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.
npx agentmods add skills/ketor/cto-fleet/teamnpx skills add ketor/cto-fleet --skill teamgit clone --depth 1 https://github.com/ketor/cto-fleetWrote 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/skills/ketor/cto-fleet/team)<a href="https://agentmods.dev/skills/ketor/cto-fleet/team"><img src="https://agentmods.dev/badge/skills/ketor/cto-fleet/team.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 | $0.00090 | $0.08517 |
| Opus 5 | $0.00045 | $0.04258 |
| Sonnet 5 | $0.00018 | $0.01703 |
| Haiku 4.5 | $0.00009 | $0.00852 |
Grade A, and why
team scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble (run first)
_UPD=$(~/.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：传递给目标 skill 的完全自主模式标志（不询问用户任何问题）--once：路由层保留一次交互机会（如单 skill vs pipeline 选择），确认后将--once传递给目标 skill，后续全程自动执行--dry-run：只分析不执行——完成路由分析后，输出所有推荐方案（单 skill、pipeline 组合、替代方案），但不调用任何 skill。用于查询"我的任务应该用哪些 team"--lang=zh|en：传递给目标 skill 的输出语言标志
解析后保留完整的任务描述（含未识别的参数，如 --focus、--depth 等，一并传递给目标 skill）。
路由决策流程
用户输入 → 提取任务关键词和意图
→ 匹配决策矩阵（按优先级）
→ 单一匹配 → 确认并调用
→ 多个候选 → AskUserQuestion 让用户选择
→ 无匹配 → AskUserQuestion 让用户指定
决策矩阵
按任务意图匹配，优先匹配排在前面的规则。当多条规则同时匹配时，选择最具体的那条。支持中英文混合输入。
开发与修复
| 意图信号（中/英） | 目标 Skill | 传递参数 |
|---|---|---|
| "小改动""快速实现""简单功能""小 feature""小需求""改个配置""加个字段""tweaks" / "quick fix""small feature""simple change""minor update""quick task""tweak" | /team-quick |
[--auto] [--once] [--lang] |
| "开发""实现""新增功能""添加""创建功能""做一个" / "implement""add feature""build""create" | /team-dev |
[--auto] [--once] [--lang] |
| "重构""迁移""拆分模块""合并模块""重命名""提取接口" / "refactor""migrate""split""merge module""extract interface" | /team-refactor |
[--auto] [--once] [--scope=module|package|system] [--lang] |
| "修复 bug""debug""定位问题""排查""为什么报错""崩溃" / "fix bug""debug""troubleshoot""why error""crash" | /team-debug |
[--auto] [--once] [--lang] |
审查与分析
| 意图信号（中/英） | 目标 Skill | 传递参数 |
|---|---|---|
| "review 代码""代码审查""代码质量""review PR" / "code review""review pull request""code quality" | /team-review |
[--auto] [--once] [--focus] [--lang] |
| "分析架构""架构评估""模块关系""依赖分析" / "analyze architecture""architecture review""dependency analysis" | /team-arch |
[--auto] [--once] [--depth] [--focus] [--lang] |
| "性能优化""性能分析""慢""延迟高""OOM""内存泄漏" / "performance""optimize""slow""high latency""memory leak" | /team-perf |
[--auto] [--once] [--focus] [--lang] |
| "安全审计""安全扫描""漏洞""安全检查""渗透""安全隐患" / "security audit""vulnerability""security scan""penetration test" | /team-security |
[--auto] [--once] [--scope] [--lang] |
| "测试策略""测试覆盖率""补测试""flaky test""测试金字塔""缺少测试" / "test strategy""test coverage""missing tests""flaky tests""test pyramid" | /team-test |
[--auto] [--once] [--focus=unit|integration|e2e|all] [--fix] [--lang] |
| "威胁建模""STRIDE""DREAD""攻击面""威胁分析" / "threat model""STRIDE""DREAD""attack surface""threat analysis" | /team-threat-model |
[--auto] [--once] [--framework=stride|dread|both] [--scope] [--lang] |
| "无障碍""WCAG""可访问性""accessibility""ARIA""屏幕阅读器" / "accessibility""WCAG""a11y""screen reader""ARIA" | /team-accessibility |
[--auto] [--once] [--level=A|AA|AAA] [--fix] [--lang] |
| "契约测试""API 兼容性""breaking change""消费者驱动" / "contract test""API compatibility""breaking change""consumer-driven" | /team-contract-test |
[--auto] [--once] [--style=pact|openapi|grpc|auto] [--scope] [--lang] |
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.
- 5d ago First seen · 379 lines · 0 tokens per session scan A d4fbfee4241c
team is a skill published in the GitHub repository ketor/cto-fleet (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 8,517 once invoked, about $0.0005 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…