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 thoughtbot/rails-consultant --skill domain-modelgit clone --depth 1 https://github.com/thoughtbot/rails-consultantWrote 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/thoughtbot/rails-consultant/domain-model)<a href="https://agentmods.dev/skills/thoughtbot/rails-consultant/domain-model"><img src="https://agentmods.dev/badge/skills/thoughtbot/rails-consultant/domain-model/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/thoughtbot/rails-consultant/domain-model"><img src="https://agentmods.dev/badge/skills/thoughtbot/rails-consultant/domain-model.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 | $0.00013 | $0.02070 |
| Opus 5.5 | $0.00005 | $0.00828 |
| Sonnet 5.5 | $0.00003 | $0.00414 |
| Haiku 4.5 | $0.00001 | $0.00207 |
Grade A, and why
domain-model 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 today.
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 model
The user describes how their business actually works. You come back with the concepts hiding in that description — and every one of them traces to something they said. An invented model is worse than none: it's fluent, confident, wrong, and in six months it's in the code under a name nobody in the business recognizes.
Five things come out, and nothing else:
| Language | The words the business uses, meaning what the business means. |
| Flow | The events, in order. Past tense — something became true. |
| Rules | Whenever X happens, we do Y. The branches and the exceptions. |
| Aggregates | Whatever protects a rule and emits those events. |
| Contexts | Where a word stops meaning one thing and starts meaning another. |
No entities-versus-value-objects, no repositories, no schema, no class diagram — those are implementation, and this is what implementation gets checked against. Don't read code either. The code already chose names, and the ones it chose are the loudest thing in the room; read them and they end up in the model, at which point the model can only tell you what the code already says.
Workflow
- Capture the process in the user's words.
- Harvest the language before interpreting any of it.
- Interview in rounds, leading with a proposed model.
- Fill in the template and paste it whole for review — the only gate, and nothing reaches disk the user hasn't read in a message first.
- Write to
docs/domains/<slug>.mdand tell the user the path.
1. Capture the process
The process, if the user passed one: $ARGUMENTS
That may be prose or a path — a transcript, a ticket, meeting notes. Read the file if it's a path. If it's empty, ask them to walk you through how the process works today, including the parts done by hand and the exceptions, because the exceptions are where the domain lives.
What ships with it
1 file 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.
- today First seen · 99 lines · 13 tokens per session scan A 566a11a124c3
domain-model is a skill published in the GitHub repository thoughtbot/rails-consultant (29 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 2,070 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 2026-11-07.
domain-model compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| domain-modelthoughtbot/rails-consultant | Skill | 29 | today | MIT | A | 13 | Claude Code |
| csiftwdhwg001/csift | Skill | 34 | 1mo ago | MIT | A | 227 | Claude Code, Codex |
| recursive-decompositionmassimodeluisa/recursive-decomposition-skill | Skill | 54 | 1mo ago | MIT | A | 144 | Claude Code |
| flowsvictorgrein/spec-crew | Skill | 8 | 8mo ago | none | A | 43 | Claude Code, Codex |
| core-buildvictorgrein/spec-crew | Skill | 8 | 8mo ago | none | A | 38 | Claude Code, Codex |
| tools-expertvictorgrein/spec-crew | Skill | 8 | 8mo ago | none | A | 50 | Claude Code, Codex |
| orchestration-governancevictorgrein/spec-crew | Skill | 8 | 8mo ago | none | A | 27 | Claude Code, Codex |