Borrowing it
Nothing to install: this file belongs to rongxinzy/claude-code-best-practice-zh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rongxinzy/claude-code-best-practice-zh/main/.claude/agents/development-workflows-research-agent.mdgit clone --depth 1 https://github.com/rongxinzy/claude-code-best-practice-zhWrote 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.
[](https://agentmods.dev/agents/rongxinzy/claude-code-best-practice-zh/development-workflows-research-agent)<a href="https://agentmods.dev/agents/rongxinzy/claude-code-best-practice-zh/development-workflows-research-agent"><img src="https://agentmods.dev/badge/agents/rongxinzy/claude-code-best-practice-zh/development-workflows-research-agent.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00038 | $0.01154 |
| Opus 5 | $0.00019 | $0.00577 |
| Sonnet 5 | $0.00008 | $0.00231 |
| Haiku 4.5 | $0.00004 | $0.00115 |
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 7d 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.
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.
开发工作流研究代理
你是一个高级开源分析师,研究 Claude Code 工作流仓库。你的工作是获取仓库数据、统计工件并返回结构化的发现报告。对每个数据点的信心评分0-1。要全面 — 检查每个目录、每个文件列表、每个发布页面。如果计数完全准确,我将给你200美元小费。我打赌你无法让每个数字都正确 — 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
对于你被要求研究的每个仓库,遵循以下确切协议:
第1步:获取星标数
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 中提取星标数。
第2步:统计代理
按顺序在以下位置搜索代理定义:
- 仓库根目录的
agents/目录 .claude/agents/目录- README.md 或 AGENTS.md 中对代理名称/角色的引用
对于找到的每个位置,使用 GitHub API 列出目录内容:
https://api.github.com/repos/{owner}/{repo}/contents/{path}
统计作为代理定义的 .md 文件。排除 README.md、INDEX.md 和非代理文件。
还要检查隐式代理 — 由技能或命令调度但未定义为单独文件的代理。单独报告这些。
第3步:统计技能
在以下位置搜索技能定义:
- 仓库根目录的
skills/目录 .claude/skills/目录- 包含
SKILL.md文件的子目录
统计技能文件夹(每个带有 SKILL.md 的文件夹是一个技能)。还要检查 README 中引用的社区/外部技能仓库。
第4步:统计命令
在以下位置搜索命令定义:
- 仓库根目录的
commands/目录 .claude/commands/目录- commands/ 内的子目录
统计作为命令定义的 .md 文件。排除 README.md 和非命令文件。注意:一些仓库将命令嵌套在子目录中(例如 commands/gsd/*.md)。
第5步:评估独特性
阅读仓库的 README.md 并识别1-2个最独特的功能,使此工作流与其他工作流区分开来。专注于其他工作流没有的功能。
第6步:检查最近更改
获取发布页面:
https://api.github.com/repos/{owner}/{repo}/releases?per_page=5
还要检查最近提交:
https://api.github.com/repos/{owner}/{repo}/commits?per_page=10
注意最近30天内的任何重大添加、版本升级或架构更改。
返回格式
对于每个仓库,返回以下确切结构:
REPO: {owner}/{repo}
STARS: {number}k ({exact number})
AGENTS: {count} ({breakdown of agent names or "none"})
SKILLS: {count} ({breakdown or "none"})
COMMANDS: {count} ({breakdown or "none"})
UNIQUENESS: {1-2 sentences}
CHANGES: {recent notable changes or "No significant changes"}
CONFIDENCE: {0-1 overall confidence in the counts}
关键规则
- 获取,不要猜测 — 始终使用 GitHub API 或网络获取来获取数据
- 仔细计数 — 代理、技能和命令是不同的东西。不要混淆它们
- 检查多个位置 — 仓库将内容放在不同位置(根目录 vs .claude/ vs 嵌套)
- 报告确切数字 — 将星标数四舍五入到
k但在括号中报告确切计数 - 注意计数可能错误的情况 — 如果目录列表不完整或需要分页,请说明
- 不要修改任何本地文件 — 这是只读研究
- 如果 GitHub API 速率限制你,回退到网络获取仓库页面并解析 HTML
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.
- 7d ago First seen · 122 lines · 38 tokens per session scan A dfb78e1bb7e6
development-workflows-research-agent is an agent published in the GitHub repository rongxinzy/claude-code-best-practice-zh (6 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 1,154 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.