kit

Imported from Nebulit-GmbH/Eventmodelers-Build-Kits (eventmodelers-cli/stacks/modeling-kit/templates/kit/AGENTS.md). Install upstream with npx skills add Nebulit-GmbH/Eventmodelers-Build-Kits --skill kit. Copyright stays with the author.

Learnings

Reusable learnings accumulated while processing prompts for this board. Append new ones in a compressed, reusable form; only add if not already covered here.

• /place-element requires an existing column — create one via the timeline API if missing.
• /wdyt posts comments onto nodes — use for analysis only, not modifications. In a chat it shows its findings as a snippet to tick first. A chat message that is "wdyt" always runs it; a review asked in other words may be answered in prose.
• The board_id, timeline_id, and organization_id from each prompt provide full context — pass them to skills that need them.
• If a prompt's context.timelineId is present and non-null, it overrules the prompt's own timeline_id field — it's the chapter the user was pointing at on the canvas, which can differ from whatever chapter the prompt/voice session was scoped to. Resolve TIMELINE_ID from context.timelineId first, falling back to timeline_id only when it's absent, before passing it to any skill.
• Same pattern for node references: if a prompt's context.selectedNodes array is present and non-empty, its first entry overrules the prompt's own node_id field (e.g. for /handle-comment's nodeId) — it reflects the actual canvas selection at prompt time, whereas node_id is only set when the prompt originated from a specific node/comment.
• Same pattern for cell references: if a prompt's context.selectedCell.id is present, it overrules any cell reference (e.g. "A2") parsed from the prompt text — pass it as /place-element's cellName argument and skip the text-parsing fast path entirely.
• Node events POST to /api/boards/:boardId/nodes/events using node:created, node:changed, node:deleted.
• /update-slice-status rejects moving a slice into a status it's already in — this is a concurrency guard so two agents can't both claim the same slice. Treat this as ALREADY_IN_STATUS, not a task failure: drop the prompt, move on to the next task, and do not retry the same update.
• macOS/BSD date silently ignores GNU-only format specifiers like %N/%3N (sub-second precision) instead of erroring — it prints the literal characters, producing a malformed timestamp that only fails downstream. Don't shell out to date for sub-second precision; use $(( $(date +%s) * 1000 )) for whole-second-in-ms, or a runtime call (Date.now(), process.hrtime()) instead.
• Before retrying a failed shell command a second time, diagnose why it failed (e.g. a GNU/BSD flag mismatch) rather than re-running it unchanged — repeating the same command produces the same failure and just burns retries.
• An existing element is addressed by its nodeId, never by a cell. A cell address (B2, AE6) is only needed to place something into a cell, and it is always read, never computed: get_board_outline is the only read that reports a node's cellName (get_nodes/get_node don't). An address inferred from a column letter plus a node's place in a list is a guess, and a guess that happens to name an occupied cell is accepted silently by every cell-addressed tool.
• Orientation and working set are two different reads, in that order: get_board_outline (or get_nodes with projection: "line") answers where is the work, and only then does one full-meta get_nodes, scoped by chapterId/nodeIds, cover the nodes actually being touched. Opening with an unscoped full-meta read pulls every field body and rendered HTML page on the board to answer the cheapest question of the turn.
• Pick each read by what the step needs, cheapest first: get_nodes projection: "line" when ids/titles/types/attribute names suffice (never carries sliceStatus, meta or field types), get_node projection: "cells"/"edges" for a grid or one node's wiring, get_slice_data projection: "outline"/"fields"/"specs" (outline/specs only in json/yaml/toon) over the full graph. Full reads only when a later step reads field types, examples, descriptions, positions, HTML or comments. Table: learn-eventmodelers-api → Which read to use.
• Both reads are once per turn. A chapter's outline and grid don't move unless something writes to them, so re-read only after a structural write. Three get_board_outline calls in one turn means the first two were thrown away.
• Mint ids once per turn, in one shell: for i in $(seq <n>); do uuidgen; done — one per new node, plus one per event, since every event needs its own fresh id (required; not the node id). Nothing in it depends on anything being read, so splitting it across several calls buys round trips for nothing. Never mint a per-event boardId or timestamp — both are server-derived and ignored if sent.
• A subagent is a fresh session: it gets token=/org=/baseUrl=/board= inline as already-resolved values (which satisfies connect at its Step 0 — tell it not to invoke /connect) plus the board state already read for it, inline. Handed bare node ids instead, it has exactly one way to recover the rest — re-reading the whole board, once per agent.
• Dispatch executor agents with model: set to the session header's subagent_model (default sonnet). The judging happened before the dispatch, on this session's model; what's left is execution against a written brief. Keep an agent on the session model only where its piece re-derives modeling structure (a chain's shape, a slice boundary).