speckit.plan

A command that turns a feature specification into a technical implementation plan and supporting design documents.

In plain words
What is it for?
It researches unclear areas, creates data models, API contracts, quickstart scenarios, and an implementation plan, then updates the project's agent context.
Why use it?
It resolves unknown technical choices and records the data, interfaces, tests, and decisions needed before implementation begins.

Command

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.plan
Clone the repo
git clone --depth 1 https://github.com/studyzy/tapd-ai-cli
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 925 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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00925
Opus 5 $0.00007 $0.00463
Sonnet 5 $0.00003 $0.00185
Haiku 4.5 $0.00001 $0.00093

Measured 2d ago against content hash 80ddd5aab92f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speckit.plan 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.plan.md · 91 lines

What it actually says

用户输入

$ARGUMENTS

在继续之前, 你必须考虑用户输入(如果不为空).

大纲

  1. 设置: 从仓库根目录运行 .specify/scripts/bash/setup-plan.sh --json 并解析 JSON 获取 FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. 对于参数中的单引号如 "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").

  2. 加载上下文: 读取 FEATURE_SPEC 和 .specify/memory/constitution.md. 加载 IMPL_PLAN 模板(已复制).

  3. 执行计划工作流: 按照 IMPL_PLAN 模板中的结构:

    • 填充技术上下文(将未知项标记为 NEEDS CLARIFICATION)
    • 从章程文档填充章程检查部分
    • 评估关卡(如果违规无正当理由则报错)
    • 阶段 0: 生成 research.md(解决所有 NEEDS CLARIFICATION)
    • 阶段 1: 生成 data-model.md, contracts/, quickstart.md
    • 阶段 1: 通过运行代理脚本更新代理上下文
    • 设计后重新评估章程检查
  4. 停止并报告: 命令在阶段 2 规划后结束. 报告分支, IMPL_PLAN 路径和生成的制品.

阶段

阶段 0: 大纲与研究

  1. 从上述技术上下文中提取未知项:

    • 每个 NEEDS CLARIFICATION → 研究任务
    • 每个依赖项 → 最佳实践任务
    • 每个集成 → 模式任务
  2. 生成和分发研究代理:

    For each unknown in Technical Context:
      Task: "Research {unknown} for {feature context}"
    For each technology choice:
      Task: "Find best practices for {tech} in {domain}"
    
  3. research.md 中整合发现, 使用格式:

    • Decision: [选择了什么]
    • Rationale: [为什么选择]
    • Alternatives considered: [还评估了什么]

输出: research.md, 所有 NEEDS CLARIFICATION 已解决

阶段 1: 设计与合同

前提条件: research.md 完成

  1. 从功能规范中提取实体data-model.md:

    • 实体名称, 字段, 关系
    • 来自需求的验证规则
    • 状态转换(如适用)
  2. 定义接口合同(如果项目有外部接口) → /contracts/:

    • 识别项目向用户或其他系统暴露的接口
    • 为项目类型选择合适的合同格式
    • 示例: 库的公共 API、CLI 工具的命令模式、Web 服务的端点、解析器的语法、应用程序的 UI 合同
    • 如果项目是纯内部项目(构建脚本、一次性工具等), 跳过此步骤
  3. 代理上下文更新:

    • 运行 .specify/scripts/bash/update-agent-context.sh codebuddy
    • 这些脚本检测正在使用哪个 AI 代理
    • 更新相应的代理特定上下文文件
    • 仅添加当前计划中的新技术
    • 保留标记之间的手动添加内容

输出: data-model.md, /contracts/*, quickstart.md, 代理特定文件

关键规则

  • 使用绝对路径
  • 关卡失败或未解决的澄清事项时报错
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. 2d ago First seen · 91 lines · 14 tokens per session scan A 80ddd5aab92f

Subscribe to this mod's changes

speckit.plan is a command published in the GitHub repository studyzy/tapd-ai-cli (54 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 925 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.