{"slug":"model-2","title":"model","summary":"Produce or update a domain-reference kit — the durable glossary + divergences/traps pages for a bounded context. Use for domain modelling, information architecture, building a domain glossary or domain model, mapping domain concepts to code (bindings), or surfacing the decidable ","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-20T17:02:54.856086Z","repo":{"url":"https://github.com/serpro69/claude-toolbox","stars":149,"forks":31,"license":null,"updatedAt":"2026-09-25T15:21:56Z"},"bodyHtml":"
\n

name: model\ndescription: |\nProduce or update a domain-reference kit — the durable glossary + divergences/traps pages for a bounded context. Use for domain modelling, information architecture, building a domain glossary or domain model, mapping domain concepts to code (bindings), or surfacing the decidable questions stakeholders must close before design. Runs upstream of feature $kk:design as the first producer of the architecture flow, and emits artifacts $kk:review-architecture verifies. Triggers: \"model the domain\", \"build a glossary\", \"domain reference\", \"bounded context\", \"what are the concepts here\". NOT for behavioral code review or writing a feature design doc.

\n\n

Domain Modelling — the steady-state kit

\n

Goal: produce a provenance-clean domain-reference kit and, above all, a decision queue of precise, role-tagged questions a human can close. The queue is the primary output — artifact count and model sophistication are explicitly not the metric.

\n

$kk:model is the first producer of the architecture flow: it runs at information-architecture altitude (what the domain's concepts are, where they bind to code, and which questions about them only a human can close), upstream of feature $kk:design and never called by it. It writes files and interacts with you mid-flow — it is a main-session skill, not a read-only reviewer.

\n

Conventions

\n\n

Workflow

\n

Mandatory order — instructions before subject matter. The flow is strictly sequential. Do not read code to model it, draft any kit page, or engage the domain beyond a mode-detecting directory/keyword scan until every instruction file is loaded: this SKILL.md, the process file model-process.md, the reading method archaeology.md, the output contract kit-contract.md, all four shared guards above, and the shared capy protocol. This ordering is load-bearing: with domain code in context before the contracts load, the model emits plausible terms and skips the methodology that makes them trustworthy.

\n
    \n
  1. Load instructions. Read model-process.md (the detailed seven-phase workflow), archaeology.md, kit-contract.md, all four shared guards — shared-requirements-harvesting.md, shared-open-question-pass.md, shared-fact-flip-propagation.md, shared-contact-ratio-guard.md — and shared-capy-knowledge-protocol.md. Minimal early scope — a directory listing or a keyword scan of the request — is permitted only to drive mode detection.
    2. \n
  2. Execute the seven phases per model-process.md:\n
      \n
    1. Scope intake — establish the bounded context, the forcing question (the feature/ticket that bounds what is worth modelling), and the mode (greenfield: no kit exists → produce the two pages; brownfield: an existing kit is read in full first and all changes are deltas, status markers never flipped unilaterally). Run the capy knowledge search.
      2. \n
    2. Requirements-harvesting gate (guard, F1) — read every linked ticket + one hop; quote the actual asks into working notes before any modelling.
      3. \n
    3. Archaeology — read code state → time → invariants per archaeology.md; two-clock discipline (code-clock facts verifiable, intent stays proposed).
      4. \n
    4. Draft the kit per kit-contract.md — glossary page + divergences/traps page (+ conventions index if the home has none).
      5. \n
    5. Verify — at least one confirm-pass plus at least one open-question pass (guard, F4).
      6. \n
    6. Self-check — conventions-bind-author lint: the produced pages obey the kit's own declared conventions.
      7. \n
    7. Surface & close — present the decision queue (each RQ precise, decidable, role-tagged); apply the contact-ratio guard (F5); in brownfield, fact-flip propagation (F2) on any contradicted recorded fact; index non-obvious rationale to kk:arch-decisions.
      8. \n
    \n
    3. \n
\n

Required Outputs

\n\n","files":[{"path":"archaeology.md","sizeBytes":3129,"isText":true},{"path":"evals/brownfield-update/eval.json","sizeBytes":4285,"isText":true},{"path":"evals/brownfield-update/oracle/gold-deltas.json","sizeBytes":4025,"isText":true},{"path":"evals/brownfield-update/test-files/docs/architecture/index.md","sizeBytes":1161,"isText":true},{"path":"evals/brownfield-update/test-files/docs/architecture/routesetting.md","sizeBytes":2836,"isText":true},{"path":"evals/brownfield-update/test-files/docs/architecture/routesetting-traps.md","sizeBytes":1328,"isText":true},{"path":"evals/brownfield-update/test-files/gym/go.mod","sizeBytes":20,"isText":false},{"path":"evals/brownfield-update/test-files/gym/grading.go","sizeBytes":492,"isText":false},{"path":"evals/brownfield-update/test-files/gym/route.go","sizeBytes":992,"isText":false},{"path":"evals/brownfield-update/test-files/gym/wall.go","sizeBytes":377,"isText":false},{"path":"evals/hidden-invariant/eval.json","sizeBytes":3684,"isText":true},{"path":"evals/hidden-invariant/oracle/gold-invariant.json","sizeBytes":2713,"isText":true},{"path":"evals/hidden-invariant/test-files/campground/booking.go","sizeBytes":1199,"isText":false},{"path":"evals/hidden-invariant/test-files/campground/gate.go","sizeBytes":455,"isText":false},{"path":"evals/hidden-invariant/test-files/campground/go.mod","sizeBytes":27,"isText":false},{"path":"evals/hidden-invariant/test-files/campground/occupancy.go","sizeBytes":378,"isText":false},{"path":"evals/hidden-invariant/test-files/campground/site.go","sizeBytes":189,"isText":false},{"path":"evals/kit-format/eval.json","sizeBytes":6075,"isText":true},{"path":"evals/kit-format/oracle/kit-conventions-checklist.json","sizeBytes":5414,"isText":true},{"path":"evals/kit-format/test-files/bikeshare/bike.go","sizeBytes":545,"isText":false},{"path":"evals/kit-format/test-files/bikeshare/dock.go","sizeBytes":409,"isText":false},{"path":"evals/kit-format/test-files/bikeshare/go.mod","sizeBytes":45,"isText":false},{"path":"evals/kit-format/test-files/bikeshare/policy.go","sizeBytes":527,"isText":false},{"path":"evals/kit-format/test-files/bikeshare/ride.go","sizeBytes":614,"isText":false},{"path":"evals/requirements-gate/eval.json","sizeBytes":3622,"isText":true},{"path":"evals/requirements-gate/oracle/gold-harvest.json","sizeBytes":2883,"isText":true},{"path":"evals/requirements-gate/test-files/ferry/boarding.go","sizeBytes":499,"isText":false},{"path":"evals/requirements-gate/test-files/ferry/go.mod","sizeBytes":22,"isText":false},{"path":"evals/requirements-gate/test-files/ferry/reservation.go","sizeBytes":983,"isText":false},{"path":"evals/requirements-gate/test-files/ferry/sailing.go","sizeBytes":493,"isText":false},{"path":"evals/requirements-gate/test-files/ferry/tickets/FERRY-12.md","sizeBytes":488,"isText":true},{"path":"evals/requirements-gate/test-files/ferry/tickets/FERRY-31.md","sizeBytes":600,"isText":true},{"path":"evals/scope-pushback/eval.json","sizeBytes":3494,"isText":true},{"path":"evals/scope-pushback/test-files/apiary/colony.go","sizeBytes":436,"isText":false},{"path":"evals/scope-pushback/test-files/apiary/go.mod","sizeBytes":23,"isText":false},{"path":"evals/scope-pushback/test-files/apiary/harvest.go","sizeBytes":418,"isText":false},{"path":"evals/scope-pushback/test-files/apiary/hive.go","sizeBytes":443,"isText":false},{"path":"evals/scope-pushback/test-files/apiary/inspection.go","sizeBytes":474,"isText":false},{"path":"kit-contract.md","sizeBytes":12568,"isText":true},{"path":"model-process.md","sizeBytes":8802,"isText":true},{"path":"shared-capy-knowledge-protocol.md","sizeBytes":1845,"isText":true},{"path":"shared-contact-ratio-guard.md","sizeBytes":2553,"isText":true},{"path":"shared-fact-flip-propagation.md","sizeBytes":2370,"isText":true},{"path":"shared-open-question-pass.md","sizeBytes":2847,"isText":true},{"path":"shared-requirements-harvesting.md","sizeBytes":2455,"isText":true},{"path":"SKILL.md","sizeBytes":5834,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-09-20T17:03:30.600923Z","sha256":"6395CC971A568F79900E788115B7FCB462734D0BB5E937B1622A9F00CABEDBFB","sizeBytes":50281},"review":null,"source":{"repositoryUrl":"https://github.com/serpro69/claude-toolbox","path":"kodex-plugin/skills/model","license":null,"commit":"6121a1cf32d47972deef60944bf3d1a5e309f287","subtreeSha":"CC757C0AE0172FB80D8254B32C60046223023E730C8623470C13DB5C82733A27","lastSyncedAt":"2026-09-28T20:55:47.763582Z"},"reviewedAt":"2026-09-20T17:04:30.299734Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/serpro69/claude-toolbox/tree/master/kodex-plugin/skills/model"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install serpro69-claude-toolbox@llmmart"},{"target":"git","command":"git clone https://github.com/serpro69/claude-toolbox.git"}]}