Back to Details

risk-classification

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Table of Contents

目录

Risk Classification

风险分类

Overview

概述

Provides inline risk classification for agent tasks using a 4-tier model (GREEN/YELLOW/RED/CRITICAL). Uses fast heuristic file-pattern matching for low-risk tiers and delegates to 
Skill(attune:war-room-checkpoint)
for high-risk tiers requiring full reversibility scoring.
基于4级模型（GREEN/YELLOW/RED/CRITICAL）为Agent任务提供内联风险分类。低风险等级采用快速启发式文件模式匹配，高风险等级则委托给
Skill(attune:war-room-checkpoint)
进行完整可逆性评分。

When To Use

适用场景

  • Assessing risk of tasks before agent assignment
  • Determining verification requirements for task completion
  • Deciding parallel execution safety between tasks
  • Adding risk markers to task checklists
  • 分配Agent任务前评估风险
  • 确定任务完成的验证要求
  • 判断任务间并行执行的安全性
  • 为任务清单添加风险标记

When NOT To Use

不适用场景

  • Single-file trivial changes (assume GREEN)
  • Strategic architecture decisions (use full 
    Skill(attune:war-room)
    instead)
  • Non-code tasks (documentation-only, configuration comments)
  • 单文件的微小变更（默认设为GREEN）
  • 战略架构决策（改用完整的
    Skill(attune:war-room)
    ）
  • 非代码任务（仅文档、配置注释类）

4-Tier Risk Model

4级风险模型

TierColorScopeExampleVerification
GREENSafeSingle file, trivial revertTest files, docs, utilsNone required
YELLOWCautionModule-level, user-visibleComponents, routes, viewsConflict check + test pass
REDDangerCross-module, security/dataMigrations, auth, database schemaWar-room RS + full test + review
CRITICALStopIrreversible, regulatedData deletion, production deployWar-room RS + human approval
等级颜色范围示例验证要求
GREEN安全单文件，可轻松回滚测试文件、文档、工具类代码无需验证
YELLOW需注意模块级，用户可见组件、路由、视图冲突检查 + 测试通过
RED危险跨模块，涉及安全/数据迁移脚本、认证模块、数据库 schemaWar-room可逆性评分（RS）+ 完整测试 + 审核
CRITICAL禁止不可回滚，受监管数据删除、生产环境部署War-room可逆性评分（RS）+ 人工审批

Hybrid Routing

混合路由

Task received
    |
    v
Heuristic classifier (file patterns)
    |
    ├── GREEN/YELLOW → Apply tier, continue
    |
    └── RED/CRITICAL → Invoke Skill(attune:war-room-checkpoint)
                        for reversibility scoring (RS)
                        |
                        └── RS confirms or adjusts tier
Why hybrid: GREEN/YELLOW classification is fast and deterministic (file pattern matching). RED/CRITICAL tasks warrant the overhead of full reversibility analysis because the cost of getting them wrong is high.
Task received
    |
    v
Heuristic classifier (file patterns)
    |
    ├── GREEN/YELLOW → Apply tier, continue
    |
    └── RED/CRITICAL → Invoke Skill(attune:war-room-checkpoint)
                        for reversibility scoring (RS)
                        |
                        └── RS confirms or adjusts tier
混合机制的优势：GREEN/YELLOW等级的分类快速且确定（基于文件模式）。RED/CRITICAL任务由于出错成本极高，值得投入资源进行完整可逆性分析。

Task Metadata Extension

任务元数据扩展

Add risk tier to task metadata for downstream consumption:
json
{
  "id": "5",
  "subject": "Add user authentication",
  "metadata": {
    "risk_tier": "YELLOW",
    "risk_reason": "Modifies src/components/LoginForm.tsx (user-visible component)",
    "classified_at": "2026-02-07T22:00:00Z"
  }
}
Tasks without 
risk_tier
metadata default to GREEN (backward compatible).
为任务元数据添加风险等级，供下游流程使用：
json
{
  "id": "5",
  "subject": "添加用户认证功能",
  "metadata": {
    "risk_tier": "YELLOW",
    "risk_reason": "修改了src/components/LoginForm.tsx（用户可见组件）",
    "classified_at": "2026-02-07T22:00:00Z"
  }
}
未包含
risk_tier
元数据的任务默认设为GREEN（向后兼容）。

Module Reference

模块参考

  • tier-definitions.md: Detailed tier criteria, boundaries, and override mechanism
  • heuristic-classifier.md: File-pattern rules for automated classification
  • verification-gates.md: Per-tier verification requirements and parallel safety matrix
  • tier-definitions.md：详细的等级标准、边界及覆盖机制
  • heuristic-classifier.md：用于自动分类的文件模式规则
  • verification-gates.md：各等级的验证要求及并行安全矩阵

Integration Pattern

集成模式

yaml
undefined
yaml
undefined

In your skill's frontmatter

在你的Skill前置声明中

dependencies: [leyline:risk-classification]
undefined
dependencies: [leyline:risk-classification]
undefined

For Task Generators

针对任务生成器

Append 
[R:TIER]
marker to task format:
markdown
- [ ] T012 [P] [US1] [R:YELLOW] Create LoginForm component in src/components/LoginForm.tsx
在任务格式中追加
[R:TIER]
标记：
markdown
- [ ] T012 [P] [US1] [R:YELLOW] 在src/components/LoginForm.tsx中创建LoginForm组件

For Orchestrators

针对编排器

Check risk tier before task assignment:
if task.risk_tier in ["RED", "CRITICAL"]:
    invoke Skill(attune:war-room-checkpoint) for RS scoring
    if CRITICAL: require human approval before proceeding
分配任务前检查风险等级：
if task.risk_tier in ["RED", "CRITICAL"]:
    invoke Skill(attune:war-room-checkpoint) for RS scoring
    if CRITICAL: require human approval before proceeding

Exit Criteria

退出标准

  • Every task has a risk tier assigned (explicit or default GREEN)
  • RED/CRITICAL tasks have war-room-checkpoint RS scores
  • Verification gates passed for the assigned tier
  • No parallel execution of prohibited tier combinations
  • 所有任务均已分配风险等级（显式设置或默认GREEN）
  • RED/CRITICAL任务已获得war-room-checkpoint的RS评分
  • 已通过对应等级的验证关卡
  • 不存在被禁止的等级组合并行执行情况