Codex 助手
- 作者仓库星标 8
- 许可证 MIT
- 作者更新于 实时读取
- 作者仓库 codex-deck
- 领域
- 工程开发
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 94 / 100 · 已通过审计
- 作者 / 版本 / 许可
- @asfsdsf · MIT
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: codex-deck-flow
description: Use this skill when the user asks for persistent multi-agent coding workflows with task dependen…
category: 工程开发
runtime: 无特殊运行时
---
# codex-deck-flow 输出预览
## PART A: 任务判断
- 适用问题:代码实现、重构、调试或代码审查。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Mandatory activation contract / Strict task creating mode / Core runtime model”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于代码实现、重构、调试或代码审查,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Mandatory activation contract / Strict task creating mode / Core runtime model”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件;主要在本地完成;通常不需要额外 API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文没有稳定的斜杠命令要求。安装验证后通常全局生效,直接在对话里点名这个 Skill 并描述任务即可。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件。
先用一个小任务确认它会围绕“Mandatory activation contract / Strict task creating mode / Core runtime model”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: codex-deck-flow
description: Use this skill when the user asks for persistent multi-agent coding workflows with task dependen…
category: 工程开发
source: asfsdsf/codex-deck
---
# codex-deck-flow
## 什么时候使用
- 把工程方向的常用动作沉淀成 Agent 可调用的技能 适合处理工程开发场景下的代码实现、调试、重构、测试或代码审查,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代…
- 面向代码实现、重构、调试或代码审查,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Mandatory activation contract / Strict task creating mode / Core runtime model」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件;主要在本地完成;通常不需要额外 API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "codex-deck-flow" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Mandatory activation contract / Strict task creating mode / Core runtime model
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} Orchestrate Persistent Multi-Agent Workflows
Use this skill to create workflows, inspect workflows, and send control messages to the background codex-deck-flow daemon.
This skill is an operator control client, not the long-running orchestrator. After the daemon has started successfully and a control message has been sent successfully, the skill should stop.
Detailed operational guidance is routed through references/*.md:
- Command sequences and syntax:
references/commands.md - Workflow/task authoring rules:
references/authoring.md - Failure recovery runbooks:
references/runbooks.md - Scheduler vs workflow-task guidance placement:
references/guidance-routing.md - Architecture, contracts, and role prompts:
references/agent-flow-design.md - Scheduler mutation heuristics (scheduler task only):
references/scheduler.md
Mandatory activation contract
- If the user explicitly mentions
$codex-deck-floworcodex-deck-flow, treat that as a strict instruction to use this workflow system. - Do not switch to direct ad-hoc coding as the primary path while that request is active.
- In the first response after activation, say that codex-deck-flow orchestration is active and state the first command you are running.
- If the user gives
project rootplusworkflow IDfor a workflow that the current session has not created, loaded, or already resolved, first runresolve-workflow, then continue withvalidate,reconcile, andstatus. - If the current session already knows the workflow path from
create, a previousresolve-workflow, or earlier inspection in the same chat, reuse that path instead of resolving again. - If the user already gave a workflow path, start with
validate, thenreconcile, thenstatus. - If no workflow exists yet, start with
create, then immediatelyvalidate, thenshoworstatus, and present the authored tasks/prompts for user approval beforetrigger. - If the user explicitly includes
Strict task creating mode, keep the normal create/validate/show flow, but use the strict authoring protocol described below. - Keep merge explicit. Never run
merge --applyunless the user explicitly asked to apply the integration branch into the target branch. - Once
triggerordaemon-sendsucceeds, stop. Do not continue the same skill turn as if it were the orchestrator.
Strict task creating mode
When the user explicitly includes Strict task creating mode, treat that as a workflow-authoring protocol layered on top of the normal codex-deck-flow create flow.
Rules:
- Still run
create, thenvalidate, thenshoworstatusas usual. - The draft workflow JSON already exists after
create; approval still gatestrigger, not draft creation. - If you must ask the user a clarifying question before the workflow is ready, the assistant message must end with exactly:
<codex-deck-flow>Question<codex-deck-flow/>
- When asking the user to approve the authored workflow, the assistant message must end with exactly:
<codex-deck-flow>Request approve:workflow-file-name.json<codex-deck-flow/>
- Replace
workflow-file-name.jsonwith the JSON file name only, for examplefeature-delivery.json. - Use only the file name token after
Request approve:. Do not add brackets or extra wrappers. - Do not put any additional text after the strict tag suffix.
- Once the user approves, exit strict task creating mode and continue with the normal codex-deck-flow flow.
- If the approval message includes workflow data for an already-created draft, reuse that workflow and do not run
createagain. - The approval workflow data may include fields such as
workflowPath,workflowFileName,workflowId,projectRoot, andboundSessionId; treat that as the canonical handoff for reusing the already-authored draft.
Core runtime model
- One workflow = one JSON file under
./.codex-deck/. - The daemon is the orchestration owner and can serve workflows from multiple project roots.
- The skill starts daemon if needed, sends one control message, then stops.
- Worker tasks run in isolated
git worktreedirectories. - Scheduler continuity should use codex-deck-flow non-interactive app-server-backed resume behavior (
scripts/codex_resume_noninteractive.pybehavior model), not rawcodex resume SESSION_IDsemantics in daemon mode.
Use references/agent-flow-design.md for full runtime contracts and role data.
Route by intent
Use this decision route, then follow details in references/commands.md:
- New workflow request:
create->validate->show/status-> user approval ->trigger - Existing workflow by known path:
validate->reconcile->status - Existing workflow by project root + workflow ID when path unknown in current session:
resolve-workflow->validate->reconcile->status - Explicit daemon control message:
daemon-sendorstop-workflow-processes - Merge request:
mergepreview, andmerge --applyonly if explicitly requested
Reference loading boundaries
- Scheduler task only:
references/scheduler.md - Scheduler/workflow-task guidance file rules and routing:
references/guidance-routing.md - Non-scheduler roles should not load scheduler-specific mutation guidance.
References
Canonical references:
references/commands.mdreferences/authoring.mdreferences/runbooks.mdreferences/guidance-routing.mdreferences/agent-flow-design.mdreferences/scheduler.md(scheduler task only)
Implementation scripts:
scripts/workflow.pyscripts/task_runner.pyscripts/daemon.pyscripts/daemon_client.pyscripts/codex_resume_noninteractive.pyscripts/session_state.pyscripts/session_summary.py
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核