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 packergit 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/packer)<a href="https://agentmods.dev/skills/seaof0/dsh-redteam-model/packer"><img src="https://agentmods.dev/badge/skills/seaof0/dsh-redteam-model/packer/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/packer"><img src="https://agentmods.dev/badge/skills/seaof0/dsh-redteam-model/packer.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 | $0.00103 | $0.01343 |
| Opus 5.5 | $0.00041 | $0.00537 |
| Sonnet 5.5 | $0.00021 | $0.00269 |
| Haiku 4.5 | $0.00010 | $0.00134 |
Grade A, and why
packer 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 1mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Packer - Shellcode 免杀加载器一键打包
概述
本 skill 采用"入口文档 + 参考文档"结构。SKILL.md 只保留主流程与关键约束，详细实现、验证、排障下沉到 references/。
首次使用建议先阅读： references/layout.md → references/techniques.md → references/gostager.md
完整阅读路径见：references/overview.md
资源索引
tools/sgn.exe、tools/keystone.dll：外部二进制工具（版本见tools/README.md）scripts/encrypt.go、scripts/encrypt_ipv4.go、scripts/parse_stager.py：辅助脚本scripts/build_qvm.py：QVM 专项构建脚本（UUID编码 + Go源码生成 + 编译 + Overlay注水 + PE修复）scripts/verify_pre.py、scripts/verify_pe.py：编译前/后验证脚本assets/versioninfo.json：静态资源模板references/overview.md：文档导航与阅读路径references/layout.md：目录职责约定references/techniques.md：注入技术与SyscallN参数表references/defense-modules.md：防御模块实现模式references/encryption.md：加解密逻辑参考references/randomization.md：随机化规范references/gostager.md：Go stager 详细流程references/verification.md：编译前/编译后验证references/troubleshooting.md：故障排查总表（含体积分诊表）references/qvm-bypass.md：360 QVM 专项免杀（UUID + Fiber + IAT欺骗 + Overlay注水 + PE元数据修复）
全局约束
- 命令中的 Python 统一写作
<python命令>，先通过环境检查确定是python3还是python。 - Windows 环境默认输出目录使用项目内
result/，不使用/tmp/。 gostager分支中下游字段以scripts/parse_stager.py输出 JSON 为唯一来源。sgn.exe属于二进制工具，放tools/；源码脚本放scripts/（见references/layout.md）。- 每次编译前必须清理上次运行残留的生成文件（
result/*.go、result/*.exe、result/.eout.txt等），确保本次编译不受上次遗留文件干扰。上次产物在两次生成之间保留，方便排查失败原因。清理方式见references/verification.md。 - Go 编译必须使用
-trimpath -ldflags="-s -w -H windowsgui"。-s去符号表、-w去调试信息、-H windowsgui隐藏控制台。跨平台命令写法见references/gostager.md。
主流程
Step 0: 环境检查
- 检测 Python（bash:
python3 --version || python --version/ CMD:python --version） - 记录统一命令占位：
<python命令> - 检测 Go、依赖与 Windows 路径约束
Step 1: 确认输入参数
.bin路径、输出目录（默认result/）、可选模块与 SGN 开关- 体积分诊： 用
<python命令> -c "import os;print(os.path.getsize('<file>'))"获取文件体积，按阈值分流。分诊表见references/troubleshooting.md。 - 用户可通过
--mode gostager或--mode createthread显式指定，跳过体积判断。
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/versioninfo.json 935 B
- README.md 2.5 KB
- references/defense-modules.md 4.8 KB
- references/encryption.md 2.4 KB
- references/gostager.md 2.4 KB
- references/layout.md 1.1 KB
- references/overview.md 1.6 KB
- references/qvm-bypass.md 11 KB
- references/randomization.md 3.9 KB
- references/techniques.md 15 KB
- references/troubleshooting.md 8.1 KB
- references/verification.md 3.4 KB
- scripts/build_qvm.py 13 KB runs code
- scripts/encrypt_ipv4.go 1.9 KB
- scripts/encrypt.go 1.8 KB
- scripts/parse_stager.py 6.6 KB runs code
- scripts/verify_pe.py 1.6 KB runs code
- scripts/verify_pre.py 4.4 KB runs code
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.
- 1mo ago First seen · 77 lines · 103 tokens per session scan A 1d8ae6379676
packer is a skill published in the GitHub repository SeaOf0/dsh-redteam-model (747 stars, last pushed 10d ago), licensed MIT. It adds 103 tokens to every session and 1,343 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
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.
video-recap
A workflow that turns a supplied video into a Chinese narrated recap by combining video understanding, story planning, editing, voiceover, and final assembly.
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.
linglu-discipline
A set of 16 operating rules for an AI coding agent, including when to read or write long-term memory and how to report completed actions. It is designed to work with the Lingshu memory service through an MCP connection.
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.