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 smixs/disruptor-skills --skill setting-up-domain-modelgit clone --depth 1 https://github.com/smixs/disruptor-skillsWrote 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/smixs/disruptor-skills/setting-up-domain-model)<a href="https://agentmods.dev/skills/smixs/disruptor-skills/setting-up-domain-model"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/setting-up-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/smixs/disruptor-skills/setting-up-domain-model"><img src="https://agentmods.dev/badge/skills/smixs/disruptor-skills/setting-up-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 | $0.00077 | $0.01194 |
| Opus 5 | $0.00039 | $0.00597 |
| Sonnet 5 | $0.00015 | $0.00239 |
| Haiku 4.5 | $0.00008 | $0.00119 |
Grade A, and why
setting-up-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 12d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup and domain model
Stage contract
- Stage: 0. Setup (once per repo) + cross-cutting upkeep · Kind: method
- Inputs: the repo; whatever domain terms and decisions surface as the flow runs.
- Outputs:
CONTEXT.md(glossary) anddocs/adr/(decision records), created lazily and kept live. - Entry gate: first time through the flow in this repo (no CONTEXT.md / conventions recorded), or a term/decision needs pinning down mid-flow.
- Done when: conventions are recorded; every term the flow relies on has one canonical definition; every hard-to-reverse decision is an ADR.
- Next: the stage you were routed to — usually the
designing-with-7w3skill. - Maintains: it owns CONTEXT.md and docs/adr/; every other stage keeps them live.
Why this exists
The whole flow rests on the invariant the document is the source of truth — design, spec, and decisions are the record; code realizes them. That invariant needs a concrete home, or it stays a slogan. These two artifacts are that home:
- CONTEXT.md keeps the vocabulary from drifting. When "user", "account", and "member" mean the same thing in three files, the design has already started to rot. One canonical term per concept keeps every later stage — spec, breakdown, reviews — talking about the same things.
- docs/adr/ keeps the why of hard-to-reverse choices from evaporating. A decision that isn't recorded gets silently re-litigated or quietly reversed by an agent that never saw the trade-off.
Create both lazily — only when the first term or the first real decision appears. An empty CONTEXT.md on day one is ceremony; a stale one is worse than none.
Once-per-repo setup
Do this the first time the flow touches a repo. Keep it to what the flow actually needs:
- Decide where the artifacts live.
- Single domain:
CONTEXT.md+docs/adr/at the repo root. - Multiple bounded contexts: a root
CONTEXT-MAP.mdpointing tosrc/<context>/CONTEXT.md+ per-contextdocs/adr/.
- Single domain:
- Record the conventions the flow assumes (a short block in
CLAUDE.md/AGENTS.md, or adocs/agents/note): where CONTEXT.md and ADRs live, and any project-specific rule the base invariants don't already cover. - Don't scaffold empty files. Note the locations; create the files when the first term/decision actually lands (see below).
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.
- 12d ago First seen · 100 lines · 77 tokens per session scan A deec81273d2a
setting-up-domain-model is a skill published in the GitHub repository smixs/disruptor-skills (18 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 1,194 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
debug
Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
setting-up-a-project
Use whenever asked to set up, onboard, initialize, or spec a project — the front door when the workspace has no spec graph yet (brand-new or an existing codebase); also seeded by the app's Set-up-project card (/skill:setting-up-a-project). Not for feature work in an already-specced project — use the brainstorming…
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
animate
Build a web animation: whether it should animate at all, the purpose, the tool, the properties, the easing curve, the duration, interruption and exit. Writes the CSS or Motion code for dropdowns, modals, toasts, tooltips, accordions, press feedback, stagger and scroll reveals. Use to animate something or make a…