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 skills add ketor/cto-fleet --skill team-perfgit 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-perf)<a href="https://agentmods.dev/skills/ketor/cto-fleet/team-perf"><img src="https://agentmods.dev/badge/skills/ketor/cto-fleet/team-perf.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 | $0.00130 | $0.08896 |
| Opus 5 | $0.00065 | $0.04448 |
| Sonnet 5 | $0.00026 | $0.01779 |
| Haiku 4.5 | $0.00013 | $0.00890 |
Grade B, and why
team-perf scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- 目录路径:`/tmp/{team-name}/`(team lead 在 TeamCreate 后执行 `mkdir -p /tmp/{team-name} && chmod 700 /tmp/{team-name}`) How it starts
The opening of the file, as written. The whole thing — 614 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble (run first)
_UPD=$(~/.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)--focus=dim1,dim2:聚焦性能维度(可选值:cpu/memory/io/latency/throughput,默认全面分析)--lang=zh|en:输出语言(默认zh中文)
解析后将标志从性能问题描述中移除。
| 模式 | 用户确认范围 | 条件节点处理 |
|---|---|---|
| 标准模式(默认) | 每轮优化方案确认 + 基准对比确认 | 正常询问用户 |
单轮确认模式(--once) |
仅首轮瓶颈分析确认 + 收尾汇总 | 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 |
单轮确认模式下自动决策规则:
- 瓶颈优先级不确定 → 按影响度排序,优先处理延迟和吞吐量影响最大的瓶颈
- 优化方案有多种选择 → 采纳对应分析维度 analyzer 的建议
- 迭代超 3 轮仍未达目标 → 不可跳过,必须暂停问用户(熔断机制)
- 优化后性能反而下降 → 不可跳过,必须暂停问用户(熔断机制)
- 双 analyzer 结论冲突 → optimizer 优先处理两者共识部分,冲突部分升级 team lead
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(迭代超 3 轮、优化后性能下降时仍必须暂停问用户)。
使用 TeamCreate 创建 team(名称格式 team-perf-{YYYYMMDD-HHmmss},如 team-perf-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):
- 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
- 目录路径:
- 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)
- 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
- 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
- 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
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 · 614 lines · 0 tokens per session scan B b70460d45fe7
team-perf is a skill published in the GitHub repository ketor/cto-fleet (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 130 tokens to every session and 8,896 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.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.