research

research is a command for Claude Code from BuaaJoseph/claude-code-best-practice-zh. It costs 18 tokens per session (3,231 once invoked), scanned A, original, MIT.

A research command for deciding whether a proposed software feature should proceed, based on product value, technical feasibility, risks, and alternatives.

In plain words
What is it for?
Use it with a feature request to produce a research report covering requirements, user value, implementation difficulty, risks, and the recommended approach.
Why use it?
It creates a go-or-no-go decision before detailed planning, reducing the chance of investing in an unsuitable or impractical feature.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

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/buaajoseph/claude-code-best-practice-zh/research
Clone the repo
git clone --depth 1 https://github.com/BuaaJoseph/claude-code-best-practice-zh

Made for: Claude Code.

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 research

README.md
[![agentmods](https://agentmods.dev/badge/commands/buaajoseph/claude-code-best-practice-zh/research.svg)](https://agentmods.dev/commands/buaajoseph/claude-code-best-practice-zh/research)
Your own site
<a href="https://agentmods.dev/commands/buaajoseph/claude-code-best-practice-zh/research"><img src="https://agentmods.dev/badge/commands/buaajoseph/claude-code-best-practice-zh/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,231 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 5.1 $0.00018 $0.03231
Opus 5 $0.00009 $0.01615
Sonnet 5 $0.00004 $0.00646
Haiku 4.5 $0.00002 $0.00323

Measured 5d ago against content hash d8c2c91e5735, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

research 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 5d 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.

development-workflows/rpi/.claude/commands/rpi/research.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

用户输入

$ARGUMENTS

必须解析用户输入以提取功能 slug(rpi/ 中的文件夹名称)。

预期输入格式rpi/{feature-slug}/REQUEST.md

目的

此命令在规划阶段开始之前对功能请求进行全面研究和分析。它作为关键的 GO/NO-GO 关卡,决定功能想法是否应该进入详细规划。

关键目标

  • 评估产品-市场匹配和用户价值
  • 评估技术可行性和复杂性
  • 识别风险和潜在阻碍
  • 确定正确的方法(构建、购买、合作或拒绝)
  • 提供明确的 go/no-go 建议和理由

前置条件

  • 功能文件夹存在于 rpi/{feature-slug}/
  • 功能请求文件存在于 rpi/{feature-slug}/REQUEST.md

输出位置rpi/{feature-slug}/research/RESEARCH.md

这是 RPI 工作流的步骤 2(步骤 1 的初始功能描述之后)。

大纲

  1. 加载上下文:从 rpi/{feature-slug}/ 和项目宪法(如果存在)读取功能描述
  2. 解析功能请求:使用 requirement-parser agent 提取结构化需求
  3. 执行多阶段研究
    • 阶段 1:解析功能请求(requirement-parser agent)
    • 阶段 2:产品分析与宪法一致性(product-manager agent)
    • 阶段 2.5:技术发现(Explore agent)- 关键:深度代码探索
    • 阶段 3:技术可行性(senior-software-engineer agent)
    • 阶段 4:战略评估(technical-cto-advisor agent)
    • 阶段 5:生成研究报告(documentation-analyst-writer agent)
  4. 综合建议:将所有分析综合为清晰的 go/no-go 建议
  5. 验证输出:检查质量关卡
  6. 报告完成:提供建议、下一步和报告位置

阶段

阶段 0:加载上下文

前置条件:提供了功能 slug,rpi/{feature-slug}/REQUEST.md 存在

流程

  1. 读取功能描述

    • 读取 rpi/{feature-slug}/REQUEST.md(必需)
    • 从 REQUEST.md 提取功能需求和目标
  2. 检查项目宪法(可选):

    • 在代码库中查找宪法或原则文档
    • 常见位置:constitution.mdPRINCIPLES.md.project/constitution.md
    • 如果找到,提取核心原则、约束和目标
  3. 创建研究上下文

    • 综合为 agent 的简洁摘要
    • 识别关键一致性标准

输出

  • 功能描述摘要
  • 宪法原则(如果找到)
  • 评估的一致性标准

验证

  • 功能文件夹存在于 rpi/{feature-slug}/
  • 功能描述已提取
  • 已检查并加载宪法(如果存在)

阶段 1:解析功能请求

前置条件:阶段 0 完成

Agent:requirement-parser(规划领域)

流程

  1. 启动 requirement-parser agent,提供功能描述

  2. Agent 提取

    • 功能名称和类型
    • 目标组件
    • 目标和目的
    • 功能和非功能需求
    • 约束和假设
    • 复杂性估算
    • 澄清问题(如果有)
  3. 审查解析结果

    • 如果存在澄清问题,停止并询问用户后再继续

输出

  • 结构化需求文档
  • 功能元数据(名称、类型、组件、复杂性)
  • 澄清问题(如果有)

阶段 2:产品分析与宪法一致性

前置条件:阶段 1 完成,需求清晰

Agent:product-manager

流程

  1. 启动 product-manager agent,提供:

    • 阶段 1 的解析需求
    • 阶段 0 的宪法上下文
  2. Agent 分析

    • 用户价值:谁受益?影响有多大?
    • 市场匹配:这是否符合市场需求?
    • 产品愿景:这是否符合我们的产品策略?
    • 宪法一致性:这是否符合项目原则?
    • 约束检查:这是否违反任何宪法约束?

Read the full file on GitHub · 381 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. 5d ago First seen · 381 lines · 18 tokens per session scan A d8c2c91e5735

Subscribe to this mod's changes

research is a command published in the GitHub repository BuaaJoseph/claude-code-best-practice-zh (2 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 3,231 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 2026-08-31.