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 asset-mapping-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/asset-mapping-playbook)<a href="https://agentmods.dev/skills/seaof0/dsh-redteam-model/asset-mapping-playbook"><img src="https://agentmods.dev/badge/skills/seaof0/dsh-redteam-model/asset-mapping-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/asset-mapping-playbook"><img src="https://agentmods.dev/badge/skills/seaof0/dsh-redteam-model/asset-mapping-playbook.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 | $0.00208 | $0.03411 |
| Opus 5.5 | $0.00083 | $0.01364 |
| Sonnet 5.5 | $0.00042 | $0.00682 |
| Haiku 4.5 | $0.00021 | $0.00341 |
Grade A, and why
asset-mapping-playbook scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
tools: curl, dig, python3 How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
资产测绘作战手册
本技能随 asset-mapping 预设走。 persona 中的硬规则(准确性>数量、只读探测、scope 白名单、表达纪律、删除纪律)不在此重复。 管线脚本随本技能目录自带:
scripts/(s0→s7 + fpdb_update + _common)与assets/(模板与种子库)。以下$S指本技能目录(从技能目录解析获得),所有脚本在测绘工作目录<work>下运行(--work参数)。
0. 定位与口径
把一个集团企业(母公司 + 授权二级/三级单位)的公网资产测成一份可审计的测绘 Excel:每条资产有归属单位、ICP 备案、来源、指纹、关联度。
- 口径 = 范围内单位全部公网资产;准确性优先于数量——一条错归属比漏十条更伤。
- 止步于测绘 + 指纹(只读、温和速率);打点/弱口令/漏洞利用走攻击类模式与各自授权。
- 交付物落工作区根目录(
<项目名>_资产测绘_<日期>.xlsx),不落 reports/。
1. 启动检查(每次先做)
key 三分支(按序判定):
<work>/keys.json存在且非空 → 照常用,先跑--doctor体检每个 key 的有效性与剩余配额(Hunter 体检耗 1 积分,其余免费),并打印能力矩阵(ICP 反查/证书 org 反查/中文公司名反查是否可用)。- keys.json 缺失或为空 → 脚本自动只读探测
~/.dsh/hunter/hunter.db(dsh-hunter 已配的 fofa/hunter/quake key):有则进程内借用(输出标注「来源: dsh-hunter」,不落盘),doctor 照常体检;读取失败静默当无。 - 全无 key → 询问用户是否提供(附各平台申请地址,见 refs/api-docs.md);用户不给则走免费降级链:crt.sh/RapidDNS 子域 → DNS 存活/泛解析 → 温和探测 + 种子指纹(缺平台查询 = 缺 ICP 反查与组件字段,资产面收窄到子域名展开,如实告知用户)。
前置输入两文件(模板在 assets/):
keys.json:五平台密钥(FOFA/Hunter/Quake/ZoomEye/Shodan),缺哪个跳过哪个,不强制配齐。scope.json:授权范围。units[]= 单位名 + 主域 + 备案号;sub_overrides= 手工归属例外;group_domains_out_of_scope= 集团域(未授权子域一律范围外);keywords= 靶标关联度打分词。初稿允许只有单位名和少量主域——S1/S2 会迭代补全。
python3 $S/scripts/s0_expand.py --work <work> --doctor # 启动体检(key 三分支内建于脚本)
2. S0 目标展开 + 范围定界(半自动,有人工核对关卡)
用户给五种入口之一,统一展开成 scope 草稿:
python3 $S/scripts/s0_expand.py --work <work> --domain a.com,b.com # 域名入口
python3 $S/scripts/s0_expand.py --work <work> --ip 1.2.3.4 # IP 入口(--cidr 1.2.3.0/24)
python3 $S/scripts/s0_expand.py --work <work> --group "XX集团" # 集团/单位名入口(--unit 同)
python3 $S/scripts/s0_expand.py --work <work> --keyword "XX平台" # 关键字入口(给查询词建议)
- 域名入口:FOFA
domain=/ Hunterdomain.suffix=小样本(50 条)→ 备案号 + 关联主域候选。 - IP/CIDR 入口:FOFA
ip=反查归属 → 写入草稿targets_ip,s5 阶段网段内资产自动算范围内。 - 集团名入口:Hunter
company="名"(中文备案公司名,唯一支持)+ FOFAorg="名"(证书 O 字段,多为英文)→ 主体/备案号/主域候选。多级控股子公司穿透(二级/三级/四级/全资)全自动不可行——按脚本输出的 checklist 走爱企查 BFS(持股 ≥50% 或授权口径,深度 ≤4),操作矩阵见 refs/osint-sources.md §1。 - 注册域归约内置国内二级后缀处理(com.cn 等),不会把
sub.n1b.com切错成三段。
What ships with it
14 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/excel_template.xlsx 14 KB
- assets/fpdb_seed.json 9.1 KB
- assets/keys.example.json 637 B
- assets/scope.example.json 1.5 KB
- scripts/_common.py 9.7 KB runs code
- scripts/fpdb_update.py 6.3 KB runs code
- scripts/s0_expand.py 17 KB runs code
- scripts/s1_scope_tools.py 3.3 KB runs code
- scripts/s2_engines.py 17 KB runs code
- scripts/s3_subdomains.py 3.0 KB runs code
- scripts/s4_dns_alive.py 4.6 KB runs code
- scripts/s5_dedupe.py 8.1 KB runs code
- scripts/s6_probe_fp.py 9.7 KB runs code
- scripts/s7_excel.py 11 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 · 141 lines · 208 tokens per session scan A 7e3a5a2efca6
asset-mapping-playbook is a skill published in the GitHub repository SeaOf0/dsh-redteam-model (716 stars, last pushed 2d ago), licensed MIT. It adds 208 tokens to every session and 3,411 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-12.
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.
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.
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.
webnovel-plan
A planning tool for turning a web-novel outline into volume plans, timelines, and chapter outlines. It also writes new story settings back into the existing setting collection.