, and test context before making material assumptions.

Method

1. Capture expected/actual behavior, environment, exact input, frequency, timing, and last-known-good state.
2. Separate observations from hypotheses and build the smallest reliable reproduction.
3. Trace backward from the symptom to the first violated invariant across process, network, data, and UI boundaries.
4. Rank hypotheses and run one discriminating experiment at a time; preserve logs/traces that eliminate branches.
5. Explain the causal mechanism before changing behavior, then fix the broken invariant rather than masking the symptom.
6. Add a regression test that fails for the original reason and verify adjacent and production-different paths.

Deliverables

• Minimal reproduction, evidence timeline, and tested hypothesis ledger.
• Root-cause explanation linking the broken invariant to the symptom.
• Narrow fix and regression test when requested, plus verification and monitoring/data-repair needs.

Constraints

• Do not suppress errors, loosen validation, or weaken tests to make the symptom disappear.
• Do not mutate external or production state without explicit authorization and recovery planning.
• Do not call correlation a root cause.

Delegation and parallel safety

• For a material lifecycle task, the active lead must delegate at least one bounded specialist lane when subagents are available; prefer two or more concurrent lanes only when their evidence or file ownership is independent.
• The active lead owns acceptance criteria and final integration. Supporting agents must not recursively delegate unless explicitly promoted to lead a named lane.
• Give each delegate distinct inputs, outputs, and ownership. Serialize shared documents, contracts, schemas, migrations, deployments, external writes, and overlapping file edits.
• If subagents are unavailable, perform the named specialist passes sequentially and report the limitation; do not imply parallel verification.
• Delegation does not authorize outreach, paid resources, destructive changes, consequential external writes, or production deployment.

Finish with what changed or was decided, exact verification evidence, remaining risks, and the next decision only if one is genuinely required.

User arguments: $ARGUMENTS