agentleFS
YSAA1YSAA1/harness-workflow/skills/plan/SKILL.md

plan

Skill3 starsChanged 13 days agoMITView on GitHub

把多阶段、依赖复杂或需要跨会话恢复的任务写成可执行计划(带依赖边的任务图),需要跨会话恢复时开一条轨道。用户只要计划时交付即止;已授权执行时写完继续。一句话能说清的小改动不用。

184 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use heartmula, webhook-subscriptions and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • math-incSkill

    heartmula

    Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

    Also in 9 projects that use this

  • Tommy-ywSkill

    webhook-subscriptions

    Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push notifications to chats.

    Also in 5 projects that use this

  • math-incSkill

    minecraft-modpack-server

    Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

    Also in 5 projects that use this

  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 6 projects that use this

  • gaebalaiSkill

    codex-system

    PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".

    Also in 3 projects that use this

  • ibahgatSkill

    context-optimize

    Improve context efficiency and cache stability for long or complex sessions.

    Also in 3 projects that use this

  • +3 more from math-inc

The file

Files
SKILL.md

可执行计划

计划说明做什么、先后关系和如何验收。它复用用户请求、已批准的 Spec、issue 和项目现有记录,不另造一套需求材料。

流程

  1. 从现有证据确定目标、范围、验收和依赖。只就影响结果的未定取舍询问用户;常规实现选择自己决定,并写明必要的假设。
  2. 优先更新项目已有的计划载体;没有惯例且确需持久计划时,用 docs/plans/YYYY-MM-DD--<topic>-plan.md。短任务用对话计划;一句话能描述且没有跨文件依赖的改动,不落盘计划文件。
  3. 写目标、范围、可执行工作项、验证方式、重要依赖或风险。多阶段任务写最终整体验收(final_integration_claim),因为每步各自通过不等于整体成功。
  4. Markdown 工作项用 checkbox;issue 或现有 tracker 保留其原生状态。多工作项计划把依赖写成边:每项带 依赖: #N(无则写「无」),让计划成为任务图——前置全部完成的项即可开工,ship 据此并行派发。切分规则:
    • 纵向切片:每项贯穿所需各层、可独立验证、一个新上下文窗口装得下;需要的预重构排最前(先让改动变容易,再做容易的改动)。
    • 全仓机械改动(改名、改共享类型,一改即破大量调用点)不硬切纵向,走 expand–contract:先加新形式且不破坏旧的 → 按爆炸半径分批迁移调用点(每批一项,依赖 expand)→ 最后删旧形式(依赖全部迁移批)。
    • 共享文件:两项会改同一共享文件(配置表、消息目录、共享类型)时,加依赖边让它们串行,或在计划里预先定死各自新增的名字。
  5. 恢复面:只有需要跨会话恢复的轨道才建文件,短任务零文件;项目已有别的 tracker(issue、看板等)时复用它,不另建 .harness/。用 .harness/ 时开一条轨道:在 .harness/index.md 的 | 轨道 | 状态 | 入口 | 表里加一行(状态 active,入口链接到 tracks/<id>.md),并建 .harness/tracks/<id>.md,写 Objective:、Status:、Entry:、Evidence:、Next:、Limits: 六行,Entry: 指向本计划文件。链接用相对路径;只动本轨道,不改其他轨道的行或文件。项目 AGENTS.md 还没有指向 .harness/index.md 的读取指引时补一行。格式细节以 writing-for-agents 的恢复面政策为准;项目有 scripts/harness_lint.py 时提交前跑一次。
  6. 用户只要求计划时,交付后结束。已授权实现时继续执行可推进的步骤;写计划不是新的批准门槛。

验证与提交

  • 验证受阻时记录缺口、可用证据和不能作出的声明,继续不依赖缺口的工作。不要把工具暂缺自动变成重新搭建工作台的任务。
  • 不用替代检查冒充原验收;改变约定的验收标准需要用户同意。
  • commit 可用于有意义的里程碑,不是每个计划的必填项。提交需满足项目约定和相关验证;项目没有提交约定时,以 implement 的提交规则为准。
  • 不强制为每项重复填写 acceptance_criteria、verification_commands、success_definition;行动和成功条件写清楚即可。

之后

  • 已授权且需要改动:implement;有多个可同时开工的工单:ship;根因未知:diagnose。
  • 用户要求审阅,或改动需要深入检查:review。
  • 计划被放弃或否决:用 cleanup 关轨道。
  • 只在真实的工作台缺口需要修复时用 harness-builder;只要计划时直接结束。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.