Self-hosted workflows for coding-agent delivery. Orchestrate CodeBuddy, Codex and Claude Code with scripts and human approval gates. Includes Local workflows for coding assistants.
JavaScript agent-orchestrationagentic-workflowai-agentsai-codingclaude-codecode-reviewcodebuddycodexcoding-agentscursordeveloper-toolshuman-on-the-loopllmmcpmulti-agentsdlcself-hostedsopworkflow-automationworkflow-engine
description: 单独执行测试阶段(spawn test-engineer 根据变更补充并运行必要测试) argument-hint: [TASK_SLUG] allowed-tools: ["task", "read_file", "write_to_file", "execute_command", "codebase_search", "search_content"]
/run-tests
用法
/run-tests [TASK_SLUG]
单独执行测试阶段(TASK-04),不启动完整 devflow 工作流。test-engineer 会根据实际变更和项目已有测试体系选择单元、集成/API 或 E2E 测试。
适用于:
- 代码审查已完成,只想补充和执行必要测试
- 重新执行测试生成与验证
前置条件
workflow-state.json存在且CODE-REVIEW已完成(PASSED)03-code/change-report.md存在
Main Agent 动作
第一步:环境检查
- 读取
workflow-state.json→ 校验前置条件 - 未传 TASK_SLUG → 从 JSON 读取
第二步:spawn test-engineer
Task(subagent_name="test-engineer", mode="bypassPermissions",
prompt="执行 TASK-04:根据实际变更和项目现有测试体系补充、执行并报告必要测试。workflow_state_path={path}")
第三步:等待完成
test-engineer 完成后产出:
{artifacts_dir}/04-e2e/test-report.md{artifacts_dir}/04-e2e/added-cases.md
完成提示
输出:测试阶段已完成,可执行 /distill-knowledge 进入知识沉淀阶段。