team-arch

team-arch is a skill for Claude Code from ketor/cto-fleet. It costs 123 tokens per session (6,449 once invoked), scanned B, original, Apache-2.0.

An automated team of software analysts that examines a codebase and produces a structured architecture document with Mermaid diagrams. It can scan the project, compare independent analyses, combine their conclusions, and cross-check the result.

In plain words
What is it for?
Use it to map modules and dependencies, investigate selected areas, document system structure, and choose the analysis depth and output language.
Why use it?
It helps when a codebase is too large or complicated to understand reliably from one person's quick review. The different analysis passes can expose disagreements and missing details.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Good fit Use it to map modules and dependencies, investigate selected areas, document system structure, and choose the analysis depth and output language.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ketor/cto-fleet/team-arch
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.

Any agent
npx skills add ketor/cto-fleet --skill team-arch
Clone the repo
git clone --depth 1 https://github.com/ketor/cto-fleet

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 team-arch

README.md
[![agentmods](https://agentmods.dev/badge/skills/ketor/cto-fleet/team-arch.svg)](https://agentmods.dev/skills/ketor/cto-fleet/team-arch)
Your own site
<a href="https://agentmods.dev/skills/ketor/cto-fleet/team-arch"><img src="https://agentmods.dev/badge/skills/ketor/cto-fleet/team-arch.svg" alt="Measured on agentmods" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,449 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00123 $0.06449
Opus 5 $0.00062 $0.03224
Sonnet 5 $0.00025 $0.01290
Haiku 4.5 $0.00012 $0.00645

Measured 7d ago against content hash c2bae3a2459d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

team-arch scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- 目录路径:`/tmp/{team-name}/`(team lead 在 TeamCreate 后执行 `mkdir -p /tmp/{team-name} && chmod 700 /tmp/{team-name}`)
team-arch/SKILL.md · 526 lines

How it starts

The opening of the file, as written. The whole thing — 526 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preamble (run first)

_UPD=$(~/.claude/skills/cto-fleet/bin/cto-fleet-update-check 2>/dev/null || true)
[ -n "$_UPD" ] && echo "$_UPD" || true

If output shows UPGRADE_AVAILABLE <old> <new>: read ~/.claude/skills/cto-fleet/cto-fleet-upgrade/SKILL.md and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If JUST_UPGRADED <from> <to>: tell user "Running cto-fleet v{to} (just updated!)" and continue.

参数解析:从 $ARGUMENTS 中检测以下标志:

  • --auto:完全自主模式(不询问用户任何问题,全程自动决策)
  • --once:单轮确认模式(将所有需要确认的问题合并为一轮提问,确认后全程自动执行)
  • --depth=shallow|standard|deep:分析深度(默认 standard
  • --focus=module1,module2:聚焦分析模块(可选,默认全量分析)
  • --lang=zh|en:输出语言(默认 zh 中文)
模式 用户确认范围 条件节点处理
标准模式(默认) 项目概况确认 + 分歧仲裁 + 最终文档确认 正常询问用户
单轮确认模式--once 仅最终文档确认 自动决策 + 收尾汇总
完全自主模式--auto 不询问用户 全部自动决策,收尾汇总所有决策

单轮确认模式下条件节点自动决策规则:

  • 分析深度不确定 → team lead 根据项目规模自行判断,在最终文档中说明
  • 两位 analyzer 分歧 → analyst 标注分歧,team lead 综合论证后裁决,收尾时汇总
  • 分歧超过 50%不可跳过,必须暂停问用户(熔断机制)
  • 交叉验证异议超过 3 项不可跳过,必须暂停问用户(熔断机制)
  • 项目过大无法完整分析 → scanner 识别核心模块,analyzer 聚焦核心模块
  • --focus 参数处理:如果用户指定了 --focus,scanner 和 analyzer 优先分析指定模块,其余模块仅概览级别

完全自主模式下:所有节点均自动决策,不询问用户。熔断机制仍然生效(分歧超过 50%、交叉验证异议超过 3 项时仍必须暂停问用户)。

分析深度说明:

深度 分析范围
shallow 仅项目结构和依赖概览,跳过深入架构模式分析。跳过交叉验证。
standard 结构 + 依赖 + 核心模块架构模式 + 数据流
deep 全量分析,额外包括性能热点、安全边界、技术债务、演进建议

使用 TeamCreate 创建 team(名称格式 team-arch-{YYYYMMDD-HHmmss},如 team-arch-20260308-143022,避免多次调用冲突),你作为 team lead 按以下流程协调。

文件交接规范(File-Based Handoff)

所有 agent 间传递详细报告时,必须采用文件交接模式(防止上下文溢出触发 20MB 限制):

  1. 写入文件:将完整报告写入团队工作目录:
    • 目录路径:/tmp/{team-name}/(team lead 在 TeamCreate 后执行 mkdir -p /tmp/{team-name} && chmod 700 /tmp/{team-name}
    • 单个文件 ≤ 2000 行;超大报告拆分为 summary + details 文件
  2. 发送引用:通过 SendMessage 仅发送(≤500 字符):
    • 文件路径(1 行)
    • 关键摘要(含核心指标/发现/评分)
  3. 按需读取:接收方使用 Read 按需读取文件,发送方不内联完整内容
  4. 路径转发:team lead 转发报告时只转发文件路径 + 摘要,不 Read 后再 SendMessage
  5. 遵从校验:team lead 收到超 1000 字符且不含 /tmp/team- 路径前缀的消息时,要求 agent 以文件交接模式重发

Read the full file on GitHub · 526 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. 7d ago First seen · 526 lines · 0 tokens per session scan B c2bae3a2459d

Subscribe to this mod's changes

team-arch is a skill published in the GitHub repository ketor/cto-fleet (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 123 tokens to every session and 6,449 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens