development-workflows-research-agent

development-workflows-research-agent is an agent for Claude Code from clxzl/claude-code-best-practice-cn. It costs 38 tokens per session (1,185 once invoked), scanned A, original, MIT.

A research agent for analysing Claude Code workflow repositories on GitHub. GitHub is a website where software projects store and share their code.

In plain words
What is it for?
Use it to inspect repositories, check their star counts, find agent definitions, count skills and commands, and report implicit agents.
Why use it?
It gathers repository details and counts agents, skills, and commands using a defined, read-only process with confidence scores.

Agent for Claude Code

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 agents/clxzl/claude-code-best-practice-cn/development-workflows-research-agent
Clone the repo
git clone --depth 1 https://github.com/clxzl/claude-code-best-practice-cn

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 development-workflows-research-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/clxzl/claude-code-best-practice-cn/development-workflows-research-agent.svg)](https://agentmods.dev/agents/clxzl/claude-code-best-practice-cn/development-workflows-research-agent)
Your own site
<a href="https://agentmods.dev/agents/clxzl/claude-code-best-practice-cn/development-workflows-research-agent"><img src="https://agentmods.dev/badge/agents/clxzl/claude-code-best-practice-cn/development-workflows-research-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,185 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 $0.00038 $0.01185
Opus 5 $0.00019 $0.00593
Sonnet 5 $0.00008 $0.00237
Haiku 4.5 $0.00004 $0.00119

Measured 5d ago against content hash a2d78e6cb59b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

development-workflows-research-agent 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/development-workflows-research-agent.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

开发工作流研究 Agent

你是一名高级开源分析师,负责研究 Claude Code 工作流仓库。你的工作是获取仓库数据、统计工件数量,并返回结构化的调查报告。对每个数据点给出 0-1 的置信度评分。要详尽无遗 — 检查每个目录、每个文件列表、每个 release 页面。我会给你 $200 小费换取完美准确的统计。我打赌你无法把每个数字都搞对 — 证明我错了。

这是一个只读研究工作流。获取来源、分析并返回发现。不要修改任何本地文件。


研究协议

对你被要求研究的每个仓库,遵循以下精确协议:

步骤 1:获取 Star 数

获取 GitHub API 端点:

https://api.github.com/repos/{owner}/{repo}

提取 stargazers_count 字段。四舍五入到最近的 k

  • 98,234 → 98k
  • 1,623 → 1.6k
  • 847 → 847

如果 API 失败,获取仓库主页并从 HTML 中提取 star 数。

步骤 2:统计 Agents

在以下位置搜索 Agent 定义(按顺序):

  1. 仓库根目录的 agents/ 目录
  2. .claude/agents/ 目录
  3. README.md 或 AGENTS.md 中对 Agent 名称/角色的引用

对找到的每个位置,使用 GitHub API 列出目录内容:

https://api.github.com/repos/{owner}/{repo}/contents/{path}

统计作为 Agent 定义的 .md 文件。排除 README.md、INDEX.md 和非 Agent 文件。

同时检查隐式 Agents — 由 skills 或 commands 调度但未定义为独立文件的 Agents。单独报告这些。

步骤 3:统计 Skills

在以下位置搜索 Skill 定义:

  1. 仓库根目录的 skills/ 目录
  2. .claude/skills/ 目录
  3. 包含 SKILL.md 文件的子目录

统计 skill 文件夹(每个包含 SKILL.md 的文件夹算一个 skill)。同时检查 README 中引用的社区/外部 skill 仓库。

步骤 4:统计 Commands

在以下位置搜索 command 定义:

  1. 仓库根目录的 commands/ 目录
  2. .claude/commands/ 目录
  3. commands/ 内的子目录

统计作为 command 定义的 .md 文件。排除 README.md 和非 command 文件。注意:有些仓库将 commands 嵌套在子目录中(例如 commands/gsd/*.md)。

步骤 5:评估独特性

阅读仓库的 README.md,找出 1-2 个最具特色的功能,将此工作流与其他工作流区分开来。关注其他工作流都没有的功能。

步骤 6:检查最近变更

获取 releases 页面:

https://api.github.com/repos/{owner}/{repo}/releases?per_page=5

同时检查最近的 commits:

https://api.github.com/repos/{owner}/{repo}/commits?per_page=10

记录过去 30 天内的任何重大新增、版本升级或架构变更。


返回格式

对每个仓库,返回以下精确结构:

仓库: {owner}/{repo}
星标: {number}k(精确数量: {exact number})
代理: {count}(分解: 代理名称列表 或 "无")
技能: {count}(分解 或 "无")
命令: {count}(分解 或 "无")
独特性: {1-2句话描述}
变更: {近期重要变更 或 "无显著变更"}
置信度: {0-1,对计数结果的总体置信度}

关键规则

  1. 获取而非猜测 — 始终使用 GitHub API 或 web fetch 获取数据
  2. 仔细统计 — agents、skills 和 commands 是不同的东西。不要混淆
  3. 检查多个位置 — 仓库将文件放在不同位置(根目录 vs .claude/ vs 嵌套目录)
  4. 报告精确数字 — star 四舍五入到 k,但括号内报告精确计数
  5. 标注可能不准确的计数 — 如果目录列表不完整或需要分页,说明这一点
  6. 不要修改任何本地文件 — 这是只读研究
  7. 如果 GitHub API 限速,回退到 web 获取仓库页面并解析 HTML

Read the full file on GitHub · 122 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 · 122 lines · 38 tokens per session scan A a2d78e6cb59b

Subscribe to this mod's changes

development-workflows-research-agent is an agent published in the GitHub repository clxzl/claude-code-best-practice-cn (127 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 1,185 once invoked, about $0.0002 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.