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 red-team-command-doctrinegit 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/red-team-command-doctrine)<a href="https://agentmods.dev/skills/seaof0/dsh-redteam-model/red-team-command-doctrine"><img src="https://agentmods.dev/badge/skills/seaof0/dsh-redteam-model/red-team-command-doctrine/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/red-team-command-doctrine"><img src="https://agentmods.dev/badge/skills/seaof0/dsh-redteam-model/red-team-command-doctrine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.00956 |
| Opus 5 | $0.00024 | $0.00478 |
| Sonnet 5 | $0.00010 | $0.00191 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
red-team-command-doctrine 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 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.
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.
What it actually says
红队指挥决策
Domain
当前处于红队指挥决策领域。 本 skill 是攻击阶段选择、路由决策、详细包选择和 OPSEC 感知推进的紧凑治理技能。 在红队模式激活时使用此 skill 进行阶段/路由决策。它不直接执行攻击，只负责选择正确的阶段、路由和叶子技能。
阶段矩阵：
| Phase | Goal | Typical Router | Exit Signal |
|---|---|---|---|
| recon | 建立目标画像 | recon-for-sec | 足够证据选择一条候选路径 |
| web | 证明一条 web 攻击路径 | auth-sec / api-sec / injection-checking | 一条可复现路径或排除分支 |
| ad | 选择最安静的域路径 | AD routers | 一条有证据的可行域路径 |
| postex | 分类立足点和下一跳 | post-exploitation-playbook | 下一跳或目标已识别 |
| reverse | 恢复执行链 | malware-loader-analysis | 执行链或可利用性已澄清 |
| code-audit | 证明一条输入到 sink 的链 | auth-sec / api-sec / injection-checking | 一条受控路径已演示 |
| payload | 塑造投递 | weaponization-and-payloads | 投递约束已匹配 |
| evasion | 选择最低噪声绕过 | windows-av-evasion | 绕过路线已选择或已排除 |
| jailbreak | 验证模型指令与破甲行为 | llm-prompt-injection | profile 切换和回归证据已确认 |
路由规则：phase → router → leaf skill
方法层默认映射：
- web/ad/reverse/code-audit → investigation-first
- postex → concentrate-forces
- payload/evasion/jailbreak → practice-cognition
- 多路径竞争时升级到 contradiction-analysis
- 需集中主攻时升级到 concentrate-forces
Boundaries
- 不得跳过阶段判断直接进入攻击。
- 不得无视 OPSEC 检查清单。
- 不得伪造阶段完成标志。
- 不在缺少证据时声明阶段完成。
- 不超出授权目标范围。
- 不把候选路径等同于已验证路径。
- 如果 scope、target 或授权边界不明确，进入 blocked 或 plan-only。
Pivot Hints
- 如果当前阶段缺少退出证据，补齐最小必要上下文再判断。
- 如果多条路径竞争，使用 contradiction-analysis 选择主要矛盾。
- 如果任务跨多阶段，切换到结构化编排（recon→strategy→exploit-dev→review→reporting）。
- 如果技术路径已可见，优先选择匹配的 detail-pack 而非抽象方法论。
- 如果检测面过大，优先选择低噪声路径。
- 如果被中断，确认当前状态可恢复后再继续。
OPSEC Gates
每次行动前检查：
- 是否存在更低噪声的路径可以先证明？
- 是否在没有新证据的情况下扩大范围？
- 此动作是否会生成可避免的日志、认证事件或扫描？
- 能否使用原生证据（Burp、CLI、主机事实）而非假设？
- 下一步是否直接关联目标？
- 是否会烧掉当前访问、凭据或基础设施？
- 预期收益是否证明检测面合理？
- 如果现在中断，当前状态是否可恢复？
Exit Evidence
Required artifacts:
- phase_selection
- route_decision
Minimum attempts for negative result: 2
Positive exit requires:
- 阶段选择有明确证据支撑。
- 路由决策基于目标特征而非猜测。
- 选定的 leaf skill 与当前证据匹配。
Negative exit requires:
- 记录已评估的阶段和路由。
- 记录为什么无法选定路径。
- 不声明目标不可攻击，只声明当前证据下无法选定攻击路径。
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 · 85 lines · 49 tokens per session scan A d1a84ca0c5d8
red-team-command-doctrine is a skill published in the GitHub repository SeaOf0/dsh-redteam-model (377 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 956 once invoked, about $0.0002 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 2026-09-03.
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…