auto-task

auto-task is a skill for Claude Code, Codex from yunshu0909/yunshu_skillshub. It costs 258 tokens per session (4,313 once invoked), scanned A, original, MIT.

A workflow for carrying out complex, unclear tasks over many steps with limited user interruption. It breaks the work into a queue, runs it in batches, checks progress, and reports when specific conditions are met.

In plain words
What is it for?
It is for autonomous multi-step research, evaluation, comparison, and information整理 tasks that may use several tools or other agents.
Why use it?
It removes the need for the user to manage every step of a long research, comparison, or organisation task.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/yunshu/Documents/trae_projects/test/liuyao-exploration/.

Good fit It is for autonomous multi-step research, evaluation, comparison, and information整理 tasks that may use several tools or other agents.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for auto-task

README.md
[![agentmods](https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/auto-task/github.svg)](https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/auto-task)
Your own site
<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/auto-task"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/auto-task/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for auto-task

Your own site · 80×15
<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/auto-task"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/auto-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 258 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,313 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00258 $0.04313
Opus 5 $0.00129 $0.02157
Sonnet 5 $0.00052 $0.00863
Haiku 4.5 $0.00026 $0.00431

Measured 13d ago against content hash bfd25c3908db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

auto-task 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 13d ago.

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.

auto-task/SKILL.md · 370 lines

How it starts

The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.

auto-task · 复杂长程任务自主执行

你(AI)将作为一个自主执行员来跑用户的复杂任务。

硬目标:用户扔个任务给你后,1-2 小时不打扰他,最后给可信结果。

核心模型:任务确认 → 任务队列 → 分批执行 → 周期校验队列 → 触发式汇报。


1. 触发判断

✅ 适合 auto-task

  • 用户有复杂或模糊的任务,需要拆解才能跑
  • 答案/产出不在用户脑子里,AI 要自己跑工具/调研/分析才能得出
  • 时间跨度长(多步、多工具、可能要 sub-agent)
  • 用户明确或隐含希望 AI 自驱

❌ 不适合(路由到其他 skill)

任务 应该用
UI/交互设计 design-exploration
待办优先级判断 priority-judge
文章写作 writing-assistant
需求池管理 backlog-manager
终局愿景发散 vision-exploration
GitHub issue 诊断 issue-triage
起名 product-naming
有明确 spec 的实现编码 直接编码

判断不准?问一句:"你希望我跑一个长任务(多步执行 / 1-2 小时)还是一个快速答案(2-3 句话)?" —— 用户的回答会立刻分流。


2. 核心原则(硬约束)

  1. 任务队列是单一真源 —— TASK.md 里的 §3 任务队列就是整个任务的状态,每跑一批必须主动校验
  2. 触发式汇报 —— 默认不打扰用户,只在 §6 触发条件命中时停下
  3. 工具完全自由 —— 任何工具都可以用:WebSearch / WebFetch / Bash / Read / Write / Edit / Glob / Grep / Sub-agent / 任意 MCP / 并行调用 / 后台任务
  4. 诚实声明 —— 测试/评估类任务必须在产出报告头部标注:数据来源、是否盲测、潜在污染
  5. 朴素问题朴素答 —— 用户口语提问时人话回答,不堆结构和小标题
  6. 立场跟着证据走 —— 新数据来了就更新立场,不是"补充"原立场

3. 启动协议(首轮 setup)

Step 1 · 任务确认 ⚠ 关键

收到用户任务后,不要直接开干也不要问 5 个细节问题

要做的是:把"我理解你想做的事"重述给用户看。可以包括:

  • 我理解你的任务核心是什么
  • 我理解的边界:做什么、不做什么
  • 我理解的产出形态(报告 / 决策 / 工具 / 文档 / 列表 / ...)
  • 如果有非问不可的疑问,最多 1-2 个最关键的问题

可以反问也可以挖用户背景(他在做什么项目 / 角色 / 之前的相关工作),这会影响你后续的拆解角度。

用户确认("对" / "嗯" / "可以")后才能进 Step 2。

不要做的事

  • ❌ 一上来就问 5 个细节问题
  • ❌ 一上来就拆任务队列
  • ❌ 一上来就开始跑

Step 2 · 拆任务队列

把任务拆成 N 项(N 通常 5-15,视复杂度),写入 TASK.md 的 §3。每项包含:

  • 编号:T1, T2, T3...
  • 任务内容:一句话描述
  • 预期产出:跑完这项应该得到什么
  • 状态:⬜ 待执行 / 🔄 进行中 / ✅ 已完成 / ❌ 已废弃 / ⏸ 等待依赖
  • 依赖:dep: T1, T3(如果有)
  • 工具建议:可选,AI 自己拍板

拆多细是 AI 自己的判断

  • 太粗 → 失控、跑飞
  • 太细 → 僵化、没空间应对意外
  • 经验值:每项执行起来 5-15 分钟工作量

Step 3 · 自主度模式(默认 b)

  • (a) 保守 —— 每完成 N 项汇报一次
  • (b) 中等 —— 只在触发条件汇报(默认
  • (c) 激进 —— 跑完全部才汇报

如果用户没说,默认 (b)。如果用户说"少打扰我"或"自己跑",倾向 (c)。

Step 4 · 创建工作目录 + TASK.md → 立即开跑

不要等用户审 TASK.md 才动。直接进入 Batch 1


4. TASK.md 模板

# {任务名} · 任务主控文档

## 0. 元信息
- 创建日期:YYYY-MM-DD
- 当前批次:Batch N
- 自主度模式:(a/b/c)
- 下次汇报触发点:{条件}

## 1. 用户的任务(原话精炼)
- {用户原话}

## 2. AI 对任务的理解(确认时给用户看的版本)
- 核心:...
- 边界:做 X,不做 Y
- 产出形态:...
- 用户已确认:✅ YYYY-MM-DD

## 3. 任务队列

| # | 任务 | 状态 | 依赖 | 预期产出 | 工具建议 |
|---|------|------|------|----------|----------|
| T1 | ... | ⬜ | - | ... | WebSearch |
| T2 | ... | ⬜ | - | ... | Bash |
| T3 | ... | ⬜ | T1 | ... | 推理 |
| ... |

## 4. 批次执行日志(倒序)

### Batch N - YYYY-MM-DD
**本批跑了**:T{x}, T{y}, T{z}
**关键发现**:...
**队列校验结果**:
- 加 T{n}(理由:...)
- 删 T{m}(理由:...)
- 改 T{k} 优先级
**触发条件**:未触发 / 触发了 §6.X

## 5. 工作假设(如果是研究/评估类任务)
- 🟡 H1:...
- 🟢 H2:...

## 6. 触发用户介入条件
1. 完成里程碑批次(产出重要交付物)
2. Premise 被证伪
3. 真分叉决策
4. 连续 2 批无新进展
5. 意外重大发现
6. 需要用户真实数据

## 7. 决策记录
- D1(YYYY-MM-DD):...

## 8. 收尾产出
- [ ] FINAL-REPORT.md
- [ ] {其他交付物}

Read the full file on GitHub · 370 lines

Changes

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.

  1. 13d ago First seen · 370 lines · 258 tokens per session scan A bfd25c3908db

Subscribe to this mod's changes

auto-task is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (757 stars, last pushed 1mo ago), licensed MIT. It adds 258 tokens to every session and 4,313 once invoked, about $0.0013 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 2026-08-30.

Related

Other skills, from other repositories