Паттерн ревью субагентом

[do-work] → [delegate-review] → [check-result] → pass → [next]
                                      ↓
                                    fail → [fix-issues] → [do-work]

{
  "type": "agent-directive",
  "id": "delegate-review",
  "directive": "Delegate review to subagent using Task tool.\n\n1) Pass ONLY necessary information:\n   - File paths to review\n   - Success criteria\n   - Context directory\n\n2) Agent delegation rules:\n   - Role clarity: 'YOU ARE reviewer'\n   - Direct commands: 'CHECK' not 'could you check'\n   - Specify files: list exact paths\n   - Demand verification: 'VERIFY by reading files'\n\n3) Save review result to {{review_file_path}}\n\n4) Report findings honestly - if reviewer found issues, report issues_found: yes",
  "completionCondition": "Review delegated, result saved, findings reported",
  "inputSchema": {
    "type": "object",
    "properties": {
      "review_file": {
        "type": "string",
        "description": "Path to saved review file"
      },
      "issues_found": {
        "type": "string",
        "enum": ["yes", "no"],
        "description": "Did reviewer find blocking issues?"
      }
    },
    "required": ["review_file", "issues_found"]
  },
  "connections": { "success": "check-review-result" }
}

YOU ARE plan reviewer. Your assessment determines if we proceed.

READ plan file directly.
CHECK step implementation.
VERIFY by reading actual files.
RETURN blocking issues only.

Pass ONLY:
- File paths to review
- Success criteria
- Relevant context paths

DO NOT pass:
- Your interpretation of quality
- Hints about what you expect
- Explanations of your work

{
  "type": "condition",
  "id": "check-review-result",
  "condition": {
    "operator": "eq",
    "left": { "contextPath": "issues_found" },
    "right": "no"
  },
  "connections": {
    "true": "next-step",
    "false": "fix-issues"
  }
}

{
  "id": "agent-validate-step",
  "directive": "Delegate critical review to subagent.\n\n1) Pass direct access to plan without interpretation\n2) No mentions of 'code was improved/added/fixed'\n3) Pass: file path, step index, changed files, reports directory\n4) Tell which project parts to study for context\n\nAgent prompt:\nYOU ARE plan step gate reviewer.\nYour assessment determines if we proceed.\nREAD plan file directly.\nCHECK step against PREVIOUS and FUTURE steps.\nEvaluate: code quality, errors, plan compliance.\nReturn BLOCKING issues only.\nProvide fix recommendations.",
  "inputSchema": {
    "properties": {
      "agent_review_file": { "type": "string" },
      "agent_issues_found": { "type": "string", "enum": ["да", "нет"] }
    },
    "required": ["agent_review_file", "agent_issues_found"]
  }
}

{
  "directive": "Check if your work meets quality standards.",
  "completionCondition": "Quality check passed"
}

{
  "directive": "Ask subagent to verify the improvements we made."
}

{
  "directive": "Tell the reviewer about all the hard work done and why each decision was made."
}

{
  "inputSchema": {
    "properties": {
      "issues_count": {
        "type": "number",
        "minimum": 0,
        "description": "Number of blocking issues found"
      }
    }
  }
}

{
  "condition": {
    "operator": "eq",
    "left": { "contextPath": "issues_count" },
    "right": 0
  }
}