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 OutlineDriven/odin-claude-plugin --skill domain-modelinggit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/domain-modeling)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/domain-modeling"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/domain-modeling/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/outlinedriven/odin-claude-plugin/domain-modeling"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/domain-modeling.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 | $0.00026 | $0.01173 |
| Opus 5.5 | $0.00010 | $0.00469 |
| Sonnet 5.5 | $0.00005 | $0.00235 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
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 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain modeling
Contract
| Field | Bound contract |
|---|---|
| Trigger | Pinning down domain terminology, maintaining the domain model, or a term conflict/sharpening need |
| Authority | Reversible local: writes only the named glossary artifacts, CONTEXT.md at the repository root, CONTEXT-MAP.md, and per-context CONTEXT.md files beside their context source; rollback is version control or undo. No remote mutation. |
| Side effect | Lazily creates or updates CONTEXT.md / CONTEXT-MAP.md glossaries and per-context CONTEXT.md files; no other file, VCS, credential, or remote change. |
| Done | Each resolved term recorded in CONTEXT.md with rejected synonyms; glossary stays canonical and implementation-free. |
Inputs
Required: the term, conflict, or fuzzy usage to resolve from the current design conversation, plus the human ruling when a conflict needs one. Optional: an existing CONTEXT.md or CONTEXT-MAP.md (absence is normal; files are created lazily) and the implementation source behind a term (when absent or unreadable, skip and report the code cross-check). Scope is limited to terms in the current design work unless the invocation requests a repository-wide glossary sweep.
Procedure
- Load the layout. Check the repository root for
CONTEXT.mdandCONTEXT-MAP.md.CONTEXT.mdat the root means one context and one glossary.CONTEXT-MAP.mdat the root means several contexts: each context'sCONTEXT.mdsits beside that context's source, andCONTEXT-MAP.mdmaps them. Read the applicable glossary before judging any term. If neither exists, create nothing yet. Done when: the layout is determined and the applicable glossary is read (or confirmed absent). - Challenge conflicting terms. Compare each term used in the current design work against the glossary. The moment a use contradicts a glossary entry, state both meanings and ask which one is correct before continuing, for example, a glossary that defines cancellation as ending an Order versus a use that changes one Line Item. Done when: every conflicting term is surfaced with both meanings and the human ruling is requested.
- Sharpen fuzzy terms. When a name is vague or overloaded, pick the single domain term that owns the rule; every other name becomes a rejected synonym. Done when: each fuzzy term has one canonical owner and its rejected synonyms are named.
- Stress-test relationships. Construct an edge case that exposes a relationship boundary. For example, if one Order is split across two shipments, when may Billing issue the invoice? Resolve which term owns each side of the boundary. Done when: each relationship boundary is resolved with an edge case that exposes it.
- Check claims against code. Read the implementation behind each term under resolution. Surface any contradiction between the model and the code, then rule which is authoritative. When the code wins, correct the model term. This skill never edits code. If the implementation is unreadable or absent, skip the cross-check and mark it not performed. Done when: each term's code cross-check is completed or marked not performed with any contradiction surfaced and ruled.
- Record each resolution immediately. The moment a term resolves, write an entry to the applicable glossary file with exactly three parts: the canonical term, a one-line definition, and its rejected synonyms. Create
CONTEXT.md(one context) orCONTEXT-MAP.mdplus the per-contextCONTEXT.md(several contexts) only at this first write: never before there is something to record. Done when: each resolved term has a glossary entry with canonical term, one-line definition, and rejected synonyms. - Keep the glossary pure. Entries contain definitions and rejected synonyms only. Refuse implementation details, specification content, and scratch notes in glossary files; put them in their own artifacts or drop them. Done when: every glossary entry contains only definitions and rejected synonyms.
What ships with it
2 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.
- 1mo ago Changed · +7 lines · -38 tokens per session e1d5d701d5e1
- 1mo ago First seen · 34 lines · 64 tokens per session scan A 3e1c8e8f0c32
domain-modeling is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (39 stars, last pushed 25d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,173 once invoked, about $0.0001 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…