recipe-diagnose

Required Skills [LOAD BEFORE EXECUTION]

1. [LOAD IF NOT ACTIVE] ai-development-guide — AI development patterns
2. [LOAD IF NOT ACTIVE] coding-rules — coding standards
3. [LOAD IF NOT ACTIVE] llm-friendly-context — clear prompts, handoffs, and generated artifacts

Spawn rule: every spawn_agent call uses fork_turns="none" so the subagent receives only the task message and explicitly provided context.

Context: Diagnosis flow to identify concrete failure points and present solutions

Target problem: $ARGUMENTS

Orchestrator Definition

Execution Method:

• Investigation -> Spawn investigator agent
• Verification -> Spawn verifier agent
• Solution derivation -> Spawn solver agent

The orchestrator structures the reported problem, coordinates the three specialist stages, evaluates their results, and passes only the context needed by the next stage.

Execution Plan: Reuse the active execution plan. When the workflow has multiple dependent actions and no plan exists, create one that tracks them through final verification. Complete a plan step after verifying its result; start a dependent step after its prerequisites are satisfied.

Step 0: Problem Structuring (Before spawning investigator)

0.1 Problem Type Determination

Type	Criteria
Change Failure	Indicates some change occurred before the problem appeared
New Discovery	No relation to changes is indicated

If uncertain, keep the type provisional and let repository history and investigation evidence resolve it.

0.2 Information Supplementation for Change Failures

For change failures, resolve the following from the supplied report and repository evidence when available:

• What was changed (cause change)
• What broke (affected area)
• Relationship between both (shared components, etc.)

Carry unresolved details into the investigator prompt as investigation targets and continue.

Diagnosis Flow Overview

Problem -> investigator -> verifier
verifier needs_more_investigation -> investigator while new evidence can change coverage
verifier ready_for_solution -> solver
solver recommendation -> Report
solver null recommendation -> investigator while new evidence can change the result
evidence saturated before recommendation -> unresolved Report