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 agentmods add skills/zxpmail/reqforge/domain-mappernpx skills add zxpmail/ReqForge --skill domain-mappergit clone --depth 1 https://github.com/zxpmail/ReqForgeWhat 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 | $0.00000 | $0.01286 |
| Opus 5 | $0.00000 | $0.00643 |
| Sonnet 5 | $0.00000 | $0.00257 |
| Haiku 4.5 | $0.00000 | $0.00129 |
Grade A, and why
domain-mapper 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 2d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: domain-mapper description: Used when the user wants to research a domain, industry, market, technology, codebase, or competitor — turning scattered/unstructured information into a structured Markdown database (domain-map.md). Triggers on phrases like "帮我研究一下", "分析一下这个", "我不太熟悉这个领域", "拆一下这个行业/代码库". version: 1.0.0 updated: 2026-06-08 requires: []
[Task] Transform unstructured/sprawling domain knowledge into a structured Markdown database, independent of any product spec flow.
**Core pipeline**: Scope definition → Domain Snapshot (domain-map.md) → optional Deep-Dive (competitor-analysis.md) → optional Social/Media Analysis (social-analysis.md) → Synthesis (update domain-map.md).
**Depth levels**:
- L1 Snapshot: 30-min pass, only domain-map.md output
- L2 Standard: 1-2h, domain-map.md + competitor-analysis.md
- L3 Deep: Half-day, full 5-step pipeline
The output is a living document: timestamped, source-attributed, and designed to be revisited when the domain evolves.
[Not For] - Writing product requirements -> use /product-spec-builder instead - Fixing bugs -> use /bug-fixer instead - Code review -> use /code-review instead - General web search without structure -> use direct WebSearch or /deep-research instead
[Dependency Check] No required prerequisite files. This skill can always run from a blank project.
- If domain-map.md already exists for the same domain, warn about staleness (check timestamp in file header) and ask whether to regenerate or append.
- If Product-Spec.md exists, read it for context but do not modify it.
[First Principles]
→ references/first-principles.md
[Shared Discipline]
Karpathy 四原则 → ../_shared/karpathy-discipline.md
Source attribution required on every claim → see workflow.md §源标注
[HARD-GATE]
Until domain-map.md is saved and the user confirms the snapshot:
- MUST NOT proceed to Step 3 (Deep-Dive) or Step 4 (Social/Media)
- MUST NOT modify Product-Spec.md, DEV-PLAN.md, or source code
- MUST NOT treat "looks good in chat" as confirmation — user must confirm the saved file
[Output Style] → 每个输出文件头部包含生成时间戳 → 每一条关键信息附来源 URL（不可溯源标注 ⚠️） → 每步完成输出一个文件，不把所有信息挤在同一份报告里
[Output Artifacts] - domain-map.md — 结构化领域数据库（所有深度级别） - competitor-analysis.md — 对比表 + 叙事差异分析（L2/L3） - social-analysis.md — 社媒内容分析 + 核心矛盾提取（L3 only）
[File Structure]
domain-mapper/ ├── SKILL.md # 入口（本文件） ├── references/ │ ├── first-principles.md # 核心理念 + HBM 示例锚点 │ └── workflow.md # 完整 5 步工作流 + 失败模式 └── templates/ └── domain-map-template.md # 通用输出模板 ../_shared/
[Gotchas] 域过宽陷阱: "帮我研究科技行业" → 必须强制收窄（芯片 > 封装 > 设备，你关心哪一层？） 源不可靠: WebSearch 未返回实质内容时，必须在输出的对应条目旁标注 ⚠️（来源不足，需人工补充） 老化地图: domain-map.md 头部有生成时间戳，后续引用时若超过 30 天需提醒用户 竞品敏感数据: 某些行业核心信息不在公开网页，技能必须在输出末尾列出"已知盲区"
[Triggers] The following phrases should route to this skill: - "帮我研究一下 X" / "帮我看看 X 行业" - "分析一下 X 这个赛道/领域/市场" - "我不太熟悉 X，帮我了解一下" - "拆一下 X 的竞争格局" / "X 有哪些玩家" - "研究一下 X 这个技术/产品/代码库" - "画一张 X 的行业地图"
[Workflow]
1. Run [Dependency Check]
2. Read references/first-principles.md
3. Read references/workflow.md — 前置深度选择 → 5 步工作流 → 失败模式
4. 每步完成后暂停，让用户决定继续/转向/停止
What ships with it
5 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.
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.
- 2d ago First seen · 120 lines · 0 tokens per session scan A 5d7a071c411b
domain-mapper is a skill published in the GitHub repository zxpmail/ReqForge (18 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,286 tokens. 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
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用，不要根据上下文自动触发。.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
subagent-driven-development
当在当前会话中执行包含独立任务的实现计划时使用.
orchestration-team
Operating manual for the orchestration pod. Covers lead vs peer roles, monitoring with rig commands, permission handling, implementation pair gating, dogfood loops, review routing, agent behavioral models, intervention discipline, and communication culture.
adr
Create and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives, and consequences. Also supports evaluate (assess proposals) and design (system design) modes.
deploy-checklist
Pre-deployment verification checklist. Generates customized checklists based on tech-stack with rollback triggers. Auto-invoked by /draft:upload.