What is speckit.tasks?

A command that turns design documents for a software feature into a task list in tasks.md, ordered by dependencies.

It uses plans, specifications, data models, API contracts, research, and test scenarios to create numbered implementation tasks grouped by user story.

It removes the need to manually sort requirements, technical work, tests, and prerequisites into an executable plan.

speckit.tasks — Command by studyzy

Install

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.

agentmods

npx agentmods add commands/studyzy/tapd-ai-cli/speckit.tasks

Clone the repo

git clone --depth 1 https://github.com/studyzy/tapd-ai-cli

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,818 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00029	$0.01818
Opus 5	$0.00015	$0.00909
Sonnet 5	$0.00006	$0.00364
Haiku 4.5	$0.00003	$0.00182

Measured 2d ago against content hash f73db58837d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speckit.tasks 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 2d 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.

.codebuddy/commands/speckit.tasks.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

用户输入

$ARGUMENTS

在继续之前, 你必须考虑用户输入(如果不为空).

概述

设置: 从仓库根目录运行 .specify/scripts/bash/check-prerequisites.sh --json 并解析 FEATURE_DIR 和 AVAILABLE_DOCS 列表. 所有路径必须是绝对路径. 对于参数值中的单引号如 "I'm Groot", 使用转义语法: 例如 'I'''m Groot'(或尽可能使用双引号: "I'm Groot").
加载设计文档: 从 FEATURE_DIR 读取:
- 必需: plan.md(技术栈, 库, 结构), spec.md(带优先级的用户故事)
- 可选: data-model.md(实体), contracts/(API 端点), research.md(决策), quickstart.md(测试场景)
- 注意: 并非所有项目都有所有文档. 基于可用内容生成任务.
执行任务生成工作流:
- 加载 plan.md 并提取技术栈, 库, 项目结构
- 加载 spec.md 并提取带优先级的用户故事(P1, P2, P3 等)
- 如果存在 data-model.md: 提取实体并映射到用户故事
- 如果存在 contracts/: 映射端点到用户故事
- 如果存在 research.md: 提取设置任务的决策
- 按用户故事生成任务(参见下面的任务生成规则)
- 生成显示用户故事完成顺序的依赖关系图
- 为每个用户故事创建并行执行示例
- 验证任务完整性(每个用户故事都有所有必需任务, 可独立测试)
生成 tasks.md: 使用 .specify/templates/tasks-template.md 作为结构, 填充:
- 来自 plan.md 的正确功能名称
- 阶段 1: 设置任务(项目初始化)
- 阶段 2: 基础任务(所有用户故事的阻塞先决条件)
- 阶段 3+: 每个用户故事一个阶段(按 spec.md 中的优先级顺序)
  - 每个阶段包括: 故事目标, 独立测试标准, 测试(如果请求), 实现任务
  - 每个任务的清晰 [Story] 标签(US1, US2, US3...)
  - 每个故事内可并行任务的 [P] 标记
  - 每个故事阶段后的检查点标记
- 最终阶段: 完善与横切关注点
- 按执行顺序编号的任务(T001, T002...)
- 所有任务必须遵循严格的检查清单格式(参见下面的任务生成规则)
- 每个任务的清晰文件路径
- 显示故事完成顺序的依赖关系部分
- 每个故事的并行执行示例
- 实现策略部分(MVP 优先, 增量交付)
报告: 输出生成的 tasks.md 路径和摘要:
- 总任务数
- 每个用户故事的任务数
- 识别的并行机会
- 每个故事的独立测试标准
- 建议的 MVP 范围(通常只是用户故事 1)

任务生成上下文: $ARGUMENTS

tasks.md 应该立即可执行 - 每个任务必须足够具体, 以便 LLM 可以在没有额外上下文的情况下完成它.

任务生成规则

关键: 任务必须按用户故事组织, 以实现独立的实现和测试.

测试是可选的: 仅当在功能规范中明确请求测试或用户请求 TDD 方法时才生成测试任务.

检查清单格式(必需)

每个任务必须严格遵循此格式:

- [ ] [TaskID] [P?] [Story?] 带文件路径的描述

格式组件:

复选框: 始终以 - [ ] 开头(markdown 复选框)
任务 ID: 按执行顺序的序号(T001, T002, T003...)
[P] 标记: 仅当任务可并行化时包含(不同文件, 不依赖于未完成的任务)
[Story] 标签: 仅用户故事阶段任务需要
- 格式: [US1], [US2], [US3] 等(映射到 spec.md 中的用户故事)
- 设置阶段: 无故事标签
- 基础阶段: 无故事标签
- 用户故事阶段: 必须有故事标签
- 完善阶段: 无故事标签
描述: 带确切文件路径的清晰操作

示例:

✅ 正确: - [ ] T001 根据实施计划创建项目结构
✅ 正确: - [ ] T005 [P] 在 src/middleware/auth.py 中实现认证中间件
✅ 正确: - [ ] T012 [P] [US1] 在 src/models/user.py 中创建用户模型
✅ 正确: - [ ] T014 [US1] 在 src/services/user_service.py 中实现 UserService
❌ 错误: - [ ] 创建用户模型(缺少 ID 和故事标签)
❌ 错误: T001 [US1] 创建模型(缺少复选框)
❌ 错误: - [ ] [US1] 创建用户模型(缺少任务 ID)
❌ 错误: - [ ] T001 [US1] 创建模型(缺少文件路径)

Read the full file on GitHub · 141 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.

2d ago First seen · 141 lines · 29 tokens per session scan A f73db58837d8

Subscribe to this mod's changes

speckit.tasks is a command published in the GitHub repository studyzy/tapd-ai-cli (54 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,818 once invoked, about $0.0001 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.

Backend and APIs Research Testing

speckit.tasks

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

用户输入

概述

任务生成规则

检查清单格式(必需)

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement