@eventmodelers/cli 1.0.163 → 2.0.2

package/stacks/supabase-react/templates/.claude/skills/build-state-view/SKILL.md

@@ -67,31 +67,39 @@ Extract:
        a Slice" step 6) — the built, mocked component still needs a real table/view before it's done,
        so don't flip it to `Done`.
   - `description` — implementation hints (filtering rules, sort order, business meaning).
-- **UI contract (read)** — the backend slice's published `GET` contract: look it up as described in
+- **UI contract (read)** — **not used for a read model backed by a table, which is the normal case on this
+  stack: that is always read directly with `queryReadModel`, even when the backend published a `GET`
+  contract.** Only when `slice.json` says the read model is not a persisted table (a computed view, an
+  external source) does the backend's published `GET` contract apply: look it up as described in
   the `ui-contract` skill ("How the UI build kit looks the contract up" — the `## UI Contract` entry in
-  `slice.json` `notes[]`; parse only its `ui-contract` block — an OpenAPI operation). **When present it
-  is the specification and you build the call from it** — it overrides `apiEndpoint` and the table read:
+  `slice.json` `notes[]`; parse only its `ui-contract` block — an OpenAPI operation). **In that case it
+  is the specification and you build the call from it** — it overrides `apiEndpoint`:
   - fetch with `getReadModel(buildPath('<contract path>', { <path params> }), { <query params> }, samples)`
     from `src/lib/api.ts` — path and query `parameters` exactly as the contract names them, never a
     guessed URL, never `supabase.from(...)`;
   - type the result from the 2xx `responses` schema (it must match `readmodel.fields[]`; the contract
-    wins for the wire shape, record any mismatch in `progress.txt`);
+    wins for the wire shape, record any mismatch as a code comment);
   - render **every** non-2xx response (status + description) as its own distinct state — a 404 "no
     reservation" is an empty state, not an error banner; don't collapse them into one generic failure;
   - the numbered samples (Step 4) are shaped like the contract's 2xx response body.
 
   **When absent** (backend slice not built or not re-fetched yet): fall back to the table read —
   `readmodel.apiEndpoint` (table/view name) + `fields[]` via `queryReadModel` — and note the assumption
-  in `progress.txt`.
+  as a code comment.
 - **screens[]** — the actor `SCREEN` element(s) that display this data, if any (see Step 2).
-- **specifications[]** — GWT scenarios/storyline; treat as acceptance criteria (e.g. "given no
-  active reservation, show an empty state").
+- **specifications[]** and **storylines[]** (optional) — GWT scenarios / board walkthroughs. These
+  describe how the slice should **behave** — read them in full (Step 3a) to understand the outcomes
+  and states the UI must present. The business logic itself lives in the backend; the UI does not implement it.
 
 > **Comments**: as in `build-state-change` — resolve consumed ones via the same node-comment
 > endpoint.
 
 ## Step 2 — Read the screen, and especially its marks
 
+> **Gated by `ui-baseline check`** (build prompt, `lib/prompt.md`, Step 4): do this step when the verdict
+> is `SCREEN_CHANGED`, `NO_BASELINE` or `UNKNOWN` — and then also diff the existing JSX against the fetched
+> screen and adjust the UI to it. On `UNCHANGED` skip it.
+
 Identical to `build-state-change` Step 2 — fetch the live screen node
 (`mcp__eventmodelers__get_node`), find this slice's marked fragment in `meta.pages`/`meta.marks`
 (or the whole page if unmarked), and treat it as the blueprint. The same `learn-styleguide` note
@@ -112,16 +120,39 @@ multi-read-model component.
 **Markup**: same rule as `build-state-change` — translate the blueprint from Step 2 1:1 into JSX;
 the mockup is the design, not a starting point for a redesign.
 
+**Data binding — the whole point of a read-model component.** Every *data* value in the mockup (names,
+role/organisation lines, selected values, dropdown options, list rows, badges, counts, dates) is a
+sample taken from the model's examples; it must be rendered from the queried data, mapped from
+`readmodel.fields[]` — keep only label/copy (headings, button captions, placeholders) verbatim.
+Check where each displayed value comes from before writing JSX: a field of this read model → bind it;
+a field of another read model on the same screen → it arrives as a prop from the parent that fetched
+it (or a sibling read-model component), never from the mockup. List rows are a `.map()` over the
+fetched rows, not the rows drawn. Self-check: grep the component for the mockup's example strings;
+any hit outside `samples/` means hardcoded data — fix it.
+
+**Find the screen's data sources on the board, not just in `slice.json`.** A screen is often shown by
+one slice but fed by a read model that belongs to *another* slice (e.g. the Contact Details screen
+sits in the Assign Tag slice, yet its contact data comes from the Contact List read model via an edge
+READMODEL → SCREEN). `slice.json` only lists this slice's own elements, so also call
+`mcp__eventmodelers__get_connected_nodes { boardId, nodeId: <screen.id> }` and take every READMODEL
+wired into the screen. Each one is a data source for the displayed values; look up its fields in that
+read model's slice (`.build-kit/.slices/*/*/slice.json`, or `get_node`). A list read model feeding a
+detail screen (`Contact List[]` → one contact) means: query it filtered by the entity id the page
+gets from the route (match the id field, e.g. `contactId` / the command's `recordId`) and render that
+row. If the source read model's slice isn't built, still type and wire against its fields (TODO), do
+not substitute the mockup's values.
+
+
 **Props**: whatever the component needs to *scope* its query (e.g. `customerId`) — passed in from
 its parent, never read from a global store. The queried data itself is **not** a prop — the
 component fetches it.
 
-**With a UI contract (Step 1)**: call `getReadModel(buildPath(path, pathParams), queryParams, samples)`
+**With a UI contract (Step 1, non-table read models only)**: call `getReadModel(buildPath(path, pathParams), queryParams, samples)`
 from `src/lib/api.ts` inside the component instead of the `queryReadModel` snippet below — same
 effect shape (`useEffect` → loading / empty / error / data), but each documented non-2xx response
 (`ApiError.status`) maps to its own state. Never a raw `fetch`.
 
-**Default (no contract) — call `queryReadModel` from `src/lib/api.ts` inside the component**. Never
+**Default (a table-backed read model — always, unless the contract case above applies) — call `queryReadModel` from `src/lib/api.ts` inside the component**. Never
 `supabase.from(...)` directly, never a raw `fetch`:
 
 ```tsx
@@ -182,6 +213,26 @@ export function ActiveReservationView({ customerId }: ActiveReservationViewProps
 }
 ```
 
+### Step 3a — Read the scenarios to understand behavior (not to implement rules)
+
+**Business logic lives in the backend (the projection). The UI never re-derives it** — no
+recomputing totals, statuses or membership from events; render what the read model holds.
+
+Read every entry in `specifications[]` (and the READMODEL beats in `storylines[]`) to understand
+**what the read model looks like in different situations and how the component should present each**:
+
+| Scenario shows | What it tells the UI |
+|---|---|
+| `then` read model is empty (`expectEmptyList` / no rows) | an **empty state** must exist, distinct from loading and error |
+| the same field takes different values across scenarios (e.g. status `open` → `closed`) | each value needs a sensible presentation (label, badge, shown/hidden actions) — presentation only |
+| rows appear/disappear between scenarios | the component renders whatever rows the read model returns; it does not decide which belong |
+| row order visible across scenarios | hint for `order`/sort on the query, if the read model doesn't already guarantee it |
+| a `STORYLINE_NOTE` beat | background only |
+
+Rules:
+- Understand, don't implement: presentation of what the backend provides, nothing more.
+- Cite the scenario behind a non-obvious state in a one-line comment.
+
 Select fields explicitly by name rather than `select('*')`. Map each field's `name` to its actual
 column name — check the paired backend stack's migrations if the naming convention (e.g. camelCase
 vs. snake_case) isn't obvious rather than guessing; if genuinely unclear, use `request-feedback`.
@@ -202,7 +253,9 @@ otherwise; use `null`/`[]` for a sample meant to exercise the empty/background s
 
 Add at least one sample (`sample-1.json`) covering the ordinary case from
 `readmodel.fields[].example` values; add more numbered ones for whatever other scenarios this
-read model's `specifications[]` call out (e.g. an empty result, a second customer's data). The
+read model's `specifications[]` show — **one sample per distinct scenario outcome**, using the
+scenario's own example values (an empty result, each status a row can take, a second customer's
+data). The
 same number across *different* components' `samples/` folders is meant to represent one coherent
 scenario across the whole app (e.g. every component's `sample-2.json` together tell the story of
 "a long-time customer") — keep that in mind when choosing what a given number represents, rather
@@ -230,7 +283,7 @@ one page per slice.
    one place allowed to import across slice folders. Translate the screen's whole, unmarked
    `meta.pages` markup into JSX (the page-level layout), and at each `data-em-mark-id` position
    render that mark's owning slice's component (only for slices already built; leave the rest as
-   the mockup's static content until they are). The page threads shared inputs down as props; a
+   the mockup's static content until they are). Static placeholder content is label/copy only — displayed data (names, selections, options, rows) is bound to its read model, never the mockup's examples or a sample file. The page threads shared inputs down as props; a
    slice component still only knows its own declared props. Update only this slice's marked
    position if the page file already exists.
 
@@ -289,8 +342,8 @@ leaves it alone.
   slice.json.
 - At least one numbered sample exists under this slice's `samples/` folder, shaped exactly like
   `queryReadModel`'s return value.
-- The component renders a sensible empty/background state, distinct from loading/error, when the
-  data is `null`/`[]`.
+- Every scenario situation (empty, each distinct field value) has a rendered presentation, and the
+  component re-derives nothing the read model already holds.
 - If a screen was read in Step 2, the rendered JSX matches the marked (or whole, if unmarked) HTML
   fragment structurally.
 - Nothing in this slice's folder is imported from another slice's folder, and nothing outside it

package/stacks/supabase-react/templates/build-kit/CLAUDE.md

@@ -28,7 +28,7 @@ not attempt to build it, flag it via `request-feedback` instead.
 2. Maintain clear separation of concerns within each slice
 3. Headers, auth, `fetch`, and Supabase table access live exclusively in `src/lib/api.ts` — a
    slice component never imports `src/lib/supabase.ts` itself, never calls `fetch`, and never
-   calls `supabase.from(...)` directly; when the backend slice published a UI contract (`ui-contract` skill, `slice.json` `notes[]`) the slice is built *from* it — path, parameters, body and every error response — and falls back to `apiEndpoint`/`fields[]` only when none exists; it calls `postCommand`/`getReadModel`/`queryReadModel` and only contains
+   calls `supabase.from(...)` directly; a table-backed read model is always read directly with `queryReadModel` (the backend's `GET` contract is ignored for it); when the backend slice published a UI contract (`ui-contract` skill, `slice.json` `notes[]`) for a *write* or a non-table read, the slice is built *from* it — path, parameters, body and every error response — and falls back to `apiEndpoint`/`fields[]` only when none exists; it calls `postCommand`/`getReadModel`/`queryReadModel` and only contains
    business logic (validation, request-body shaping, response handling)
 4. A command's/read-model's screen markup (`meta.pages` on its actor HTML_SCREEN node, scoped to
    this slice's `meta.marks` when the screen is shared) is the visual blueprint — translate it into
@@ -95,16 +95,16 @@ not attempt to build it, flag it via `request-feedback` instead.
     on its next build. Never hand-write CSS to imitate a framework. See `build-state-change` Step 7 /
     `build-state-view` Step 6.
 
-At the start of every session, read `.build-kit/AGENTS.md` if it exists to load accumulated project learnings.
+At the start of every session, read `.build-kit/AGENTS.md` if it exists to load accumulated project learnings. It is generated from the learnings recorded so far — record a new one with `npx @eventmodelers/cli learn "<one terse line>" --topic <topic>`, never by editing the file.
 
-When starting to work on a slice, invoke the `update-slice-status` skill with `InProgress` status before doing anything else.
+When working from a queued task, invoke the `update-slice-status` skill with `InProgress` status before doing anything else. When the task request names the slice to build (a run-loop build), the run loop has already set it to `InProgress` and pushes the final status itself — do not call `update-slice-status`; record the outcome with `npx @eventmodelers/cli slice-status <status>`.
 
 ## Building a Slice
 
 **CRITICAL: You MUST always use the provided skills to build slices. NEVER implement a slice manually.**
 **ALL fields, event names, command names, and business rules MUST come exclusively from slice.json. Do NOT invent, assume, or guess any field or logic not present in the slice definition.**
 
-**Default: make a reasonable assumption and build the slice.** If a detail is unclear or missing (an example value, a field type, a status mapping, a referenced event that isn't modeled yet, ...), pick the most sensible interpretation from `slice.json`, its specifications and the surrounding model, build it, and record each assumption in one line in `progress.txt` and as a code comment. Ambiguity alone is never a reason to stop. **Only if the slice literally cannot be built** — nothing runnable can be produced even with sensible assumptions — invoke `/request-feedback` with the specific question; it posts the question as a comment on the slice and marks it `Blocked`. That must be the absolute exception; a `Blocked` slice should mean "impossible without a human", never "the agent preferred to ask".
+**Default: make a reasonable assumption and build the slice.** If a detail is unclear or missing (an example value, a field type, a status mapping, a referenced event that isn't modeled yet, ...), pick the most sensible interpretation from `slice.json`, its specifications and the surrounding model, build it, and record each assumption in one line as a code comment. Ambiguity alone is never a reason to stop. **Only if the slice literally cannot be built** — nothing runnable can be produced even with sensible assumptions — invoke `/request-feedback` with the specific question; it posts the question as a comment on the slice and marks it `Blocked`. That must be the absolute exception; a `Blocked` slice should mean "impossible without a human", never "the agent preferred to ask".
 
 **Exception: a missing `apiEndpoint`** (no backend endpoint/table decided yet) is a partial version of
 this — flag it, but don't fully stop. `build-state-change`/`build-state-view` Step 1 cover the exact
@@ -122,9 +122,10 @@ When asked to build a slice, always follow this flow:
    - **`AUTOMATION`** → not this stack's job (no UI counterpart) — invoke `request-feedback`
      rather than building it; it belongs to whichever backend stack is installed alongside this one
 3. Invoke the matching skill and follow its instructions completely. Do not deviate.
-4. **Verify against slice.json**: After the skill completes, check that every command field, event field, and specification in slice.json appears in the implementation. No invented fields — if it is not in slice.json, it must not be in the code.
-5. Run `npm run build` and `npm run lint` (both must pass clean), then the slice's own tests only, if any exist.
-6. If checks pass, commit with `feat: [Slice Name]` and set slice status to `Done` — **unless** the
+4. **UI baseline gate**: run `npx @eventmodelers/cli ui-baseline check` first and act only on its verdict — `UNCHANGED` means skip all UI work; `NO_BASELINE`/`UNKNOWN` mean one full screen diff and every `codeGen.uiPrompts` entry; `CHANGED` names the elements that changed, were added or removed (work on exactly those) and flags `SCREEN_CHANGED` (re-fetch the screen node and adjust the components to it), `ELEMENTS_CHANGED` (diff slice.json against the code) and `PROMPTS_CHANGED` (apply the printed prompts). Details in `lib/prompt.md`, Step 4. After the checks pass and before committing, run `ui-baseline record`.
+5. **Verify against slice.json**: After the skill completes, check that every command field, event field, and specification in slice.json appears in the implementation — specifications are read (Step 3a of the build skill) to understand how the UI should behave and present outcomes; the business logic lives in the backend and is not re-implemented here. No invented fields — if it is not in slice.json, it must not be in the code.
+6. Run `npm run build` and `npm run lint` (both must pass clean), then the slice's own tests only, if any exist.
+7. If checks pass, commit with `feat: [Slice Name]` and set slice status to `Done` — **unless** the
    matching build skill flagged a missing `apiEndpoint` and already marked the slice `Blocked`
    (Step 1 exception above); in that case, commit as normal but leave the status `Blocked`.
 

package/stacks/supabase-react/templates/build-kit/lib/AGENT.md

@@ -1,12 +1,11 @@
-# Agent Learnings
+# Agent Reference
 
-Patterns and gotchas discovered during task processing. Update this file whenever you encounter something reusable.
+What task processing relies on: the shape of a task and the API facts the skills use. A reusable learning is recorded with `npx @eventmodelers/cli learn "<one terse line>"`, not added here.
 
-## tasks.json
+## Tasks
 
-- Tasks are objects with `id`, `createdAt`, and `payload` (a `SliceChangedPayload`).
-- After completing a task, remove it from the array entirely — do not add a status field.
-- Write `[]` to `tasks.json` if the last task is completed.
+- A task is a slice change the run loop queued: an `id` and a `payload` (a `SliceChangedPayload`). The task request names it.
+- You never read or write a queue file: the run loop completes the task when your turn ends.
 
 ## SliceChangedPayload fields
 
@@ -44,4 +43,4 @@ These files are always up to date — read them directly before invoking any ski
 - The `boardId` and `organizationId` from each payload provide full context — pass them to skills.
 - Node events use `node:created`, `node:changed`, `node:deleted` — always POST to `/api/org/:orgId/boards/:boardId/nodes/events`.
 - Slice metadata (title, status) lives on the SLICE_BORDER node under `meta.sliceStatus` and `meta.title`.
-- `/update-slice-status` rejects moving a slice into a status it's already in — this is a concurrency guard, not a bug. It means another agent already claimed the slice. Treat it as `ALREADY_IN_STATUS`, skip that slice, and move on to the next `Handover` one instead of erroring out.
+- `/update-slice-status` rejects moving a slice into a status it's already in — this is a concurrency guard, not a bug. It means another agent already claimed the slice. Treat it as `ALREADY_IN_STATUS`, skip that slice, and move on to the next `Waiting` one instead of erroring out. This applies to queued tasks only: when the task request names the slice to build, the run loop owns its status — never call `/update-slice-status` there.

package/stacks/supabase-react/templates/build-kit/lib/backend-prompt.md

@@ -9,67 +9,50 @@ The structure defined in the Project-Skills is relevant.
 You work within **exactly ONE context at a time** — the one named in `.build-kit/.slices/current_context.json` (the runner picks it).
 
 - **ONLY** look for and build slices inside `.build-kit/.slices/<currentContext>/`.
-- **NEVER** read, scan, or build slices from any other context directory, even if it has "Handover" slices, and even if the current context has no work left.
-- A "Handover" slice in a *different* context is **NOT yours to build**. Ignore it completely.
-- If the current context has no "Handover" slice, you are **done for this iteration** — reply `<promise>NO_TASKS</promise>` and stop. Do not go looking elsewhere. The runner moves `current_context.json` on to the next context with Handover work between iterations — never change it yourself.
+- **NEVER** read, scan, or build slices from any other context directory, even if it has "Waiting" slices, and even if the current context has no work left.
+- A "Waiting" slice in a *different* context is **NOT yours to build**. Ignore it completely.
+- If the current context has no "Waiting" slice, you are **done for this iteration** — reply `<promise>NO_TASKS</promise>` and stop. Do not go looking elsewhere. The runner moves `current_context.json` on to the next context with Waiting work between iterations — never change it yourself.
 
 ## Your Task
 
 0. Do not read the entire code base. Focus on the tasks in this description.
 1. Read `.build-kit/.slices/current_context.json` to find the active context name, then read `.build-kit/.slices/<contextName>/index.json`. Every item in status "handover" is a task.
-2. Read the progress log at `progress.txt` **if it exists** (check Codebase Patterns section first) — it is absent until the first slice is built, which is not an error; create it when you write your first entry
+2. Read `.build-kit/AGENTS.md` **if it exists** — the project's accumulated learnings, generated from what earlier builds recorded. If the slice's `slice.json` has a `lastAttempt`, an earlier attempt at it failed: read its `reason`, `lastReply`, `branch` and `changed`, and do not repeat what failed.
 3. Make sure you are on the right branch "feature/<slicename>", if unsure, start from main.
-5. Pick the **highest priority** slice where status is **exactly** "Handover" (case insensitive). This becomes your PRD. Set the status "InProgress" in the index.json **and** update the slice status on the eventmodelers board using the `update-slice-status` skill (or MCP if available).
-   **IMPORTANT: Only work on slices with status "Handover" in the CURRENT context. Never pick up a slice that is "InProgress", "Done", "Blocked", "Created", or any other status — even if it looks incomplete. If no slice has status "Handover" in the current context, reply with:**
+5. Your slice is the one the task request names (the run loop picked the highest priority slice with status "Waiting"); it becomes your PRD. The run loop has already claimed it — its status is "InProgress" in index.json and on the board. Build that slice and do not call `update-slice-status`: the run loop owns the slice's status on the board.
+   **IMPORTANT: Only work on the slice named in the task request. Never switch to another slice, whatever its status. If the task request names no slice and no slice has status "Waiting" in the current context, reply with:**
    <promise>NO_TASKS</promise> and stop immediately. Do not work on other slices and do not switch to another context.
-   **Claim conflict**: the board rejects the status update if the slice is already in the target status — this is expected: another agent claimed it first, racing you for the same slice. This is NOT an error. Do not stop, do not retry the same slice. Re-read `index.json` (or re-fetch via `load-slice`), pick the next-highest-priority slice still "Handover", and try claiming that one instead. Repeat until a claim succeeds or no "Handover" slice remains, in which case reply `<promise>NO_TASKS</promise>`.
 6. Pick the slice definition from `.build-kit/.slices/<contextName>/<folder>/slice.json` as defined in the prd. Never work on more than one slice per iteration.
-7. A slice can define additional prompts as codegen/backendPrompt. Any additional prompts defined in backend are hints for the implementation of the slice and have to be taken into account. If you use the additional prompt, add a line in progress.txt
+7. A slice can define additional prompts as codegen/backendPrompt. Any additional prompts defined in backend are hints for the implementation of the slice and have to be taken into account.
 7. Determine the slice type and invoke the matching skill as defined in the **Building a Slice** section of `.build-kit/CLAUDE.md`. Do NOT implement manually.
-8. Write a short progress one liner after each step to progress.txt
+8. Record each learning the moment you have it (see **Recording Learnings**), not at the end.
 9. Analyze and Implement that single slice, making use of the skills in the skills directory plus your previously collected knowledge. Make a TODO list for what needs to be done, and adjust the implementation according to the JSON definition. Carefully inspect events, fields and compare against the implemented slice. JSON is the desired state. ATTENTION: a "handover" task can also be just added specifications. So always look at the slice itself, but also the specifications. If specifications were added in json which are not on code, you need to add them in code.
 10. The slice in the json is always true, the code follows what is defined in the json
 11. Slice is only 'Done' if business logic is implemented as defined in the JSON, APIs are implemented, all scenarios in JSON are implemented in code and it fulfills the slice.json. There must be no specification in json that has no equivalent in code.
 12. Build against the backend slice's published UI contract (see the `ui-contract` skill, "How the UI build kit looks the contract up") — the build-state-view / build-state-change skills say how to apply it
 13. Run quality checks — `npm run build` (typecheck + build) and `npm run lint`. No test runner is configured in this stack yet; if a slice's specifications demand behavioral tests, flag it via `request-feedback` instead of inventing a test setup ad hoc.
 14. If checks pass, commit ALL changes with message: `feat: [Slice Name]` and merge back to main as FF merge (update first)
-15. Update the PRD to set `status: Done` for the completed story in index.json **and** update the slice status on the eventmodelers board using the `update-slice-status` skill (or MCP if available).
-16. Append your progress to `progress.txt` after each step in the iteration.
-17. Append your new learnings to `.build-kit/AGENTS.md` in a compressed form, reusable for future iterations. Only add learnings if they are not already there.
+15. Record the outcome with `npx @eventmodelers/cli slice-status Done` — not by editing index.json, and do not call `update-slice-status`: the run loop pushes the status to the board when your turn ends. A slice you could not finish needs no status: leave it as it is and the run loop discards the attempt.
+16. Record any reusable learning you have not recorded yet (see **Recording Learnings**).
+17. If an entry in `.build-kit/AGENTS.md` turned out wrong or obsolete, retract it (see **Recording Learnings**).
 18. Finish the iteration.
 
 ## Escalating Ambiguity
 
-**Default: make a reasonable assumption and build the slice.** If a detail is unclear or missing (an example value, a field type, a status mapping, a referenced event that isn't modeled yet, ...), pick the most sensible interpretation from `slice.json`, its specifications and the surrounding model, build it, and record each assumption in one line in `progress.txt` and as a code comment. Ambiguity alone is never a reason to stop. **Only if the slice literally cannot be built** — nothing runnable can be produced even with sensible assumptions — invoke `/request-feedback` with the specific question; it posts the question as a comment on the slice and marks it `Blocked`. That must be the absolute exception; a `Blocked` slice should mean "impossible without a human", never "the agent preferred to ask".
+**Default: make a reasonable assumption and build the slice.** If a detail is unclear or missing (an example value, a field type, a status mapping, a referenced event that isn't modeled yet, ...), pick the most sensible interpretation from `slice.json`, its specifications and the surrounding model, build it, and record each assumption in one line as a code comment. Ambiguity alone is never a reason to stop. **Only if the slice literally cannot be built** — nothing runnable can be produced even with sensible assumptions — invoke `/request-feedback` with the specific question; it posts the question as a comment on the slice and marks it `Blocked`. That must be the absolute exception; a `Blocked` slice should mean "impossible without a human", never "the agent preferred to ask".
 
-## Progress Report Format
+## Recording Learnings
 
-APPEND to progress.txt (never replace, always append):
+`.build-kit/AGENTS.md` is generated from the learnings recorded so far — read it at the start of every session, never edit it by hand. Record a learning the moment you have it:
 
 ```
-## [Date/Time] - [Slice]
-
-- What was implemented
-- Files changed
-- **Learnings for future iterations:**
-  - Patterns discovered (e.g., "this codebase uses X for Y")
-  - Gotchas encountered (e.g., "don't forget to update Z when changing W")
-  - Useful context (e.g., "the evaluation panel is in component X")
----
+npx @eventmodelers/cli learn "<one terse line>" --topic "<topic>"
 ```
 
-The learnings section is critical - it helps future iterations avoid repeating mistakes and understand the codebase better.
-
-## Consolidate Patterns
-
-If you discover a **reusable pattern** that future iterations should know, add it to the `## Codebase Patterns` section at the TOP of progress.txt (create it if it doesn't exist).
-
-```
-## Codebase Patterns
-- TODO: an example of a your stack-specific reusable pattern once you have one
-```
-
-Only add patterns that are **general and reusable**, not story-specific details.
+- Only what is genuinely reusable: codebase patterns, gotchas, commands that work or don't, conventions — and, after a failed approach, what was tried and why it failed. Not slice-specific details, and nothing the code or git log already says.
+- One learning per call, one line each. A learning that is already in `.build-kit/AGENTS.md` is skipped for you.
+- `--scope system` for what is true of the modeled domain (a business rule, a naming convention of the model); `repo` (the default) for the codebase and its tooling. `--tag <tag>` labels it (repeatable).
+- One in `.build-kit/AGENTS.md` that turned out wrong or obsolete: `npx @eventmodelers/cli learnings --ids` lists each with its id, `npx @eventmodelers/cli learn --retract <id>` removes it.
 
 ## Update AGENTS.md Files
 
@@ -80,7 +63,7 @@ Before committing, check if any edited files have learnings worth preserving in
 - Slice specific implementation details
 - Story-specific implementation details
 - Temporary debugging notes
-- Information already in progress.txt
+- Information already recorded as a learning in `.build-kit/AGENTS.md`
 - Task-specific learnings
 
 Only update AGENTS.md if you have **genuinely reusable knowledge** that would help future work
@@ -107,12 +90,12 @@ A Slice is not complete if specifications are missing or can't be executed.
 
 ## Stop Condition
 
-**After completing ONE slice, always stop — regardless of whether more slices are in Handover.** The ralph loop will invoke you again for the next slice. Never chain multiple slices in one iteration.
+**After completing ONE slice, always stop — regardless of whether more slices are in Waiting.** The ralph loop will invoke you again for the next slice. Never chain multiple slices in one iteration.
 
 If the slice was completed and committed successfully, reply with:
 <promise>DONE</promise>
 
-If no slice has status "Handover" in the current context, reply with:
+If no slice has status "Waiting" in the current context, reply with:
 <promise>NO_TASKS</promise>
 (Do NOT switch to another context to find work — stop here.)
 
@@ -124,9 +107,9 @@ If ALL slices in the current context are Done, reply with:
 - If no `.eventmodelers/config.json` exists anywhere (project root or an ancestor directory, or `~/.eventmodelers/config.json` — the one inside `.build-kit/` is only an optional override, so its absence means nothing), skip all platform communication (MCP calls, `update-slice-status`, board sync) and continue working locally.
 - Work on ONE slice per iteration
 - Commit frequently
-- update progress.txt frequently
-- Read the Codebase Patterns section in progress.txt before starting
+- Record learnings as you go with `learn`
+- Read `.build-kit/AGENTS.md` before starting
 
 ## When an iteration completes
 
-Use all the key learnings from the progress.txt and update the `.build-kit/AGENTS.md` file with those learnings.
+Make sure every reusable learning is recorded with `learn`; `.build-kit/AGENTS.md` is generated from them — never edit it by hand.

package/stacks/supabase-react/templates/build-kit/lib/kit.json

@@ -1,3 +1,3 @@
 {
-  "pickupStatus": "Handover"
+  "pickupStatus": "Waiting"
 }

package/stacks/supabase-react/templates/build-kit/lib/prompt.md

@@ -4,17 +4,11 @@ You are an autonomous agent reacting to slice status change events on an Eventmo
 
 ## Your Loop
 
-1. Read `AGENT.md` to load accumulated learnings before doing anything else.
-2. Read `.build-kit/tasks.json`.
-3. If `tasks.json` is empty or missing, reply with:
-   <promise>IDLE</promise>
-   and stop.
-4. Pick the **oldest task** (earliest `createdAt`).
-5. Execute the task — see the Execution section below.
-6. After execution, remove that task from the array and write `.build-kit/tasks.json` back.
-7. Append a progress entry to `progress.txt` (create if missing).
-8. Update `AGENT.md` with any new reusable learnings discovered this iteration.
-9. Reply normally so the next iteration can pick up the next task.
+1. Read `AGENT.md` and, if it exists, `.build-kit/AGENTS.md` to load accumulated knowledge before doing anything else.
+2. The task request at the end of this prompt names your task: its id and the slice change that queued it (`sliceId`, `sliceTitle`, `sliceStatus`, …). It is the oldest one waiting — the run loop picked it for you.
+3. Execute the task — see the Execution section below.
+4. Record any reusable learning with `npx @eventmodelers/cli learn "<one terse line>" --topic <topic>` (see **Recording Learnings**).
+5. Reply normally. The run loop completes the task when your turn ends and hands you the next one in a fresh turn — you never read or write a queue file.
 
 ## Execution
 
@@ -44,13 +38,13 @@ Run `/load-slice sliceId=<payload.sliceId>` to fetch full slice details (title,
 
 Inspect the `sliceStatus` in the payload:
 
-#### `Handover` — build the slice
+#### `Waiting` — build the slice
 
 This is the build trigger. Setting `InProgress` and building are one atomic step:
 
 1. Immediately call `/update-slice-status` to set the slice to `InProgress` on the board.
 
-   **Claim conflict**: if this call reports the slice is already in `InProgress` (or any status other than `Handover`), another agent already claimed it first — this is expected, not an error. Log it in `progress.txt`, drop this task without building, and continue the loop (the next task will naturally cover the next slice). Do not retry.
+   **Claim conflict**: if this call reports the slice is already in `InProgress` (or any status other than `Waiting`), another agent already claimed it first — this is expected, not an error. Say so in your reply, drop this task without building, and continue the loop (the next task will naturally cover the next slice). Do not retry.
 
 2. Run `/load-slice sliceId=<payload.sliceId>` to fetch the full slice, then read the slice definition from `.build-kit/.slices/<contextSlug>/<sliceFolder>/slice.json`. The runner keeps a `slice.json` fresh from a summary endpoint, so a file holding only `id`, `title`, `status` and `sliceType` is that stub, not an empty slice — never conclude a slice has no elements from it. Only if the full fetch itself returns no commands/events/read models/fields is the slice actually empty.
 
@@ -62,7 +56,34 @@ This is the build trigger. Setting `InProgress` and building are one atomic step
 
 4. Invoke the matching skill and follow its instructions **completely**. Do NOT implement the slice manually.
 
-5. **Verify against slice.json**: cross-check the implementation — every command field, event field, and specification in slice.json must appear in the code. No invented fields — if it is not in slice.json, it must not be in the code.
+   **UI baseline gate** — before touching any code, run `npx @eventmodelers/cli ui-baseline check`. It
+   compares the board's node hashes (the slice's screen and every element) and `codeGen.uiPrompts` with
+   what was recorded after the last UI build, and decides what this build has to do:
+   - `UNCHANGED` — nothing on the board changed since the last UI build. Skip all UI work; do not
+     re-fetch or diff the screen. Only now is "no code changes needed" a valid outcome.
+   - `NO_BASELINE` — no UI build recorded yet (first build, or the slice predates the baseline). Do one
+     full screen diff (below), apply every UI prompt.
+   - `UNKNOWN` — the board could not be read. Treat it as `NO_BASELINE`; never as `UNCHANGED`.
+   - `CHANGED` — it also lists, per element, what changed, was added or was removed since the last recorded
+     build (e.g. `changed: Contact Details (screen), Assign Tag (command)`). Work on exactly those nodes
+     and leave what matches alone. Act on the parts it flags:
+     - `SCREEN_CHANGED`: re-fetch the live screen node (`get_node`, its `meta.pages` / `meta.marks`) —
+       never trust the JSX already in the repo — and diff the existing component(s) against the marked
+       (or whole, if unmarked) HTML: tags, classes, layout, copy, fields/buttons added, removed or
+       reordered, and `cssFrameworks`. Edit the components (and `src/pages/<ScreenTitle>.tsx`, for this
+       slice's marked position only) until they match 1:1 and update `samples/`. Keep what already
+       matches; do not regenerate the slice from scratch.
+     - `ELEMENTS_CHANGED`: diff slice.json against the code field by field (fields,
+       `apiEndpoint`/UI contract) and fix every drift.
+     - `PROMPTS_CHANGED`: apply the UI prompts it prints — each is an instruction the user typed on the
+       board for this slice's UI (e.g. "adjust the UI to the new layout!") — to the component(s) and
+       screen markup. Name each prompt and the change you made for it in your final reply.
+
+   When the UI work is done and the checks in step 6 pass, run `npx @eventmodelers/cli ui-baseline record`
+   **before committing**, so `ui-baseline.json` is committed with the slice. Never record without having
+   done the work the verdict asked for.
+
+5. **Verify against slice.json**: first check where every displayed value comes from — screen examples are samples, so names, selections, options and list rows must be bound to the read model (grep the components for the mockup's example strings; hits outside `samples/` are hardcoded data and must be fixed). Then cross-check the implementation — every command field, event field, and specification in slice.json must appear in the code — specifications are read (Step 3a of the build skill) to understand how the UI should behave and present outcomes; the business logic itself lives in the backend and is not re-implemented here. No invented fields — if it is not in slice.json, it must not be in the code.
 
 6. Run `npm run build` and `npm run lint` (both must pass clean) — plus the slice's own tests only, if any exist.
 
@@ -76,26 +97,22 @@ This is the build trigger. Setting `InProgress` and building are one atomic step
 Another agent is already building this slice. Log it and skip — do not build.
 
 #### `Done`
-Summarize what was completed and update `progress.txt`.
+Summarize what was completed in your reply.
 
 #### `Blocked`
-Log the blocker in `progress.txt`.
+State the blocker in your reply.
 
 #### `Review`
-Fetch slice details and prepare a review summary in `progress.txt`.
+Fetch slice details and prepare a review summary in your reply.
 
 #### Any other status (`Created`, etc.)
-Load the slice and log the state transition in `progress.txt`. No build action.
+Load the slice and note the state transition in your reply. No build action.
 
 Use the skills available in `.claude/skills/` to interact with the board.
 
-## Updating tasks.json
-
-After completing a task, remove it from the array and write the updated array back to `.build-kit/tasks.json`. If the array is now empty, write `[]`.
-
 ## Escalating Ambiguity
 
-**Default: make a reasonable assumption and build the slice.** If a detail is unclear or missing (an example value, a field type, a status mapping, a referenced event that isn't modeled yet, ...), pick the most sensible interpretation from `slice.json`, its specifications and the surrounding model, build it, and record each assumption in one line in `progress.txt` and as a code comment. Ambiguity alone is never a reason to stop. **Only if the slice literally cannot be built** — nothing runnable can be produced even with sensible assumptions — invoke `/request-feedback` with the specific question; it posts the question as a comment on the slice and marks it `Blocked`. That must be the absolute exception; a `Blocked` slice should mean "impossible without a human", never "the agent preferred to ask".
+**Default: make a reasonable assumption and build the slice.** If a detail is unclear or missing (an example value, a field type, a status mapping, a referenced event that isn't modeled yet, ...), pick the most sensible interpretation from `slice.json`, its specifications and the surrounding model, build it, and record each assumption in one line as a code comment. Ambiguity alone is never a reason to stop. **Only if the slice literally cannot be built** — nothing runnable can be produced even with sensible assumptions — invoke `/request-feedback` with the specific question; it posts the question as a comment on the slice and marks it `Blocked`. That must be the absolute exception; a `Blocked` slice should mean "impossible without a human", never "the agent preferred to ask".
 
 **Exception: a missing `apiEndpoint`** (no backend endpoint/table decided yet) is a partial version of
 this — flag it, but don't fully stop. `build-state-change`/`build-state-view` Step 1 cover the exact
@@ -105,31 +122,18 @@ sample data. The slice ends this run `Blocked` (step 8 above does not apply for
 `Blocked` instead of setting `Done`), but the code is there, mocked, ready to be pointed at the real
 API once one exists.
 
-## Progress Report Format
-
-APPEND to `progress.txt` (never replace):
-```
-## [ISO timestamp] — Task [task.id]
-
-Slice: [sliceTitle] ([sliceId])
-Status change: [sliceStatus]
+## Recording Learnings
 
-Action taken:
-- [what was done in response to the slice change]
+`.build-kit/AGENTS.md` is generated from the learnings recorded so far — read it at the start of every session, never edit it by hand. Record a learning the moment you have it:
 
-Learnings:
-- [any patterns, gotchas, or reusable knowledge discovered]
----
+```
+npx @eventmodelers/cli learn "<one terse line>" --topic "<topic>"
 ```
 
-## Stop Condition
-
-If `.build-kit/tasks.json` is empty (`[]`) or does not exist, reply with:
-<promise>IDLE</promise>
-
-## Updating AGENT.md
-
-After completing a task, add any **reusable** learnings to `AGENT.md` — patterns, gotchas, API quirks, or skill behaviour that future iterations should know. Only add things that are general and applicable beyond this single task. Do not duplicate what is already there.
+- Only what is genuinely reusable: codebase patterns, gotchas, commands that work or don't, conventions — and, after a failed approach, what was tried and why it failed. Not slice-specific details, and nothing the code or git log already says.
+- One learning per call, one line each. A learning that is already in `.build-kit/AGENTS.md` is skipped for you.
+- `--scope system` for what is true of the modeled domain (a business rule, a naming convention of the model); `repo` (the default) for the codebase and its tooling. `--tag <tag>` labels it (repeatable).
+- One in `.build-kit/AGENTS.md` that turned out wrong or obsolete: `npx @eventmodelers/cli learnings --ids` lists each with its id, `npx @eventmodelers/cli learn --retract <id>` removes it.
 
 ## Important
 

package/stacks/umadb/templates/build-kit/CLAUDE.md

@@ -39,16 +39,16 @@ Ignore case for files and slices in prompts. "CartItems" slice is the same as "c
 
 Do not change test files unless explicitly instructed, or the change brings the test in line with slice.json (e.g. step 4's field/spec diff).
 
-At the start of every session, read `.build-kit/AGENTS.md` if it exists to load accumulated project learnings.
+At the start of every session, read `.build-kit/AGENTS.md` if it exists to load accumulated project learnings. It is generated from the learnings recorded so far — record a new one with `npx @eventmodelers/cli learn "<one terse line>" --topic <topic>`, never by editing the file.
 
-When starting to work on a slice, invoke the `update-slice-status` skill with `InProgress` status before doing anything else.
+When working from a queued task, invoke the `update-slice-status` skill with `InProgress` status before doing anything else. When the task request names the slice to build (a run-loop build), the run loop has already set it to `InProgress` and pushes the final status itself — do not call `update-slice-status`; record the outcome with `npx @eventmodelers/cli slice-status <status>`.
 
 ## Building a Slice
 
 **CRITICAL: You MUST always use the provided skills to build slices. NEVER implement a slice manually.**
 **ALL fields, event names, command names, and business rules MUST come exclusively from slice.json. Do NOT invent, assume, or guess any field or logic not present in the slice definition.**
 
-**Default: make a reasonable assumption and build the slice.** If a detail is unclear or missing (an example value, a field type, a status mapping, a referenced event that isn't modeled yet, ...), pick the most sensible interpretation from `slice.json`, its specifications and the surrounding model, build it, and record each assumption in one line in `progress.txt` and as a code comment. Ambiguity alone is never a reason to stop. **Only if the slice literally cannot be built** — nothing runnable can be produced even with sensible assumptions — invoke `/request-feedback` with the specific question; it posts the question as a comment on the slice and marks it `Blocked`. That must be the absolute exception; a `Blocked` slice should mean "impossible without a human", never "the agent preferred to ask".
+**Default: make a reasonable assumption and build the slice.** If a detail is unclear or missing (an example value, a field type, a status mapping, a referenced event that isn't modeled yet, ...), pick the most sensible interpretation from `slice.json`, its specifications and the surrounding model, build it, and record each assumption in one line as a code comment. Ambiguity alone is never a reason to stop. **Only if the slice literally cannot be built** — nothing runnable can be produced even with sensible assumptions — invoke `/request-feedback` with the specific question; it posts the question as a comment on the slice and marks it `Blocked`. That must be the absolute exception; a `Blocked` slice should mean "impossible without a human", never "the agent preferred to ask".
 
 When asked to build a slice, always follow this flow:
 
@@ -59,9 +59,10 @@ When asked to build a slice, always follow this flow:
    - **State-view** — `projections` or `queries` array is non-empty → invoke `/build-state-view`
    - **State-change** — default (has `commands` / `events`) → invoke `/build-state-change`
 3. Invoke the matching skill and follow its instructions completely. Do not deviate.
-4. **Verify against slice.json**: After the skill completes, check that every command field, event field, and specification in slice.json appears in the implementation. No invented fields — if it is not in slice.json, it must not be in the code. This applies even when the slice was previously `Done` and reappears as `Planned` — never dismiss a mismatch as "already implemented" or harmless drift; diff slice.json against the code field by field and update the code to match every change.
-5. Run quality checks (`./mvnw compile -q`, then the slice tests only).
-6. If checks pass, commit with `feat: [Slice Name]` and set slice status to `Done`. For STATE_VIEW/STATE_CHANGE slices when `handover` is enabled the status to set is `Handover`, not `Done` — see the `ui-contract` skill, Step 4.
+4. **Baseline gate**: run `npx @eventmodelers/cli build-baseline check --scope backend` first and act only on its verdict — `UNCHANGED` means nothing on the board changed since the last recorded build: do not rebuild, just run the slice's tests and finish; `NO_BASELINE`/`UNKNOWN` mean one full field-by-field diff of slice.json against the code; `CHANGED` lists exactly which elements changed, were added or removed — diff and fix only those. After the checks pass and before committing, run `build-baseline record --scope backend`. A screen or UI prompt change never triggers a backend build.
+5. **Verify against slice.json**: After the skill completes, check that every command field, event field, and specification in slice.json appears in the implementation. No invented fields — if it is not in slice.json, it must not be in the code. This applies even when the slice was previously `Done` and reappears as `Planned` — never dismiss a mismatch as "already implemented" or harmless drift; diff slice.json against the code field by field and update the code to match every change.
+6. Run quality checks (`./mvnw compile -q`, then the slice tests only).
+7. If checks pass, commit with `feat: [Slice Name]` and set slice status to `Done`. For STATE_VIEW/STATE_CHANGE slices when `handover` is enabled the status to set is `Waiting`, not `Done` — see the `ui-contract` skill, Step 4.
 
 After you are done, automatically run the tests for the slice that was edited.
 

package/stacks/umadb/templates/build-kit/lib/AGENT.md

@@ -1,12 +1,11 @@
-# Agent Learnings
+# Agent Reference
 
-Patterns and gotchas discovered during task processing. Update this file whenever you encounter something reusable.
+What task processing relies on: the shape of a task and the API facts the skills use. A reusable learning is recorded with `npx @eventmodelers/cli learn "<one terse line>"`, not added here.
 
-## tasks.json
+## Tasks
 
-- Tasks are objects with `id`, `createdAt`, and `payload` (a `SliceChangedPayload`).
-- After completing a task, remove it from the array entirely — do not add a status field.
-- Write `[]` to `tasks.json` if the last task is completed.
+- A task is a slice change the run loop queued: an `id` and a `payload` (a `SliceChangedPayload`). The task request names it.
+- You never read or write a queue file: the run loop completes the task when your turn ends.
 
 ## SliceChangedPayload fields
 
@@ -44,4 +43,4 @@ These files are always up to date — read them directly before invoking any ski
 - The `boardId` and `organizationId` from each payload provide full context — pass them to skills.
 - Node events use `node:created`, `node:changed`, `node:deleted` — always POST to `/api/org/:orgId/boards/:boardId/nodes/events`.
 - Slice metadata (title, status) lives on the SLICE_BORDER node under `meta.sliceStatus` and `meta.title`.
-- `/update-slice-status` rejects moving a slice into a status it's already in — this is a concurrency guard, not a bug. It means another agent already claimed the slice. Treat it as `ALREADY_IN_STATUS`, skip that slice, and move on to the next `Planned` one instead of erroring out.
+- `/update-slice-status` rejects moving a slice into a status it's already in — this is a concurrency guard, not a bug. It means another agent already claimed the slice. Treat it as `ALREADY_IN_STATUS`, skip that slice, and move on to the next `Planned` one instead of erroring out. This applies to queued tasks only: when the task request names the slice to build, the run loop owns its status — never call `/update-slice-status` there.