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/kensaurus/cursor-kenji/docs-domain-modelingnpx skills add kensaurus/cursor-kenji --skill docs-domain-modelinggit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/docs-domain-modeling)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/docs-domain-modeling"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/docs-domain-modeling.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.01015 |
| Opus 5 | $0.00027 | $0.00508 |
| Sonnet 5 | $0.00011 | $0.00203 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
docs-domain-modeling 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 yesterday.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Modeling
Degree of freedom: MIXED. Which term is canonical [HIGH freedom];
CONTEXT.md shape, lazy create, and the three ADR gates
[LOW freedom — run exactly].
A shared language between user, agent, and codebase pays off every session: consistent naming, fewer tokens spent describing concepts, and a codebase the agent can navigate by vocabulary. Adapted from mattpocock/skills (MIT).
This is the active discipline — challenging terms, inventing edge-case
scenarios, and writing the glossary and decisions down the moment they
crystallize. Merely reading CONTEXT.md for vocabulary is a one-line habit any
skill can do; this skill is for changing the model, not consuming it.
How to reason
- Observe — the word just used, and what CONTEXT.md already pins
- Interpret — conflict, overload, or a genuine new concept
- Classify — challenge / sharpen / write the glossary entry / offer an ADR
- Capture — write the moment it crystallizes; do not batch
Worked example
Observe: user says "account" for both the billing Customer and the login User; CONTEXT.md is empty;
accountsandauth.usersboth exist. Interpret: one word, two entities — the next session will keep writing the wrong one. Classify: sharpen now — Customer (billing party) vs User (login). Not an ADR: naming is still reversible. Write immediately:**Customer**: the billing party. _Avoid_: account, user
Self-critique before reporting
- Domain language — definitions are not table or column names
- Avoid filled — rejected synonyms are listed
- Inline, not batched — each resolved term is in CONTEXT.md this turn
- Right owner — INDEX.md / rejected alternatives →
docs-adr; interview-the-user →workflow-grilling
File structure [LOW freedom — this shape]
/
├── CONTEXT.md ← the glossary (create on first resolved term)
├── docs/adr/ ← architectural decision records
│ └── 0001-<dash-case-title>.md
└── src/
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.
- yesterday First seen · 99 lines · 54 tokens per session scan A a6c1869d3920
docs-domain-modeling is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 7d ago), licensed MIT. It adds 54 tokens to every session and 1,015 once invoked, about $0.0003 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
claude-code-repo-migration
Move or rename a git repo on disk without losing its Claude Code history — remap the session dir (/.claude/projects/ /) and the /.claude.json projects key so every past session still resumes from the new path with trust, allowedTools and MCP servers intact, and repair the git worktrees the move breaks. Use when moving…
project-docs-management
项目结构化知识库初始化，基于渐进式披露原则从零搭建AGENTS.md、架构.md和文档目录。仅用于首次建立知识库，后续维护和文档整理请使用 doc-gardener 技能。当用户提到"建立知识库""初始化文档""搭建文档结构"时使用。.
apple-notes-sync
将 Mac 备忘录同步到工作区并加入向量索引，实现语义搜索。当用户说"同步备忘录"、"把备忘录加入记忆"、或想搜索备忘录内容时使用。.
checkpoint
Save a session checkpoint — what was done, what's next, any blockers.
resume
Resume from last checkpoint — load full context and continue where you left off.
note
Quick note — save a decision, observation, or thought to persistent memory.