Skip to content

lordfine/codex-claude-bridge / plugins/claude-code/skills/consult-claude

consult-claude

Verified

用户要求 Codex 指挥 Claude Code、接入或新建 Orca 会话、调整协作频率或思考档位、读取历史/实时进度、安排审查返工或后台续接时使用。一般 Claude 产品知识不触发。

references/思考与检查复用.md

View on GitHub
# 思考与检查复用

频率 profile 决定交付边界,思考 thinking 决定每次处理的投入,均为 low/medium/high。

| 组合 | 适用工作 |
| --- | --- |
| 低频低思考 | 边界明确的批量小改动,优先省成本 |
| 低频中思考 | 常规功能自主推进,集中验收 |
| 低频高思考 | 复杂长任务,关键交付深入判断 |
| 中频低思考 | 简单多步骤任务,里程碑纠偏 |
| 中频中思考 | 日常研发默认 |
| 中频高思考 | 跨模块修改,关键里程碑深审 |
| 高频低思考 | 人类紧密参与的小改动 |
| 高频中思考 | 探索式开发、频繁方向调整 |
| 高频高思考 | 高难度交互排障,控制使用范围 |

通过 delegate_coordination configure 设置主控 profile/thinking;单任务 action=profile 或 thinking,附 task_id 和 backend。inherit 回到主控默认。escalate 须附当前 request_id 和 reason;最高到 high,restore_thinking 恢复,旧请求升档不会应用到新请求。

新 Claude 启动传会话 --effort 与 --plugin-dir,加载会话专用分档代理codex-claude-execution:ccb-low/ccb-medium/ccb-high,继承当前模型。环境变量优先级、已有代理定义及模型能力仍可能覆盖设置。CLI 参数、界面显示和第三方模型实际推理支持分别记录。已有会话无法安全切换时显示 pending_restart;不要发送会写用户默认配置的 /effort 指令。

检查账本使用 action=record_check,字段 check_id、scope、environment、command、result(passed/failed)、evidence、uncovered。environment 须包含与任务相关的数据集、运行时、服务等环境身份,evidence 指向实际结果。程序记录当前源码指纹;不执行 command,也不认证执行方声明。

复用使用 action=reuse_check,附 check_id、scope、environment、command。匹配源码、环境、范围、命令且原结果通过才返回 reusable=true;主控还须核查证据充分性。checks 列出历史记录,不暗示所有检查都能复用。必要的全量、真实环境及部署前检查保留。
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall