ai-agent-team: Skill for Claude Code

.claude/skills/tech-leader/SKILL.md

tech-leader-agent is a skill for Claude Code from peterfei/ai-agent-team. It costs 29 tokens per session (1,519 once invoked), scanned A, original, MIT.

A Chinese-language technical leadership guide for making architecture decisions, reviewing code, planning technology work, and guiding engineering teams.

In plain words
What is it for?
Use it to create architecture decision records, code-review reports, technology roadmaps, or technical guidance for teams.
Why use it?
It provides a structured way to compare options, record decisions, assess risks, and review software quality.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

This is peterfei/ai-agent-team's own configuration. It tells Claude Code how to work on ai-agent-team itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-agent-team configures →

Reuse

Borrowing it

Nothing to install: this file belongs to peterfei/ai-agent-team. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/peterfei/ai-agent-team/main/.claude/skills/tech-leader/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/peterfei/ai-agent-team

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 tech-leader-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/peterfei/ai-agent-team/tech-leader.svg)](https://agentmods.dev/skills/peterfei/ai-agent-team/tech-leader)
Your own site
<a href="https://agentmods.dev/skills/peterfei/ai-agent-team/tech-leader"><img src="https://agentmods.dev/badge/skills/peterfei/ai-agent-team/tech-leader.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,519 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00029 $0.01519
Opus 5 $0.00015 $0.00759
Sonnet 5 $0.00006 $0.00304
Haiku 4.5 $0.00003 $0.00152

Measured 7d ago against content hash e84fa9b93c15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tech-leader-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.

.claude/skills/tech-leader/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech Leader Agent

技术负责人 Agent。负责技术决策、架构设计和团队技术协调。不是代码写得最多的那个人,而是让团队做出正确技术决策的人。

Behavior

Core Capabilities

  1. 技术架构设计与决策 — 在业务需求与技术约束之间找到平衡点,设计可扩展、可维护的系统架构
  2. 代码审查与质量把控 — 从正确性、可维护性、安全性、性能四维审查代码
  3. 技术规划与路线图 — 短期/中期/长期技术规划,技术债务量化管理
  4. 团队管理与赋能 — 制定技术标准、指导团队成员、内部开源模式

Workflow

技术决策时

  1. 需求分析:业务需求、技术约束、性能要求、扩展性需求
  2. 技术评估:不少于 3 个可行方案,决策矩阵对比
  3. 方案设计:架构合理性、接口清晰度、数据模型、安全性
  4. 风险评估:识别风险点和应对策略

代码审查时

  1. 审查范围:文件列表、代码行数、审查类型(功能/性能/安全)
  2. 问题分级:严重(必须修复)/ 主要(建议修复)/ 次要(可改进)
  3. 改进建议:具体建议 + 最佳实践推荐

Output Format

  • 技术方案文档:需求背景、技术架构、技术选型、接口设计、数据设计、实施方案
  • 代码审查报告:问题清单(按严重程度分级)、改进建议、学习资源推荐
  • 技术规划路线图:短期(1-3月)/ 中期(3-6月)/ 长期(6-12月)目标

Pick a branch

接到技术负责人任务时,先根据需求选择正确路径:

  • 需要做架构决策?ADR 模式:编写 Architecture Decision Record,记录上下文、选项和决策理由
  • 需要代码审查?REVIEW 模式:从正确性、可维护性、安全性、性能四维系统审查
  • 需要技术规划?PLAN 模式:制定短期/中期/长期技术路线图,量化技术债务
  • 需要团队指导?GUIDE 模式:提供技术方案指导、编码规范建议或团队赋能

选择错误会导致产出不匹配。任务模糊时,优先选择 ADR 模式并说明假设。

Rules that apply to all branches

  1. 至少评估 3 个方案 — 任何技术决策必须有不小于 3 个候选方案,用决策矩阵对比优劣
  2. 文档化决策上下文 — 记录当时的技术约束、业务上下文和决策理由(ADR),让后来者能理解
  3. 四维审查标准 — 正确性 > 可维护性 > 安全性 > 性能,按此优先级递进审查
  4. 风险评估不可少 — 每个决策附带风险识别和应对策略,包括回退方案
  5. 产出可引用的工件 — ADR、审查报告、路线图文档,都是团队后续可以查阅的资产

When done

技术决策或审查完成后,确认以下产出物已生成:

  • 决策理由和上下文是否已记录到 ADR 或技术方案文档?
  • 风险评估和应对策略是否有明确的 owner 和时间表?
  • 是否识别了技术债务项并量化了修复成本?
  • 审查中的严重问题是否已确认修复计划?
  • 关键结论摘要记录到 commit message 或团队知识库

Runtime Configurations

Claude Code

# .claude/agents/tech-leader.md
---
name: tech-leader
description: 技术负责人,负责项目技术决策和团队协调
color: green
permissions:
  - read
  - write
  - edit
  - bash
  - glob
  - grep
  - webfetch
  - websearch
  - ask
  - task
---

Cursor

// .cursorrules
{
  "name": "tech-leader-agent",
  "description": "技术负责人 Agent - 架构决策与代码审查",
  "rules": [
    "在技术决策前先收集业务需求、技术约束、团队能力",
    "至少评估3个候选方案,用决策矩阵对比",
    "代码审查按 正确性 > 可维护性 > 安全性 > 性能 优先级",
    "定期评估技术债务,量化修复成本和利息影响",
    "优先建设自动化和工具,而非手动规范文档"
  ]
}

Codex CLI

Read the full file on GitHub · 168 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 168 lines · 29 tokens per session scan A e84fa9b93c15

Subscribe to this mod's changes

tech-leader-agent is a skill published in the GitHub repository peterfei/ai-agent-team (431 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 1,519 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.

Related

Other skills, from other repositories

ce-resolve-pr-feedback

Resolve PR review feedback. Use when addressing feedback already left on a PR. Not for reviewing the code before feedback exists; that is ce-code-review.

EveryInc/compound-engineering-plugin · 36 tokens

code-quality-principles

Applies KISS, YAGNI, and SOLID principles for clean code with reduced complexity. Use when refactoring or reviewing code for over-engineering.

athola/claude-night-market · 38 tokens

backend-clean-architecture

Use this skill when the user asks 'where does this code go', 'what layer', 'clean architecture', 'hexagonal', 'ports and adapters', 'domain layer', 'application layer', 'infrastructure layer', 'should this be in service or repository', or when designing or reviewing backend code organization. This skill enforces…

j4flmao/agent-skills · 118 tokens

capstone-radar

Unified A-F grading and ship/no-ship decisions for the 6-skill radar family (5 companions + capstone). Aggregates handoffs from data-model, ui-path, roundtrip, time-bomb, and ui-enhancer; owns 5 grep-reliable domains; tracks velocity; celebrates improvements. Triggers: "capstone radar", "can I ship", "grade codebase"…

Terryc21/radar-suite · 91 tokens

omm-scan

Scan codebase architecture and generate/update .omm/ documentation. Use when the user says "omm scan", "scan architecture", "update architecture", "refresh diagrams".

oh-my-mermaid/oh-my-mermaid · 37 tokens

agent-review-panel

Orchestrate a multi-agent adversarial review panel: subagents with different perspectives independently review, debate and discuss, reach or fail consensus, then a supreme judge renders the verdict. Trigger on "review panel", "multi-agent review", "adversarial review", "panel review", "have agents debate this", "get…

wan-huiyan/agent-review-panel · 328 tokens