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 ecosystem-cooperationgit 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/ecosystem-cooperation)<a href="https://agentmods.dev/skills/seaof0/dsh-redteam-model/ecosystem-cooperation"><img src="https://agentmods.dev/badge/skills/seaof0/dsh-redteam-model/ecosystem-cooperation/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/ecosystem-cooperation"><img src="https://agentmods.dev/badge/skills/seaof0/dsh-redteam-model/ecosystem-cooperation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00179 | $0.07221 |
| Opus 5 | $0.00089 | $0.03610 |
| Sonnet 5 | $0.00036 | $0.01444 |
| Haiku 4.5 | $0.00018 | $0.00722 |
Grade C, and why
ecosystem-cooperation scanned grade C with 2 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
不用 never refuse 类措辞（强 RLHF 模型上那类词反而升高拒答率）。 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| HTTP 客户端 | `curl`（参数跨平台兼容） | 同左 | **`curl.exe`**（PowerShell 中 `curl` 是 Invoke-WebRequest 别名） | How it starts
The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
九预设动态生态协作规则
本技能被九个预设共同加载（位于
plugins/dsh-redteam-model/shared/skills/）。
核心原则
模式是主镜头，不是边界。 九个预设（redteam 总入口 + 八专业模式 pentest / code-audit / binary-analysis / attack-defense / av-evasion / incident-response / cloud-security）是一个动态生态：当前模式决定本次任务以什么为主， 但当任务需要其他模式的能力时，应当按生态规则配合，而不是在边界内硬撑。
- 需要其他模式的方法论 → 加载对应 playbook 技能（七个 playbook 都在你的技能目录里）。
- 需要其他模式的执行 → 派子代理按该模式的 playbook 干活，产物回主模式合并。
- 结果不确定或过复杂 → 按 persona 的 claude 规则升级。
主镜头选择与切换
初始镜头按任务输入选：
| 任务输入 | 主镜头 |
|---|---|
| 通用/不确定/多领域混合、信息收集概览、多任务并行组织 | redteam 总入口（浅做 + 深度即路由，见 router-playbook） |
| 黑盒目标 / 资产清单，要全面漏洞挖掘与验证（全等级穷尽、SRC 式） | pentest（SRC/众测语义走其「SRC 挖掘作战线」） |
| 源码 / 反编译产物 / 小程序解包代码，要代码级结论 | code-audit |
| 二进制样本 / 需要脱壳还原 | binary-analysis |
| 全链路评估 + 防御视角 + 评分 + 复测闭环（渗透定位=打点，拿到立足点即转横向主线） | attack-defense |
| 免杀技术研究与检测配套 | av-evasion |
| 失陷主机调查 / 日志与样本排查 / 应急响应与攻击链还原报告 | incident-response |
| 云平台 / 云原生目标（AWS/Azure/GCP/阿里云/腾讯云/华为云、K8s/容器/Serverless），要云攻击路径验证与权限链收口 | cloud-security |
| CTF 竞赛解题（赛题/题目环境/附件，要 flag 与解题复盘） | ctf-solver |
升级路径：redteam 总入口命中某专业模式决定性特征（router-playbook 路由表）→ 生成任务书、 指引切换对应专业模式会话——总控只消费其 gate-pass 落盘产物做汇总，不代专业判定。
会话中引入其他镜头的时机：
- 白盒线索需要代码定位 → 拉 audit-playbook。
- 黑盒打到可疑样本 → 交 binary-analysis（按下方落盘约定移交）。
- 需要总评估 / 评分 / ATT&CK 映射 → attack-defense 收口。
- 需要检测侧情报（检测面/规则建议） → av-playbook 检测侧章节（OPSEC 情报，按任务流动）。
切镜头不改报告归属：仍按发起任务的主模式出报告。
会话拓扑
三种拓扑都是正选项，由任务形态决定，不是演进关系：
| 任务形态 | 拓扑 | 说明 |
|---|---|---|
| 单一镜头能完成 | 单会话 | 跨模式需求走机制内做法：加载他模式 playbook，或派按该 playbook 干活的子代理（子代理经 composeFrom 继承本会话组合） |
| 多战线并行 / 多目标 | 多会话并行 + 文件交接 | 每战线一个模式会话；共享状态=工作区落盘；各自门禁各自管 |
| 单一评估需多模式收口（全链路评估 / AEV 复测闭环） | 总控 + 工作会话 | 总控 = attack-defense 会话本身（其编排章的总控本职），不发明新实体 |
总控边界三条：
- 总控只编排/收口/报告，不替工作会话做模式内门禁判定（各自复核员管各自 gate）。
- 总控消费的唯一形式 = 对方落盘的 gate-pass 产物——无 gate-pass 不收（与其报告只收 gate-pass finding 的规则一致）。
- 总控的跨会话可见性来自读工作区（evidence-index / coverage 表），不假设任何实时通道； 需要更好的协调能力属第 9 步 backlog，不提前做。
跨会话交接硬规则：唯一合法通道 = 落盘三步（产物 + provenance + 索引）； 禁止在会话里口头引用「另一个会话里看到的」——不可复现即不可用。
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 · 316 lines · 179 tokens per session scan C 6dec77027a90
ecosystem-cooperation is a skill published in the GitHub repository SeaOf0/dsh-redteam-model (377 stars, last pushed yesterday), licensed MIT. It adds 179 tokens to every session and 7,221 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 2 findings (tells the agent never to refuse, 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…