@eventmodelers/cli 1.0.124 → 1.0.126

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@eventmodelers/cli",
-  "version": "1.0.124",
+  "version": "1.0.126",
   "description": "Eventmodelers CLI — real-time Claude agent + skills for Claude Code, for any stack (Node, Supabase, Axon, OpenCQRS, UmaDB, Kurrent, or modeling-only)",
   "type": "module",
   "bin": {

package/shared/skills/learn-eventmodelers-api/SKILL.md

@@ -26,7 +26,7 @@ Write tools take their items as an array (`nodeIds[]`, `elements[]`, `connection
 | Tool | Args | Purpose | REST equivalent |
 |---|---|---|---|
 | `list_boards` | — | List boards for the org | §1 `GET /api/boards` (org-scoped) |
-| `get_nodes` | `boardId`, `type?`, `name?`, `chapterId?`, `nodeIds?`, `projection?` (`"line"`) | List nodes, optionally by type and/or a partial case-insensitive title match. **Unscoped with full `meta` it is expensive** — about 2 KB per node, ~1 MB on a 500-node board — so always pass a filter or `projection: "line"`. `chapterId` scopes to one timeline — prefer this over an unscoped board-wide call whenever the step is working within one chapter (the common case); `nodeIds` fetches a known, scattered subset in one call (e.g. re-verifying exactly the nodes just touched by a batch write) instead of a full `type` refetch; `projection: "line"` maps each match to `{id, type, title, fields}` — `fields` being just the attribute names. No `cellName` — an existing node is addressed by its `id`; when a cell address is needed (placing into a cell), read it from `get_board_outline`. No `sliceStatus` — take it per column from `get_board_outline` | §3 `GET .../nodes` (REST records carry no `cellName`, `projection=line` included) |
+| `get_nodes` | `boardId`, `type?`, `name?`, `chapterId?`, `nodeIds?`, `projection?` (`"line"` \| `"fields"`) | List nodes, optionally by type and/or a partial case-insensitive title match. **Unscoped with full `meta` it is expensive** — about 2 KB per node, ~1 MB on a 500-node board — so always pass a filter or a projection. `chapterId` scopes to one timeline — prefer this over an unscoped board-wide call whenever the step is working within one chapter (the common case); `nodeIds` fetches a known, scattered subset in one call (e.g. re-verifying exactly the nodes just touched by a batch write) instead of a full `type` refetch; `projection: "line"` maps each match to `{id, type, title, fields}` — `fields` being just the attribute names; `projection: "fields"` to `{id, type, title, parentId, fields}` with the full field definitions (type, example, idAttribute, …) but no html, description, sketch or grid data. No `cellName` — an existing node is addressed by its `id`; when a cell address is needed (placing into a cell), read it from `get_board_outline`. No `sliceStatus` — take it per column from `get_board_outline` | §3 `GET .../nodes` (REST records carry no `cellName`, `projection=line`/`fields` included) |
 | `get_node` | `boardId`, `nodeId`, `projection?` (`"cells"` \| `"edges"`) | Get one node (no `cellName` — address it by `nodeId`; cell addresses come only from `get_board_outline`). `projection: "cells"` (CHAPTER nodes only) returns just `{rows, columns, cells}` instead of the full `timelineData` — use whenever only the grid/occupancy is needed, not the whole chapter; `projection: "edges"` returns just that node's inbound/outbound connections instead of `findNodeById`'s full record. Both are opt-in — omitting `projection` is the unchanged full response. An unknown id is a `NODE_NOT_FOUND` error | §3 `GET .../nodes/:nodeId` (REST returns the node as stored, without `cellName`; `404` carries `code: 'NODE_NOT_FOUND'`) |
 | `get_node_comments` | `boardId`, `nodeId` | List comments on a node | §1 `GET .../nodes/:nodeId/comments` |
 | `get_chat_attachment` | `boardId`, `sessionId`, `attachmentId` | The file a chat message came with — the message's `attachments` list `{id, type, ending}`. Images come back as images, a PDF as an embedded resource, csv / xml / txt / json as text. Only the agent the message was addressed to can read it (`CHAT_ATTACHMENT_NOT_FOUND`); needs the connection's `x-agent-id` (`CHAT_AGENT_REQUIRED`). Max 5 MB per file. | §15 `GET /api/org/:orgId/chat/sessions/:sessionId/attachments/:attachmentId` |
@@ -83,13 +83,14 @@ Pick the cheapest read that answers the step's question, and name the reason in
 | a chapter's grid / cell occupancy | `get_node { nodeId: <chapterId>, projection: "cells" }` |
 | one node's connections | `get_node { nodeId, projection: "edges" }` |
 | what is where in a chapter (incl. cell names for placement), plus `sliceStatus` per column | `get_board_outline` |
-| field types, examples, descriptions, positions, HTML | full `get_nodes`, scoped by `chapterId` or `nodeIds` — never board-wide when avoidable |
+| field types, examples, field descriptions | `get_nodes` with `projection: "fields"`, scoped by `chapterId` or `nodeIds` |
+| a node's description, position, HTML | full `get_nodes`, scoped by `chapterId` or `nodeIds` — never board-wide when avoidable |
 | finding slices / their elements / element counts | `get_slice_data` with `projection: "outline"` (format `json`/`yaml`/`toon`) |
 | attribute, field-flow or completeness work | `get_slice_data` with `projection: "fields"` |
 | scenario / spec review, spec coverage | `get_slice_data` with `projection: "specs"` (format `json`/`yaml`/`toon`) |
 | elements **and** specs **and** comments/prompts together (e.g. a business review) | full `get_slice_data` — say why |
 
-Two cheap projected calls (e.g. `outline` + `specs`) beat one full call when the step doesn't need comments, prompts or field bodies. `projection: "line"` never carries `sliceStatus`, `meta`, positions, field types or examples — if a later step reads any of those, use the full read. `get_nodes { type: "CHAPTER" }` without a projection returns every chapter's full grid; to just list or pick chapters, add `projection: "line"`.
+Two cheap projected calls (e.g. `outline` + `specs`) beat one full call when the step doesn't need comments, prompts or field bodies. `projection: "line"` never carries `sliceStatus`, `meta`, positions, field types or examples; `projection: "fields"` adds the full field definitions and `parentId`, still no `sliceStatus`, positions or node description — if a later step reads any of those, use the full read. `get_nodes { type: "CHAPTER" }` without a projection returns every chapter's full grid; to just list or pick chapters, add `projection: "line"`.
 
 ---
 
@@ -473,21 +474,21 @@ List all nodes on a board.
 - `type?: ElementType` — exact match.
 - `name?: string` — partial, case-insensitive title match.
 - `chapterId?: string` — only nodes placed in this chapter (timeline).
-- `projection?: "line"` — compact `{id, type, title, fields?}` per node (`fields` = attribute names only, absent on nodes without fields) instead of the full record. Neither form carries `cellName` — address existing nodes by `id`. Any other value is `400 PROJECTION_INVALID`.
+- `projection?: "line" | "fields"` — `line`: compact `{id, type, title, fields?}` per node (`fields` = attribute names only, absent on nodes without fields); `fields`: `{id, type, title, parentId, fields?}` with the full field definitions as stored, but no html, description, sketch or grid data. Either instead of the full record. Neither form carries `cellName` — address existing nodes by `id`. Any other value is `400 PROJECTION_INVALID`.
 - `cellId?: string` — return only the node occupying this timeline cell (format `<rowId>-<colId>`). Requires `timelineId`. Empty array if the cell is unoccupied.
 - `colId?: string` — return every node occupying this column, across *all* rows of the timeline (e.g. to check for an existing COMMAND/READMODEL/SCREEN/AUTOMATION before placing one, since the server caps those at one per column even across separate lane rows). Requires `timelineId`. Combine with `type` to narrow to one element type.
 - `timelineId?: string` — the CHAPTER node `cellId`/`colId` are resolved against. Required together with either of those two; `400` if omitted.
 
 Cell/column occupancy lives only in the CHAPTER node's `meta.timelineData.cells`, never on the node rows themselves — this endpoint resolves `cellId`/`colId` against that timeline internally so callers don't have to fetch and parse the whole chapter node just to check occupancy.
 
-**Response**: `200` — node record array (or `line` projections). `400` — `cellId`/`colId` given without `timelineId`, `PROJECTION_INVALID`, or `QUERY_PARAM_INVALID`. `404` — `timelineId` doesn't reference an existing CHAPTER node with grid data.
+**Response**: `200` — node record array (or `line`/`fields` projections). `400` — `cellId`/`colId` given without `timelineId`, `PROJECTION_INVALID`, or `QUERY_PARAM_INVALID`. `404` — `timelineId` doesn't reference an existing CHAPTER node with grid data.
 
 ---
 
 ### POST `/api/org/:orgId/boards/:boardId/nodes/query`
 Fetch a known set of nodes in one call.
 
-**Body**: `{ "ids": string[], "projection"?: "line" }` — `ids` non-empty. Missing ids are silently omitted. Without `projection`, full stored records; `line` gives the compact shape above. Neither carries `cellName`.
+**Body**: `{ "ids": string[], "projection"?: "line" | "fields" }` — `ids` non-empty. Missing ids are silently omitted. Without `projection`, full stored records; `line`/`fields` give the shapes above. Neither carries `cellName`.
 
 **Response**: `200` — node array. `400` — `ids` empty/not an array, or `PROJECTION_INVALID`.
 

package/stacks/modeling-kit/templates/.claude/skills/detect-model-drift/SKILL.md

@@ -65,11 +65,10 @@ Index the result in memory: per slice → commands, events, read models, screens
 
 The code base is the directory resolved in Step 0 (`$EVENTMODELERS_CODE_DIR`, else the current directory) — every path below is relative to it, and it may hold any stack. Find out which, don't assume.
 
-**With a `branch` other than the one checked out, read the code from git, never from the working tree:** `git ls-tree -r --name-only $REF [<dir>]` lists the files, `git show $REF:<path>` reads one. That applies to everything below — `.build-kit/CLAUDE.md`, the `.build-kit/.slices` snapshot, the slice folders. Never `git checkout`/`git switch`: the working tree may hold someone's uncommitted work. Without `branch`, or when it is the current branch, read the working tree as usual.
+**With a `branch` other than the one checked out, read the code from git, never from the working tree:** `git ls-tree -r --name-only $REF [<dir>]` lists the files, `git show $REF:<path>` reads one. That applies to everything below — `.build-kit/CLAUDE.md`, the slice folders. Never `git checkout`/`git switch`: the working tree may hold someone's uncommitted work. Without `branch`, or when it is the current branch, read the working tree as usual.
 
 1. Read `.build-kit/CLAUDE.md` (and `.build-kit/AGENTS.md` if present) — its *Structure* section says where slices live and how they're named (e.g. `src/slices/{slice}/` for Node, `src/main/java/.../slices/{context}/{slice}/` for Axon).
-2. If `.build-kit/.slices/<context>/<slice>/slice.json` exists, it is the snapshot the code was **last built from** — useful for telling "the code changed" apart from "the model changed since the build" (see Step 5).
-3. Without a build kit, infer the layout from the repo (folders named after slices, `*Command*`, `*Event*`, projection/read-model files, route/UI files). If you cannot find any slice structure, stop and tell the user what you looked at — do not fabricate a mapping.
+2. Without a build kit, infer the layout from the repo (folders named after slices, `*Command*`, `*Event*`, projection/read-model files, route/UI files). If you cannot find any slice structure, stop and tell the user what you looked at — do not fabricate a mapping.
 
 Build a **code inventory** per slice folder: the command type and its fields, the events it emits and their fields, read-model/projection types and fields, the screens/components/routes wired to it, tests and what they assert, and what each handler/projection/automation reads and writes.
 
@@ -109,9 +108,7 @@ For every finding, pick who should move:
 
 | Evidence | Fix goes to | How it's done |
 |----------|-------------|---------------|
-| Code differs from `.build-kit/.slices` snapshot (read from the same branch as the code), board still equals the snapshot | **Model** — the code moved on deliberately | Skill that changes the board: `/attributes` (fields), `/timeline` / `/place-element` (elements), `/eventmodeling-elaborating-scenarios` (specs), `/storyboard-screen` or `/html-screen` (screens — including updating every existing screen connected to a changed element, see below) |
-| Board differs from the snapshot, code still equals it | **Code** — the model moved on | Set the slice back to `Planned` with `/update-slice-status` so the build kit picks it up again and diffs code against `slice.json` |
-| Both moved, or no snapshot | **Judgement call** — present both options, recommend one | Recommend by which side is more specific/complete |
+| A field, element, spec, screen or edge differs | **Judgement call** — present both options, recommend one | Recommend by which side is more specific/complete. Model fix: `/attributes` (fields), `/timeline` / `/place-element` (elements), `/eventmodeling-elaborating-scenarios` (specs), `/storyboard-screen` or `/html-screen` (screens — including updating every existing screen connected to a changed element, see below). Code fix: set the slice back to `Planned` with `/update-slice-status` so the build kit picks it up again |
 | Slice only in code | **Model** | Add the slice, via `/eventmodeling-slicing-event-models` after placing its elements |
 | Slice missing in code, board says `Done` | **Model status** (it isn't done) | `/update-slice-status` → `Planned` |
 
@@ -190,3 +187,4 @@ Omit empty sections. Say plainly when nothing drifted.
 - Fixing drift on the model side means updating the existing screens connected to the changed elements too (pages and `meta.fields`), in place — not just the command/event/read model.
 - `--branch` reads the code via `git ls-tree`/`git show` from that ref — never check it out, the working tree may hold someone's uncommitted work. No `--branch` = the working tree, as before.
 - Always read the MARKDOWN note in the feedback lane of each chapter's first column first — it is the chapter's context, and differences it explains are not drift.
+- `.build-kit/.slices` is no evidence for the direction of a fix: every fetch, `/load-slice` and runner loop rewrites it, so it holds the last fetch, not what the code was built from — reading it as "the build" recommends undoing board changes. The direction is a judgement call.

package/stacks/modeling-kit/templates/.claude/skills/discover-storyboard/SKILL.md

@@ -235,7 +235,8 @@ mcp__eventmodelers__submit_node_events {
     "changedAttributes": ["meta.title"],
     "meta": { "type": "CHAPTER", "title": "<flow name>" },
     "node": { "id": "<CHAPTER_ID>", "data": {} }
-  }]
+  }],
+  "compact": true
 }
 ```
 

package/stacks/modeling-kit/templates/.claude/skills/eventmodeling-brainstorming-events/SKILL.md

@@ -116,7 +116,8 @@ mcp__eventmodelers__submit_node_events {
     "eventType": "node:changed",
     "nodeId": "<chapterId>",
     "meta": {"type": "CHAPTER", "title": "Reservation & Lending"}
-  }]
+  }],
+  "compact": true
 }
 ```
 
@@ -219,7 +220,8 @@ mcp__eventmodelers__submit_node_events {
         {"name": "reservedAt",    "type": "DateTime", "example": "2026-05-29T10:00:00Z"}
       ]
     }
-  }]
+  }],
+  "compact": true
 }
 ```
 

package/stacks/modeling-kit/templates/.claude/skills/eventmodeling-designing-automation-chains/SKILL.md

@@ -88,7 +88,8 @@ mcp__eventmodelers__place_element {
     "elementType": "READMODEL",
     "title": "NotificationsToSend",
     "columnIndex": <automationColumnIndex - 1>
-  }]
+  }],
+  "compact": true
 }
 ```
 Then set `meta.fields` and `meta.listElement: true` on the returned node id:
@@ -98,7 +99,8 @@ mcp__eventmodelers__submit_node_events {
   "events": [{
     "id": "<event-uuid>", "eventType": "node:changed", "nodeId": "<returned-node-id>",
     "meta": {"type": "READMODEL", "title": "NotificationsToSend", "fields": [...], "listElement": true}
-  }]
+  }],
+  "compact": true
 }
 ```
 
@@ -114,11 +116,11 @@ For a **translation-chain automation**, place its three columns left to right in
 
 1. **READMODEL → AUTOMATION first** — the automation reads its own todo list. The closing connection below is only accepted once this edge exists.
    ```
-   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<readmodelNodeId>", "target": "<automationNodeId>", "action": "connect" }] }
+   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<readmodelNodeId>", "target": "<automationNodeId>", "action": "connect" }], "compact": true }
    ```
 2. **Every opening EVENT → READMODEL.**
    ```
-   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<openingEventNodeId>", "target": "<readmodelNodeId>", "action": "connect" }] }
+   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<openingEventNodeId>", "target": "<readmodelNodeId>", "action": "connect" }], "compact": true }
    ```
 3. **Every closing EVENT → READMODEL — worker-stage todo lists only.** Including the automation's own resulting event, even though that event is produced by the command this same automation issues. This is not a backward arrow: `EVENT → READMODEL` connections are exempt from column ordering when the read model already has a `READMODEL → AUTOMATION` edge (see `learn-eventmodelers-api` §3) — this todo-list read model qualifies because of the edge from step 1 above. A read model in this shape is a live projection, not a frozen snapshot — a later event closing an earlier-opened item is the normal case, not an exception to reach for only when convenient. **Do not add this edge for a translation automation's todo list** — it has no closing event at all (see the translation-chain rule above); wiring one back is a modeling error, not a convenience.
 

package/stacks/modeling-kit/templates/.claude/skills/eventmodeling-identifying-inputs/SKILL.md

@@ -151,7 +151,8 @@ mcp__eventmodelers__place_element {
   "elements": [{
     "elementType": "COMMAND",
     "title": "ReserveBike"
-  }]
+  }],
+  "compact": true
 }
 ```
 `place_element` finds/creates the empty cell in the interaction lane in the correct column and places the node. Pass each entry's `fields` in the same call when the attributes are already known; otherwise follow up with `submit_node_events` (`node:changed`) to set `meta.fields` (with `mapping`/`generated`/`cardinality` per the rules above) on the node it returned:
@@ -171,7 +172,8 @@ mcp__eventmodelers__submit_node_events {
         {"name": "startTime",  "type": "DateTime", "example": "2026-06-01T09:00:00Z","mapping": "user-input"}
       ]
     }
-  }]
+  }],
+  "compact": true
 }
 ```
 
@@ -203,7 +205,7 @@ After `place-element` returns the COMMAND node ID, create the arrows that comple
    ```
    Read `cells["<actorRowId>-<columnId>"]` for the occupying node id (a cell id absent from that sparse array is empty — no SCREEN placed yet). Then connect with the type-checked edge tool, which auto-corrects direction and skips duplicates:
    ```
-   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<screenNodeId>", "target": "<commandNodeId>", "action": "connect" }] }
+   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<screenNodeId>", "target": "<commandNodeId>", "action": "connect" }], "compact": true }
    ```
    If wiring more than one COMMAND in the same pass, put every SCREEN→COMMAND and COMMAND→EVENT pair across all of them into one `set_connection` call's `connections` array (see step 2 below) instead of one call per pair.
 
@@ -219,7 +221,7 @@ After `place-element` returns the COMMAND node ID, create the arrows that comple
    ```
    Read `cells["<swimlaneRowId>-<columnId>"]` for the occupying node id, then:
    ```
-   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<commandNodeId>", "target": "<eventNodeId>", "action": "connect" }] }
+   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<commandNodeId>", "target": "<eventNodeId>", "action": "connect" }], "compact": true }
    ```
 
    **Fallback (no MCP):** see `references/api-fallback.md` — "Wire connections — Step 2: COMMAND → EVENT".

package/stacks/modeling-kit/templates/.claude/skills/eventmodeling-identifying-outputs/SKILL.md

@@ -260,7 +260,8 @@ mcp__eventmodelers__place_element {
     "elementType": "READMODEL",
     "title": "ActiveReservationView",
     "columnIndex": <consumerScreenColumnIndex>  // or <automationColumnIndex - 1> for an AUTOMATION consumer
-  }]
+  }],
+  "compact": true
 }
 ```
 Then set `meta.fields` (with `mapping`/`generated`/`cardinality`) — and `meta.listElement: true` if this read model is list-shaped — on the returned node id:
@@ -270,7 +271,8 @@ mcp__eventmodelers__submit_node_events {
   "events": [{
     "id": "<event-uuid>", "eventType": "node:changed", "nodeId": "<returned-node-id>",
     "meta": {"type": "READMODEL", "title": "ActiveReservationView", "fields": [...]}
-  }]
+  }],
+  "compact": true
 }
 ```
 To determine the consumer's column index beforehand, or to check whether a specific interaction cell is already occupied (`get_nodes` filters by `type`, `name`, `chapterId` and `nodeIds`, but has no `cellId` filter — see the note under "Wire connections" below), fetch the chapter and read its cell map — `projection: "cells"` returns just `{rows, columns, cells}`, not the whole chapter node:
@@ -327,7 +329,7 @@ After `place-element` returns the READMODEL node ID, create the arrows that comp
    ```
    mcp__eventmodelers__get_node { "boardId": "<BOARD_ID>", "nodeId": "<CHAPTER_ID>", "projection": "cells" }
    # → read cells["<swimlaneRowId>-<columnId>"] for the occupying node id
-   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<eventNodeId>", "target": "<readmodelNodeId>", "action": "connect" }] }
+   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<eventNodeId>", "target": "<readmodelNodeId>", "action": "connect" }], "compact": true }
    ```
 
    **Fallback (no MCP):** see `references/api-fallback.md` — "Step 5h.1 — Wire EVENT → READMODEL".
@@ -336,7 +338,7 @@ After `place-element` returns the READMODEL node ID, create the arrows that comp
 
    **Prefer MCP:**
    ```
-   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<readmodelNodeId>", "target": "<screenNodeId>", "action": "connect" }] }
+   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<readmodelNodeId>", "target": "<screenNodeId>", "action": "connect" }], "compact": true }
    ```
 
    **Fallback (no MCP):** see `references/api-fallback.md` — "Step 5h.2 — Wire READMODEL → SCREEN".
@@ -347,7 +349,7 @@ After `place-element` returns the READMODEL node ID, create the arrows that comp
 
    **Prefer MCP:**
    ```
-   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<readmodelNodeId>", "target": "<automationNodeId>", "action": "connect" }] }
+   mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<readmodelNodeId>", "target": "<automationNodeId>", "action": "connect" }], "compact": true }
    ```
 
    **Fallback (no MCP):** see `references/api-fallback.md` — "Step 5h.3 — Wire READMODEL → AUTOMATION".

package/stacks/modeling-kit/templates/.claude/skills/eventmodeling-orchestrating-event-modeling/SKILL.md

@@ -163,7 +163,7 @@ For a "what is on the board and how is it wired right now" check between steps
 
 **Structural validation is one call, not a scan.** `validate_model` (`{boardId, chapterId}`) runs the whole structural checklist server-side — unplaced nodes, backward arrows (todo-list exception applied), zero/multi-issuer commands, sourceless read models, two-screens-in-a-column, missing scenarios — and returns only `findings`. Use it for the mandatory post-step unplaced check and as the first move in Step 9, instead of per-type `get_nodes` loops and `get_node` `projection: "edges"` spot-checks.
 
-**Ask echo-heavy write tools for less.** `add_scenario`, `add_storyline`, `set_connection` and `submit_node_events` each accept `compact: true`, which drops the full-object echo from the response (returning `{specNodeId, added, count, isNewNode}`, a `{connected, existed, removed, notFound, failed, errors}` tally, or `{persisted: <count>}` respectively). Pass it whenever you're not going to read individual fields back off the response — which is almost always for a large `set_connection` batch or a bulk scenario post.
+**Ask echo-heavy write tools for less.** `place_element`, `add_scenario`, `add_storyline`, `set_connection` and `submit_node_events` each accept `compact: true`, which drops the full-object echo from the response (returning `{nodeId, cellName, columnIndex}` per placed node, `{specNodeId, added, count, isNewNode}`, a `{connected, existed, removed, notFound, failed, errors}` tally, or `{persisted: <count>}` respectively). Pass it by default — every example in these skills does — and drop it only when a later step reads a field the compact form leaves out (e.g. `place_element`'s `autoConnected` edge list). Failures are still reported in full either way.
 
 ### Documenting decisions inline, at any step
 
@@ -440,7 +440,8 @@ Not delegated to a separate skill — performed directly by this orchestrating s
        "id": "<event-uuid>", "eventType": "node:created", "nodeId": "<node-uuid>",
        "chapterId": "$CHAPTER_ID", "cellId": "<feedbackLaneId>-<firstColumnId>",
        "meta": { "type": "MARKDOWN", "title": "Modeling Reasoning — <Chapter Name>", "description": "<full markdown body>" }
-     }]
+     }],
+     "compact": true
    }
    ```
 

package/stacks/modeling-kit/templates/.claude/skills/eventmodeling-storyboarding-events/SKILL.md

@@ -263,7 +263,8 @@ mcp__eventmodelers__submit_node_events {
     "chapterId": "<CHAPTER_ID>",
     "cellId": "<actorRowId>-<columnId>",
     "meta": {"type": "SCREEN", "title": "<Screen Title>", "fields": [...]}
-  }]
+  }],
+  "compact": true
 }
 ```
 

package/stacks/modeling-kit/templates/.claude/skills/examples/SKILL.md

@@ -37,7 +37,7 @@ with a `confirm` snippet — `CLAUDE.md` § *Locked slices in a chat* — and po
 
 `target` is singular, but the common real request is "fill in the examples across this chapter". When you have more than one target, **do not run this skill once per element and do not fetch context a node at a time.**
 
-1. Read the chapter **once**: `mcp__eventmodelers__get_nodes { "boardId": "$BOARD_ID", "chapterId": "$CHAPTER_ID" }`. That single response carries every element's `meta.fields` *including the `example` values already filled in* — which is exactly the canonical-value pool Step 3c asks for, for the whole chapter, in one call.
+1. Read the chapter **once**: `mcp__eventmodelers__get_nodes { "boardId": "$BOARD_ID", "chapterId": "$CHAPTER_ID", "projection": "fields" }`. That single response carries every element's `fields` *including the `example` values already filled in*, without the html, descriptions and grid data a full read drags along — which is exactly the canonical-value pool Step 3c asks for, for the whole chapter, in one call.
 2. Pick the canonical value per field name from that pool (e.g. `customerId: "cust-123"`, `email: "jane@example.com"`) before writing anything, so every element ends up consistent.
 3. Then generate every target's values and write them all in a single `submit_node_events { events: [...] }` call — one `node:changed` event per element, never one call per element.
 
@@ -105,7 +105,8 @@ mcp__eventmodelers__submit_node_events {
     "nodeId": "<TARGET_NODE.id>",
     "changedAttributes": ["meta.fields"],
     "meta": { "fields": "<updated-fields-array>" }
-  }]
+  }],
+  "compact": true
 }
 ```
 

package/stacks/modeling-kit/templates/.claude/skills/html-screen/SKILL.md

@@ -105,7 +105,8 @@ mcp__eventmodelers__submit_node_events {
       "marks": [{"id": "em-abc123", "color": "#e74c3c", "pageIndex": 0, "blurOutside": true, "whiteOutside": false}],
       "fields": [...]
     }
-  }]
+  }],
+  "compact": true
 }
 ```
 
@@ -181,7 +182,8 @@ mcp__eventmodelers__submit_node_events {
     "meta": { "type": "HTML_SCREEN", "fields": [
       {"name": "status", "type": "String", "example": "confirmed", "mapping": "ActiveReservationView.status", "cardinality": "Single"}
     ] }
-  }]
+  }],
+  "compact": true
 }
 ```
 

package/stacks/modeling-kit/templates/.claude/skills/place-element/SKILL.md

@@ -50,7 +50,8 @@ mcp__eventmodelers__place_element {
     "columnIndex": <position,
     if given>,
     "fields": [{ "name": "orderId", "type": "String", "example": "ord-1" }]
-  }]
+  }],
+  "compact": true
 }
 ```
 
@@ -132,7 +133,8 @@ mcp__eventmodelers__add_scenario {
   "boardId": "<BOARD_ID>",
   "timelineId": "<TL>",
   "columnId": "<COL>",
-  "scenarios": [ /* same scenario objects as the curl body below */ ]
+  "scenarios": [ /* same scenario objects as the curl body below */ ],
+  "compact": true
 }
 ```
 
@@ -335,7 +337,8 @@ mcp__eventmodelers__submit_node_events {
     "cellId": "<CELL_ID>",
     "meta": { "type": "<ELEMENT_TYPE>", "title": "<title>" },
     "node": { "data": { "title": "<title>" } }
-  }]
+  }],
+  "compact": true
 }
 ```
 
@@ -356,7 +359,8 @@ mcp__eventmodelers__submit_node_events {
     "cellName": "<CELL_NAME>",
     "meta": { "type": "<ELEMENT_TYPE>", "title": "<title>" },
     "node": { "data": { "title": "<title>" } }
-  }]
+  }],
+  "compact": true
 }
 ```
 
@@ -385,7 +389,7 @@ Take the inbound edges (`target === COMMAND_NODE_ID`) and resolve their source t
 - **2 or more** → keep the edge whose source sits in the COMMAND's own column (the deliberate, same-slice issuer) and remove every other one:
 
 ```
-mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<extra-issuer-node-id>", "target": "<COMMAND_NODE_ID>", "action": "remove" }] }
+mcp__eventmodelers__set_connection { "boardId": "<BOARD_ID>", "connections": [{ "source": "<extra-issuer-node-id>", "target": "<COMMAND_NODE_ID>", "action": "remove" }], "compact": true }
 ```
 
 If it's not clear which edge is the deliberate one (e.g. neither source sits in the COMMAND's own column), do not guess — leave both edges and post a comment on the COMMAND node via `handle-comment` instead, describing the ambiguity.
@@ -416,4 +420,4 @@ Timeline: <timelineId>
 
 ## Example — place an EVENT via curl
 
-A full worked example (add column → fetch chapter → create node) placing an EVENT called "Order Placed" at the end of a timeline lives in `references/api-fallback.md`'s "Full worked example" section. With MCP connected, the same result is one call: `mcp__eventmodelers__place_element { "boardId": "<BOARD_ID>", "timelineId": "<TIMELINE_ID>", "elements": [{ "elementType": "EVENT", "title": "Order Placed" }] }` (see "Prefer MCP" above).
+A full worked example (add column → fetch chapter → create node) placing an EVENT called "Order Placed" at the end of a timeline lives in `references/api-fallback.md`'s "Full worked example" section. With MCP connected, the same result is one call: `mcp__eventmodelers__place_element { "boardId": "<BOARD_ID>", "timelineId": "<TIMELINE_ID>", "elements": [{ "elementType": "EVENT", "title": "Order Placed" }], "compact": true }` (see "Prefer MCP" above).

package/stacks/modeling-kit/templates/.claude/skills/storyboard/SKILL.md

@@ -230,7 +230,8 @@ mcp__eventmodelers__submit_node_events {
     "id": "<event-uuid>", "eventType": "node:changed", "nodeId": "<SCREEN_NODE_ID>",
     "changedAttributes": ["meta.fields"],
     "meta": { "type": "HTML_SCREEN", "fields": [ /* planned fields */ ] }
-  }]
+  }],
+  "compact": true
 }
 ```
 

package/stacks/modeling-kit/templates/.claude/skills/storyboard-screen/SKILL.md

@@ -126,7 +126,8 @@ mcp__eventmodelers__submit_node_events {
     "meta": { "type": "SCREEN", "fields": [
       {"name": "status", "type": "String", "example": "confirmed", "mapping": "ActiveReservationView.status", "cardinality": "Single"}
     ] }
-  }]
+  }],
+  "compact": true
 }
 ```
 

package/stacks/modeling-kit/templates/.claude/skills/timeline/SKILL.md

@@ -290,7 +290,8 @@ mcp__eventmodelers__submit_node_events {
     "cellId": "<CELL_ID>",
     "meta": { "type": "EVENT", "title": "<EventName>" },
     "node": { "id": "<node-uuid>", "data": { "title": "<EventName>" } }
-  }]
+  }],
+  "compact": true
 }
 ```
 
@@ -300,7 +301,7 @@ mcp__eventmodelers__submit_node_events {
 
 **Prefer MCP:** this whole "find/create a column, compute the cell, place the node" sequence collapses into one call:
 ```
-mcp__eventmodelers__place_element { "boardId": "<BOARD_ID>", "timelineId": "<CHAPTER_ID>", "elements": [{ "elementType": "EVENT", "title": "<EventName>", "columnIndex": <index> }] }
+mcp__eventmodelers__place_element { "boardId": "<BOARD_ID>", "timelineId": "<CHAPTER_ID>", "elements": [{ "elementType": "EVENT", "title": "<EventName>", "columnIndex": <index> }], "compact": true }
 ```
 Extract `nodeId` and `columnId` directly from the tool result.
 
@@ -343,7 +344,8 @@ mcp__eventmodelers__submit_node_events {
     "changedAttributes": ["meta.title"],
     "meta": { "type": "EVENT", "title": "<NewTitle>" },
     "node": { "id": "<eventNodeId>", "data": {} }
-  }]
+  }],
+  "compact": true
 }
 ```
 

package/stacks/modeling-kit/templates/.claude/skills/walkthrough/SKILL.md

@@ -111,7 +111,7 @@ Per step:
 mcp__eventmodelers__post_chat_message {
   "boardId": "$BOARD_ID",
   "replyTo": "<message_id>",
-  "text": "Registration in 5 steps — pick a step to jump to it, or press Play.",
+  "text": "Registration in 5 steps — step through it here, or press Play.",
   "snippet": {
     "kind": "walkthrough",
     "title": "How registration works",