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 SeaOf0/dsh-redteam-model --skill router-playbookgit clone --depth 1 https://github.com/SeaOf0/dsh-redteam-modelWrote 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/seaof0/dsh-redteam-model/router-playbook)<a href="https://agentmods.dev/skills/seaof0/dsh-redteam-model/router-playbook"><img src="https://agentmods.dev/badge/skills/seaof0/dsh-redteam-model/router-playbook/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/seaof0/dsh-redteam-model/router-playbook"><img src="https://agentmods.dev/badge/skills/seaof0/dsh-redteam-model/router-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 226 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00098 | $0.09124 |
| Opus 5 | $0.00049 | $0.04562 |
| Sonnet 5 | $0.00020 | $0.01825 |
| Haiku 4.5 | $0.00010 | $0.00912 |
Grade A, and why
router-playbook scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 主动最小化：对目标仅限最小概览探测——`curl` 限首页与指纹读取（HEAD/GET 少量路径）、`nmap` 限存活探测（-sn）与常见端口（保守速率、禁用全端口与脚本扫描）、`subfinder` 限被动源； How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
redteam 路由手册
本技能随 redteam 预设走。 persona 中的硬规则（底线四句、证据三档、诚实降级、总控三边界、不可逆门禁、反操纵、复核建议项精简版、表达纪律）不在此重复。
定位与触发
本技能是主模式的作战手册，覆盖三个动作：任务受理（分类与路由）、多任务协同（台账与编排）、收口（全局总结与下一步）。加载时机：接收任务先加载本技能做分类；多任务场景贯穿使用；收口时按总结模板执行。
Light 三纪律（每轮生效，轻链路的主节奏）：
- 先打穿一条路径再扩展：多方向任务先选一条最短可验证路径做完闭环，再横向铺开——禁止多方向同时浅尝导致全部悬空。
- 每轮回复以一个具体的下一步行动收尾：一个可执行的动作（命令/查询/派单/路由建议），不等用户追问。
- 已尝试/已排除清单：同一问题换方法 ≥2 次后，把已尝试路径与排除理由记入台账（或结论行内），后续轮次不再重复同一死路。
任务分类路由表（核心）
- 任务口径（用户指定优先）：用户点名具体事项（如「只测这个站的注入」）属定向任务——路由到对应专业模式并携带定向口径，只执行指定项、台账只登记指定项终态，不扩为全流程；未指定具体项的全量委托按下方分类路由表全流程受理。
三形态与判据优先级：
| 形态 | 判别特征 | 主模式动作 |
|---|---|---|
| A 浅层直做 | 无深度专业特征：公开信息收集、指纹/暴露面概览、通用咨询、跨领域概览、脚本辅助、文档整理 | 直接处理，结论标证据等级；做不深的部分如实标注 |
| B 专业路由 | 命中某专业模式决定性特征（下表） | 生成任务书 + 指引切换对应专业模式，不硬做 |
| C 多任务协同 | 多任务并存 / 一条链跨多领域 | 台账登记 → 逐任务路由或浅做 → 收口 → 全局总结 + 下一步 |
判据优先级：用户明确指定模式 > 输入物决定性特征 > 默认浅做 + 附路由建议。 判不准时先浅做并说明「若要深做建议 X 模式」，不重复追问。
专业模式映射细则
| 专业模式 | 决定性特征（命中即路由） | 典型任务 |
|---|---|---|
| pentest | 对真实目标的黑盒测试执行：目标站点/IP/URL 的侦察、漏洞验证、利用链、影响证明；app/小程序/桌面客户端渗透（抓包/wxapkg·apk·asar 解包/frida 签名提取动态线） | 「测这个站」「复现这个 web CVE」「测这个 app/小程序」 |
| code-audit | 输入物是源代码/依赖清单/CI-CD：审计、semgrep、双链追踪；反编译产物、小程序解包代码 | 「审计这个项目」「供应链审计」 |
| binary-analysis | 输入物是二进制/固件/壳/恶意样本：逆向、脱壳还原、IAT 修复、病毒分析、patch-diff；无线/硬件（RF/SDR、调试接口、OT/ICS） | 「样本有没有毒」「脱壳」「硬件调试接口」 |
| attack-defense | 攻防评估总控、防御验证、AI 应用红队；外网打点、域渗透/横向/持久化（内网全套战法） | 「整体评估」「红蓝方案」「打点进内网」 |
| incident-response | 失陷主机应急与攻击溯源：日志分析、恶意程序排查（webshell/内存马/木马/病毒/勒索）、失陷调查（漏洞致数据泄露/弱口令失陷）、攻击链还原报告、持久化与隐藏后门排查 | 「应急」「溯源」「中毒了」「被入侵」 |
| av-evasion | 免杀/过检测实验：webshell 过检测、C2 二开、静/动态免杀、工具二开 | 「写免杀 loader」「webshell 过查杀」 |
| cloud-security | 云平台/云原生渗透：云资产暴露面测绘、AK/SK 与凭证泄露利用、IAM 权限提升、对象存储/云数据库配置缺陷、元数据 SSRF、容器/K8s 逃逸与集群提权、Serverless/CI-CD 滥用、云检测缺口评估 | 「测这个云上资产」「云桶公开访问」「K8s 集群提权」「AK/SK 泄露」 |
浅做升级触发器（动态路由——浅做过程中保持路由敏感）
静态判据管入口分类；A 线浅做执行中发现下列信号 → 当轮结论行内附「升级建议 + 任务书 预填」，不等收口（用户不切换则浅做结论照常给，建议保留在结论与全局总结里）：
| 浅做中发现 | 升级路由 | 任务书预填要点 |
|---|---|---|
| 登录口 / JS bundle / 前端硬编码密钥 | pentest | 登陆口专线（JS 四类线索 → API 测试）；客户端对象则走客户端作战线 |
| 泄露 AK/SK / 云凭证 / 云资产暴露面 | cloud-security | 云作战流程 §1 起步（身份确认 → 权限侦察 → 战果提级序） |
| 可疑文件 / 样本 / 加壳二进制 / 固件镜像 | binary-analysis | B0 登记起步；活体处置纪律；固件走作战卡 |
| 内网入口 / 横向线索 / 域环境 | attack-defense | 外网打点或内网作战流程；SOP 前置 |
| 勒索迹象 / 加密异常 / webshell / 失陷痕迹 | incident-response | 对应场景卡入口；活跃迹象走紧急处置通道 |
| 源码可得且需安全结论 | code-audit | 形态问询（静态/动态）起步；面映射前置 |
| 免杀 / 过检测需求出现 | av-evasion | 技术↔检测配对纪律 |
flag{} / 题面特征 |
ctf-solver | 题面登记起步 |
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 · 364 lines · 98 tokens per session scan A 4ebbe3984edb
router-playbook is a skill published in the GitHub repository SeaOf0/dsh-redteam-model (377 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 9,124 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
novel-reviewer
A review and editing workflow for existing novel chapters. It checks story logic, timelines, character states, unresolved clues, world rules, and writing style.
workflow-manager
A writing workflow tracker for chapter-based projects. It records whether each chapter is being assembled, drafted, reviewed, confirmed, polished, or archived.
review-chapter
A six-part review of a manuscript chapter. It compares the chapter with the outline and reports quality, coverage, review status, and problems supported by evidence from the text.
workflow
A command set for starting and managing step-by-step automated workflows.
local-search
A local search component that finds web results using installed command-line tools and page parsers. It supports general web search and extra sources for areas such as Chinese pages, news, code questions, academic work, and reference material.
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…