git:20260728.312fef9 to git:20260802.aa3bfed

---

name: recipe-diagnose

description: "Investigate problem, verify findings, and derive solutions through structured diagnosis."

---

## 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

**Execution Plan Gate**: Before substantive work, call `update_plan` with first "Map active rules to this task", then problem structuring, investigation, verification, and solution, and final "Verify outputs and rule adherence". While work remains, keep exactly one step `in_progress`; after final report evidence exists, mark every step `completed`.

## 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 |

### 0.2 Information Supplementation for Change Failures

- What was changed (cause change)

- What broke (affected area)

- Relationship between both (shared components, etc.)

## Diagnosis Flow Overview

```

Problem -> investigator -> verifier -> solver --+

^ |

+-- coverage insufficient -----+

(max 2 iterations)

coverage sufficient -> Report

```

**Context Separation**: Pass only structured output to each step. Each step starts fresh with the data only.

## Execution Steps

Execute the registered steps:

### Step 1: Investigation (investigator)

Spawn investigator agent with the following prompt:

```text

Comprehensively collect information related to the following phenomenon.

Phenomenon: [Problem reported by user]

- what changed

- what broke

- what both areas share

```

**Expected output**: Evidence matrix, path map, failure points, comparison analysis results, list of unexplored areas, investigation limitations

### Step 2: Investigation Quality Check

Review investigation output:

**Quality Check** (verify output contains the following):

- [ ] `comparisonAnalysis` is present and `normalImplementation` is non-null, or explicitly states that no working implementation was found

- [ ] `pathMap` is present with ordered nodes or explicit unknown segments

- [ ] causalChain for each failure point reaches a stop condition

- [ ] causeCategory for each failure point

- [ ] `investigationSources` covers at least 3 distinct source types

- [ ] each failure point has supporting evidence with a concrete source

**If quality insufficient**: MUST re-spawn investigator agent specifying the missing items and include the previous investigation output for context

ENFORCEMENT: Proceeding to verifier with incomplete investigation data produces unreliable conclusions.

Proceed to verifier once quality is satisfied.

### Step 3: Verification (verifier)

Spawn verifier agent: "Verify the following investigation results. Investigation results: [Investigation output]"

**Expected output**: Path coverage findings, independent failure-point evaluation, final conclusion, coverageAssessment/finalStatus

**Coverage Criteria**:

- **sufficient**: No major uncovered boundary affects solution selection or implementation

- **partial**: Some uncertainty exists but a bounded next investigation is possible

- **insufficient**: Fundamental information gap exists on the relevant path

### Step 4: Solution Derivation (solver)

Spawn solver agent: "Derive solutions based on the following verified conclusion. Failure points: [verifier's conclusion.confirmedFailurePoints]. Failure-point relationships: [verifier's conclusion.failurePointRelationships]. Coverage assessment: [verifier's conclusion.coverageAssessment]. Final status: [verifier's conclusion.finalStatus]. Impact analysis: [investigator output impactAnalysis]."

**Expected output**: Multiple solutions (at least 3), tradeoff analysis, recommendation and implementation steps, residual risks

**Completion condition**: `coverageAssessment=sufficient` and `finalStatus=ready_for_solution`

**When not reached**:

1. Return to Step 1 with uncertainties identified by solver as investigation targets

2. Maximum 2 additional investigation iterations

3. After 2 iterations without reaching sufficient coverage, present user with options:

- Continue additional investigation

- Execute solution at current coverage level

### Step 5: Final Report Creation

**Prerequisite**: sufficient coverage achieved

After diagnosis completion, report to user in the following format:

```

## Diagnosis Result Summary

### Identified Failure Points

[Failure point list from verification results]

- Failure-point relationships: [independent/upstream_of/downstream_of/amplifies/same_boundary]

### Verification Process

- Investigation scope: [Scope confirmed in investigation]

- Additional investigation iterations: [0/1/2]

- Coverage assessment: [sufficient/partial/insufficient]

### Recommended Solution

[Solution derivation recommendation]

Rationale: [Selection rationale]

### Implementation Steps

1. [Step 1]

2. [Step 2]

...

### Alternatives

[Alternative description]

### Residual Risks

[solver's residualRisks]

### Post-Resolution Verification Items

- [Verification item 1]

- [Verification item 2]

```

## Completion Criteria

- [ ] Spawned investigator and obtained evidence matrix, comparison analysis, and causal tracking

- [ ] Performed investigation quality check and re-ran if insufficient

- [ ] Spawned verifier and obtained coverage assessment

- [ ] Spawned solver

- [ ] Achieved sufficient coverage (or obtained user approval after 2 additional iterations)

- [ ] Presented final report to user