@@ -21,6 +21,8 @@ Sections dated before 2026-09-19 predate the cycle and stay as they are.
 - process(merging): **every PR gets an independent review before it merges — a merge go is not a review.** A reviewer that did not write the PR returns MERGE / MERGE-AFTER-FIX / HOLD on value, regression risk after sync, correctness and context cost; builder self-reports and green CI no longer count. Nine PRs merged on 2026-10-13 without one. — MendixMau
 - process(context): **the baseline word budget is made room for by moving text, never by deleting rules.** Rules, STOP rows, denominators and failure examples are protected; stories and examples move behind pointers in a separate, independently reviewed trim PR; a trim PR lands first when a PR would take the baseline within 2,000 words of the cap. — MendixMau
 - fix(page-fidelity): **text is matched against what the page shows, on whole words; ButtonStyle counts as `btn btn-<style>`; layout chrome comes from the layout** ([#158](https://github.com/MendixMau/mxcli-project-toolkit/issues/158), [#157](https://github.com/MendixMau/mxcli-project-toolkit/issues/157)). Headings, actions and content were a substring test over the whole page MDL with 60% of the >3-char words enough, so a wireframe H2 "Product overview" counted as present on a page named `Product_Overview`, "Deactivate product" on a button captioned "Deactivate", and an "Add" button passed with no words to test. Each wireframe string is now matched per literal against the page's own captions — headings against Title/Content/non-button Captions, actions against button Captions, content against every displayed literal — on whole words, all of them for a label under three words; bindings keep the identifier corpus. An `actionbutton` now declares `btn` + `btn-<ButtonStyle>` (`btn-default` when DESCRIBE omits it), per the measured DOM contract in `learned-stylegallery.md`. The page's layout, when its MDL is in the input (`describe layout`), or `--chrome a,b`, adds to the fixed chrome set; without either nothing changes. Whole-word matching folds plurals (`Orders` = `Order`) on both sides, and multi-line ALTER `set (…) on w` statements count, including a ButtonStyle that replaces the old one. Scores move: of the 11 page/wireframe pairs already in the repo, 10 are unchanged and a stub page drops 66%→39% (a "Waiting for customer" heading credited from `dgWaiting` + `CustomerQuery`); the new probe pairs fail on the old scorer; a field run on a live project is still owed. — MendixMau
+- skill(interaction-model, design-artifacts, runbook): **Stage 3 writes `design/interaction-model.md` before the first wireframe — a home per role, an inbox per user task, and per page how it is reached, its page parameter and its data view source; every wireframe opens with a `wf-contract` block (`Page parameter:`, `Reached from:`, `Drawn as role:`)** ([#291](https://github.com/MendixMau/mxcli-project-toolkit/issues/291), part 1 of 3). Three apps built with the toolkit passed every gate (Stage 3/4 PASS, page fidelity 81-89% on the affected pages, lint 0 errors, e2e 69/69) while one of them rooted 8 pages on a parameterless "current record" retrieve, gave all 6 roles one home page and put 3 process stages in a 6-item menu; the wireframes were drawn as one role with one record, so every downstream check inherited the defect. Routed on demand, Stage 3, lead + ba + architect; the gate facts and the model-side check are follow-ups. — MendixMau
+- chore(context): **baseline word budget freed — 79,735 → 75,963 words (−3,772) without dropping a rule.** The always-on tier sat 265 words under its 80,000 cap, so three open PRs could not all merge. Long incident narratives in `conversion-runbook.md`, `source-triage.md` and `interview-protocol.md` became one-line failure examples pointing at new on-demand `process/baseline-incident-history.md`, where the original text is kept verbatim per section (R1–R20, AR1, ST1–ST4, IP1–IP3); the runbook's copy of the open-questions status table now defers to `interview-protocol.md` §4; `agent-roles.md`'s six template shapes (setup-only, ~2,300 words) moved verbatim to `agents/README.md`, which the installers never copy (explicit `MXTK_AGENTS` list). Every STOP, rule, denominator and gate cell stays in place; files touched by open PRs were left alone. — MendixMau
 - learn(testing-shape, test-result-audit): **three test-strength rules, each with a denominator: refusals probed on the server, every undeclared 4xx a failure, one clean-database final run** ([#172](https://github.com/MendixMau/mxcli-project-toolkit/issues/172)). A field comparison of two builds against one frozen spec found the toolkit build checked permission refusals only in the client (a hidden menu item), logged unexpected 400/422 responses as information, and reached 20/20 by stitching three runs. `testing-shape.md` §7 gains three report lines (`N of N restricted pairs probed server-side`, `undeclared 4xx/5xx: 0 of M requests — each fails its step`, `one clean-DB run <id>: N of N scenarios incl. timers, not stitched`); `test-result-audit.md` gains check 2e, which carries the reasons and the field evidence and asks for those numbers. Both baseline skills stay inside the 80,000-word baseline budget (79,997): the reasons live in the on-demand audit skill, and two redundant sentences in `testing-shape.md` §4's verdict paragraphs were folded (the empty-set corollary is stated in the Trace row, `harness-architecture.md` and `report-schema.md`). The backing inbox note is trimmed to its unpromoted "Keep" items. — MendixMau
 - learn(learned-detection-gaps, module-review): **two UI defects every model gate passes: a lazy-loaded combo box filter hides its preset, and a theme that pins row heights by position lets the next row cover an inserted widget** ([#299](https://github.com/MendixMau/mxcli-project-toolkit/issues/299)). Both passed check, mxbuild, lint and the scripted checks on a 127-module production app and were found only in the running app. Two register rows with the first oracle and the pre-build check (pluggable properties that change *when* data loads; grep the theme for fixed `height` on positional row classes before an insert), and two LOOK lines in `module-review.md` §4c with denominators (`N of N filters show their preset on first load`, `N of N widgets inserted into an existing container fully visible`). — jopterhorst
 - fix(app-restart, test-stack-up): **a port held by another process before `run --local` is named and reported as "instrument blocked" (exit 4), never killed** ([#262](https://github.com/MendixMau/mxcli-project-toolkit/issues/262)). Studio Pro had started its own runtime on the app/admin ports a restart needed; `mxcli run --local` then failed with "Authentication failed" (the admin API answering was Studio Pro's), the next journey ran against Studio Pro's runtime, and four more runs were NOT RUN. `app-restart.sh` now checks the app port and the admin port (record's `adminPort`, else app + 10) before stopping anything — a holder outside the recorded process tree exits 4 with its name, pid and parent — and again after the stop, where anything still holding a port is by definition not ours. `test-stack-up.sh` runs the same check wherever it would tell you to start `run --local` (`--no-docker`, no Docker daemon, `--check` with a leftover record), on the record's ports, `RUN_LOCAL_APP_PORT`/`RUN_LOCAL_ADMIN_PORT`, or mxcli's defaults 8080/8090. Holder lookup: lsof, then ss, then netstat + tasklist on Windows; unnamed holders still block when nothing of ours is running. Fixtures: `test-app-restart.sh` +2 cases (14 assertions, all fail on the old script), `test-stack-up-local.sh` T7 (4 of 6 fail on the old script). — AlvinnYeo
 
@@ -580,6 +580,7 @@ Every mxcli project has a `.ai-context/skills/` directory (bundled by `mxcli ini
 | After every wireframe edit: assembles design/wireframes/*.html into design/prototype.html, one hash-routed page a stakeholder can click through instead of twenty separate files. Generated, never edited (design-artifacts.md Step 3) | `project-bin/assemble-prototype.js` |
 | Before wireframes pass to the build loop, and with --brd before a BRD is signed off: dead #/route links, orphan screens, controls with no data-bind and no data-cut, BRD routes no screen has, screens no use case walks (design-artifacts.md Step 3c, brd-validation.md check 8) | `project-bin/check-prototype-links.js` |
 | Designing the brand and ONE ANNOTATED WIREFRAME PER SCREEN before building pages — the design system alone is half the deliverable | `skills/design-artifacts.md` |
+| Stage 3, after the role model is CONFIRMED and BEFORE THE FIRST WIREFRAME — and any time a page shows ONE object, a menu item or home page is added, or a data source retrieves the current/first record: role homes, inboxes, and per page how it is reached and which object it takes as parameter | `skills/interaction-model.md` |
 | Before a wireframe or a design commits to a WIDGET, when a requirement shows a widget to one role and not another, and when a page script hits a parse error that looks like a syntax mistake: the short list of things MDL cannot write at all, and the four-minute probe that answers it at Stage 3 instead of at build time | `skills/learned-mdl-cannot-express.md` |
 
 **Build — the loop itself**
 
@@ -126,6 +126,7 @@ picks the row up. That is the whole procedure — there is no second list to rem
 | After every wireframe edit: assembles design/wireframes/*.html into design/prototype.html, one hash-routed page a stakeholder can click through instead of twenty separate files. Generated, never edited (design-artifacts.md Step 3) | `project-bin/assemble-prototype.js` | architect,review | 3 | ondemand |
 | Before wireframes pass to the build loop, and with --brd before a BRD is signed off: dead #/route links, orphan screens, controls with no data-bind and no data-cut, BRD routes no screen has, screens no use case walks (design-artifacts.md Step 3c, brd-validation.md check 8) | `project-bin/check-prototype-links.js` | architect,review | 3 | ondemand |
 | Designing the brand and ONE ANNOTATED WIREFRAME PER SCREEN before building pages — the design system alone is half the deliverable | `skills/design-artifacts.md` | architect | 3 | ondemand |
+| Stage 3, after the role model is CONFIRMED and BEFORE THE FIRST WIREFRAME — and any time a page shows ONE object, a menu item or home page is added, or a data source retrieves the current/first record: role homes, inboxes, and per page how it is reached and which object it takes as parameter | `skills/interaction-model.md` | lead,ba,architect | 3 | ondemand |
 | Before a wireframe or a design commits to a WIDGET, when a requirement shows a widget to one role and not another, and when a page script hits a parse error that looks like a syntax mistake: the short list of things MDL cannot write at all, and the four-minute probe that answers it at Stage 3 instead of at build time | `skills/learned-mdl-cannot-express.md` | architect,mdl | 3,5 | ondemand |
 | A style change that appears to have done nothing, a focus ring that paints on every page landing, or an app still grey after a design port every instrument called green — the three ways a correct rule paints nothing (matches nothing / matches chrome / loses the cascade), the two reads that tell them apart, and the class that arrived in the stylesheet and is bound to no widget | `skills/learned-css-that-never-applied.md` | mdl,review,gate | 5,6 | baseline |
 
 
@@ -65,6 +65,7 @@ This table is your whole list. The baseline table in the project's CLAUDE.local.
 | `skills/architecture-blueprint.md` | Diagramming target architecture |
 | `skills/modularize-domain.md` | Deciding module boundaries before "create module" |
 | `skills/design-artifacts.md` | Designing the brand and ONE ANNOTATED WIREFRAME PER SCREEN before building pages |
+| `skills/interaction-model.md` | Stage 3, after the role model is CONFIRMED and BEFORE THE FIRST WIREFRAME |
 | `skills/brd-to-build-plan.md` | Turning BRDs plus architecture into a numbered, dependency-ordered build plan |
 | `skills/coverage-ledger.md` | Building the Stage 4 coverage ledger |
 | `bin/coverage-check.sh` | Checking a coverage ledger against its BRD |
 
@@ -85,6 +85,7 @@ This table is your whole list. The baseline table in the project's CLAUDE.local.
 | `skills/kb-generation.md` | Extracting Excel/Word/PDF specs into a knowledge base |
 | `skills/brd-generation.md` | Writing or enriching a BRD JSON |
 | `skills/brd-validation.md` | Validating BRDs against the code and document KB |
+| `skills/interaction-model.md` | Stage 3, after the role model is CONFIRMED and BEFORE THE FIRST WIREFRAME |
 | `skills/company-brain.md` | Setting up or wiring a COMPANY BRAIN |
 | `skills/close-the-loop.md` | Cutover and retrospective |
 | `skills/measured-claims.md` | Before citing ANY behavioural claim about the harness, the Mendix runtime or a test tool as evidence |
 
@@ -1769,7 +1769,7 @@ stage_protocol_paths() {
     0)  echo "skills/interview-protocol.md skills/grill-mode.md skills/checkpoints/checkpoint-template.md skills/checkpoints/checkpoint-scope.md skills/source-triage.md skills/image-transcription.md skills/small-project-tier.md skills/existing-app-change.md skills/app-analysis.md skills/layering-review.md skills/module-dependency-review.md skills/microflow-loop-antipatterns.md skills/assess-migration.md skills/migration-pipeline.md skills/migrate-general.md skills/migrate-outsystems.md skills/source-os11.md skills/os-xml-schema.md skills/source-node-express-react.md skills/document-discovery.md skills/extractor-quality-loop.md skills/qa-loop-goal-pattern.md skills/mendix-epics-api.md skills/corpus-extraction-integrity.md skills/gate-check-file-locations.md" ;;
     1)  echo "skills/interview-protocol.md skills/grill-mode.md skills/checkpoints/checkpoint-template.md skills/checkpoints/checkpoint-extraction.md skills/agent-roles.md skills/image-transcription.md skills/small-project-tier.md skills/migration-pipeline.md skills/source-os11.md skills/os-xml-schema.md skills/source-node-express-react.md skills/document-discovery.md skills/extractor-quality-loop.md skills/kb-generation.md skills/corpus-extraction-integrity.md" ;;
     2)  echo "skills/interview-protocol.md skills/change-intake.md skills/grill-mode.md skills/checkpoints/checkpoint-template.md skills/checkpoints/checkpoint-brd.md skills/checkpoints/checkpoint-architecture.md skills/agent-roles.md skills/image-transcription.md skills/small-project-tier.md skills/kb-generation.md skills/brd-generation.md skills/brd-validation.md" ;;
-    3)  echo "skills/interview-protocol.md skills/change-intake.md skills/grill-mode.md skills/checkpoints/checkpoint-template.md skills/checkpoints/checkpoint-design.md skills/agent-roles.md skills/small-project-tier.md skills/mendix-best-practices-index.md skills/layering-review.md skills/architecture-blueprint.md skills/modularize-domain.md skills/design-artifacts.md skills/brd-to-build-plan.md skills/workflow-structure-rules.md skills/learned-mdl-cannot-express.md" ;;
+    3)  echo "skills/interview-protocol.md skills/change-intake.md skills/grill-mode.md skills/checkpoints/checkpoint-template.md skills/checkpoints/checkpoint-design.md skills/agent-roles.md skills/small-project-tier.md skills/mendix-best-practices-index.md skills/layering-review.md skills/architecture-blueprint.md skills/modularize-domain.md skills/design-artifacts.md skills/interaction-model.md skills/brd-to-build-plan.md skills/workflow-structure-rules.md skills/learned-mdl-cannot-express.md" ;;
     4)  echo "skills/interview-protocol.md skills/change-intake.md skills/grill-mode.md skills/checkpoints/checkpoint-template.md skills/checkpoints/checkpoint-build.md skills/agent-roles.md skills/small-project-tier.md skills/module-brief.md skills/module-folder-convention.md skills/brd-to-build-plan.md skills/coverage-ledger.md skills/workflow-structure-rules.md skills/rest-integration-first-time-right.md skills/learned-constants-and-secrets.md" ;;
     5|build-ready) echo "skills/interview-protocol.md skills/change-intake.md skills/grill-mode.md skills/agent-roles.md skills/module-brief.md skills/learned-mdl-preflight.md skills/module-folder-convention.md skills/learned-microflow-patterns.md skills/microflow-preflight.md skills/mendix-best-practices-index.md skills/ui-preflight-pages.md skills/design-spacing.md skills/learned-stylegallery.md skills/ui-loop.md skills/module-review.md skills/testing-shape.md skills/microflow-loop-antipatterns.md skills/iterative-build-loop.md skills/mdl-cookbook-microflows.md skills/build/mdl/oneshot-mdl-method.md skills/learned-page-patterns.md skills/oneshot-page-structure-patterns.md skills/mendix-agents.md skills/mendix-agent-ui.md skills/mendix-agent-setup.md skills/fixture-seeding.md skills/journey-proof.md skills/unhappy-path-testing.md skills/monkey-test.md skills/e2e-locators-that-lie.md skills/report-schema.md skills/harness-architecture.md skills/process-coherence-pass.md skills/lint-that-actually-runs.md skills/improvement-register.md skills/journey-examples.md skills/wiring-sweep.md skills/learned-workflow-patterns.md skills/workflow-structure-rules.md skills/rest-integration-first-time-right.md skills/bug-submission-checklist.md skills/empty-widget-triage.md skills/learned-sidebar-collapse-icons.md skills/learned-popup-navigation.md skills/learned-datagrid-customcontent-binding.md skills/learned-popup-feedback-pattern.md skills/learned-mdl-cannot-express.md skills/learned-css-that-never-applied.md skills/learned-detection-gaps.md skills/learned-dg2-patterns.md skills/learned-file-upload-widget.md skills/security-is-not-a-later-script.md skills/learned-local-db-confusion.md skills/full-harness-audit.md skills/test-result-audit.md skills/finding-disposition.md skills/preview-over-hub-tunnel.md skills/walking-skeleton.md skills/platform-link.md skills/teamserver-alignment.md skills/learned-constants-and-secrets.md" ;;
     6)  echo "skills/interview-protocol.md skills/change-intake.md skills/grill-mode.md skills/checkpoints/checkpoint-template.md skills/checkpoints/checkpoint-cutover.md skills/agent-roles.md skills/mendix-best-practices-index.md skills/module-review.md skills/testing-shape.md skills/existing-app-assurance.md skills/app-analysis.md skills/module-dependency-review.md skills/microflow-loop-antipatterns.md skills/qa-loop-goal-pattern.md skills/mendix-agent-setup.md skills/e2e-harness-base.md skills/learned-db-assertions.md skills/fixture-seeding.md skills/journey-proof.md skills/unhappy-path-testing.md skills/monkey-test.md skills/e2e-locators-that-lie.md skills/learned-skill-ux-audit.md skills/learned-skill-scope-delta.md skills/report-schema.md skills/harness-architecture.md skills/process-coherence-pass.md skills/e2e-evidence-report.md skills/record-demo-video.md skills/share-demo-package.md skills/lint-that-actually-runs.md skills/improvement-register.md skills/journey-examples.md skills/wiring-sweep.md skills/workflow-structure-rules.md skills/bug-submission-checklist.md skills/empty-widget-triage.md skills/anonymize-client-app-for-demo.md skills/learned-css-that-never-applied.md skills/learned-detection-gaps.md skills/learned-local-db-confusion.md skills/full-harness-audit.md skills/test-result-audit.md skills/finding-disposition.md skills/handoff-to-studio-pro.md skills/preview-over-hub-tunnel.md skills/platform-link.md skills/teamserver-alignment.md skills/learned-constants-and-secrets.md" ;;