Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/jianchen08/agent-os-open/skill-container-task-flownpx skills add jianchen08/Agent-os-open --skill skill-container-task-flowgit clone --depth 1 https://github.com/jianchen08/Agent-os-openWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jianchen08/agent-os-open/skill-container-task-flow)<a href="https://agentmods.dev/skills/jianchen08/agent-os-open/skill-container-task-flow"><img src="https://agentmods.dev/badge/skills/jianchen08/agent-os-open/skill-container-task-flow.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00063 | $0.02051 |
| Opus 5 | $0.00032 | $0.01026 |
| Sonnet 5 | $0.00013 | $0.00410 |
| Haiku 4.5 | $0.00006 | $0.00205 |
Grade A, and why
项目任务流程 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目任务流程
本技能是流程指引，不是逐条打勾清单：按场景判断使用，遇不适用情况保持裁量，不机械执行。
适用场景
L1 组织和管理项目任务链（一个 app、一个游戏、一部网络小说等复杂长期任务）时加载本 skill。项目 = 真实文件夹 + 登记（projects 域），不是任务实体。
一、项目挂靠流程
- 澄清需求
- 确认项目：项目由用户在界面创建（新建任务表单选"挂靠项目"）或已存在——L1 向用户确认项目 ID 后，后续任务提交都传
project_id=项目ID（子任务系统自动继承，无需显式传） - 设置进度触发器：使用
trigger_setup设置定时触发器（详见下文） - 提交规划任务：派发给
solution_planning_agent - 执行任务链（方案确认后立即执行，无需询问用户）：
- 直接传递方案路径：不要自己读任务链再转述给下级，下级比你更专业，它自己会读。goal 中写明方案文档路径（如
docs/{title}_solution.md），让下级自行读取任务链并执行 - 用
file_read(fields=["task_chain"])只读取任务链中的执行者列表，用于检查所需 Agent 是否已存在 - 缺失资源 → 触发资源准备流程创建
- 等待资源就绪后，将方案路径提交给对应执行者
- 直接传递方案路径：不要自己读任务链再转述给下级，下级比你更专业，它自己会读。goal 中写明方案文档路径（如
- 项目任务链收尾：任务链全部完成（含最后的端到端验证任务）后通知用户
- 取消触发器：任务链完成后立即使用
trigger_setup(action="cancel", trigger_id="之前记录的ID")取消进度触发器 - 项目的暂停/恢复/删除由用户在界面管理（projects 域），L1 不代操作
- 取消触发器：任务链完成后立即使用
二、workspace 决策
| 场景 | workspace 填法 |
|---|---|
| 挂靠项目（project_id） | 不填——系统恒解析为项目文件夹（worktree 从项目仓库分叉） |
| 独立任务 + 用户明确指定某个目录 | 填该目标目录 |
| ⚠️ 系统内部路径（.ai_workspaces 等） | 禁止填写，只用于资源管理任务 |
三、进度触发器配置
使用 trigger_setup 设置定时触发器，定期检查项目任务执行进度。
| 配置项 | 值 |
|---|---|
| 触发间隔 | 15 分钟 |
| 最大触发次数 | 小型 32 次（约 8 小时）、中型 96 次（约 24 小时）、大型 288 次（约 3 天） |
| 触发动作 | 检查项目任务当前状态，对照速查表验证产出物是否已生成 |
| 共用触发器 | 已有相同间隔的活跃触发器时不要新建，用 update 延长其生命周期 |
| 超时处理 | 触发次数耗尽后任务链仍未完成 → 延长次数并通知用户 |
| 记录 trigger_id | 任务链完成时用于取消 |
停滞检测：子任务运行超 1 小时时查看详细进度，下次触发对比是否有变化。有变化继续等，无变化按优先级处理：①注入提示引导恢复 ②分析错误尝试修复 ③多次无效再通知用户。
四、方案不可变原则
方案准备阶段人类确认的方案稿是任务执行的绝对标准，确认后不可更改：
- 方案内容不可变：已确认方案的核心设计、功能范围、技术选型等不可修改
- 细化发现问题：细化过程中发现方案有缺陷或需要调整，细化 Agent 需提交新的细化任务说明问题，由 L1 决定处理方式
- 执行中发现方案需要更改：必须向人类请示，获得明确同意后方可修改方案
- 细化细节可调整：方案细化的粒度、实现步骤等细节可以在不违背方案核心的前提下调整
架构调整与方案修订
项目任务执行过程中，可能出现需要调整方案核心架构的情况。此时必须经过严格审查：
- 判断影响范围：架构调整是否涉及已确认方案的核心设计、功能范围或技术选型
- 如果涉及核心变更：
- 必须先向人类请示，获得明确同意
- 或提交给下级 Agent（如 solution_planning_agent）进行审查评估，产出审查报告
- 人类根据审查报告决定是否同意修订
- 执行修订：获得同意后，重新提交
solution_planning_agent（继承原工作空间），让其基于已有方案进行修订，产出更新后的方案文档和任务链 - 人类确认修订：修订后的方案同样需要人类确认
- 继续执行：根据新任务链继续派发，未受影响的已完成子任务无需重做
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +3 tokens per session fe73c58daefc
- 5d ago First seen · 118 lines · 60 tokens per session scan A e5130cebab6c
项目任务流程 is a skill published in the GitHub repository jianchen08/Agent-os-open (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 63 tokens to every session and 2,051 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
docker-expert
Docker containerization, multi-stage builds, and optimization.
harbor
CLI toolkit for managing containerized LLM services. Use when the user wants to start, stop, configure, or manage AI/LLM services like Ollama, Open WebUI, llama.cpp, vLLM, LiteLLM, ComfyUI, and 250+ others. Triggers on requests to "run a model", "start ollama", "set up an LLM", "configure harbor", "manage services"…
new-service
Add a new service to Harbor — scaffold the compose config, environment variables, metadata, documentation, and cross-service integrations. Use this skill whenever the user wants to add a new service to Harbor, integrate a new tool/app/model server, create a compose configuration for a new project, or onboard any…
background-task
Add or modify work that runs outside the request/response cycle — emails, document ingestion, webhooks, cleanups, scheduled jobs. Use when something is slow or fire-and-forget, or when adding a periodic/cron task. This project's queue is {{ cookiecutter.backgroundtasks }}.
agent-tool
Add a new tool/function the AI agent can call (e.g. look something up, hit an external API, perform an action). Use when extending the assistant's capabilities, wiring a new function into the agent, or when the model needs a new action. This project uses {{ cookiecutter.aiframework }}.
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.