lavish-axi 0.1.71 → 0.1.72

package/README.md

@@ -266,7 +266,7 @@ pnpm link
 | `lavish-axi setup plugin`       | Register the installed package as an [Agent Plugin](https://agent-plugins.org) in VS Code, Cursor, and GitHub Copilot CLI; opt-in, idempotent, no marketplace involved. Reload each client afterward.                                                                                                                                                     |
 | `lavish-axi server`             | Run the local Lavish Editor server.                                                                                                                                                                                                                                                                                                                       |
 
-Known playbook IDs: `diagram`, `table`, `comparison`, `plan`, `code`, `input`, `slides`.
+Known playbook IDs: `diagram`, `table`, `comparison`, `plan`, `code`, `input`, `explanation`, `slides`.
 One artifact often combines several playbooks, such as a plan that includes a comparison and a diagram, so agents must match against each `use_when` trigger and open every matching playbook before writing HTML.
 For flows, architecture, state, or sequence diagrams, open the diagram playbook for the recommended tooling and SVG guidance.
 

package/dist/cli.mjs

@@ -249,6 +249,38 @@ var PLAYBOOKS = [
       "End input paths with an obvious way for the user to send feedback back to the agent."
     ]
   },
+  {
+    id: "explanation",
+    use_when: "Explain an existing system, PR, incident, or decision to a reader who was not there - when the goal is understanding what is and why, not choosing a direction or inspecting a plan before implementation",
+    choose: [
+      "Use this when the reader needs to understand something that already exists: a PR's mechanism, an incident's root cause, an architecture, a past decision.",
+      "Use the plan playbook when the reader must inspect and approve an approach before implementation begins; use comparison when they must choose between options.",
+      "Combine with diagram for flows or architecture, table for evidence inventories, and code when the mechanism lives in specific lines."
+    ],
+    structure: [
+      "Lead with the one-sentence answer to the question the reader actually has, before any mechanism.",
+      "Then show only what changed or how it works - a flow or before/after of the relevant slice, not a diagram of the whole system.",
+      "Keep evidence (file paths, line references, links, commands) subordinate to the narrative: cited where a claim needs support, never inlined wholesale.",
+      "Make each claim its own section or annotation target so the reader can push back on exactly the part they disagree with.",
+      "End with what was deliberately left out and where to look next, not a summary that restates the piece."
+    ],
+    design_rules: [
+      "Define unfamiliar terms at first use; for the reader's starting point, follow the diagram playbook's assume-nothing rule rather than restating it here.",
+      "Name the question the explanation answers at the top, so the reader knows whether it is their question.",
+      "Put prose beside figures - inline SVG for the flow or before/after, HTML for the reasoning - per the diagram playbook.",
+      "Link evidence rather than pasting logs or diffs; inlined evidence buries the narrative and goes stale.",
+      "Distinguish verified claims (cited to files, commands, or links) from inference; label uncertain reasoning as a question."
+    ],
+    pitfalls: [
+      "Do not restate the PR body, diff, or ticket file-by-file; the source documents already exist and the reader can open them.",
+      "Do not bury the answer under a diagram of the entire system when the question is about one slice of it.",
+      "Do not present inferred reasoning as verified fact; cite or label it."
+    ],
+    lavish_notes: [
+      "A Lavish explanation should let the reader annotate the exact claim they doubt or want expanded.",
+      "When an explanation surfaces a disagreement, queue prompts that name the claim and the evidence gap."
+    ]
+  },
   {
     id: "slides",
     use_when: "Create a deliberate presentation when slides are requested",
@@ -11492,7 +11524,7 @@ var AGENT_REPLY_JSON_ENVELOPE_BYTES = Buffer.byteLength(JSON.stringify({ text: "
 var AGENT_REPLY_INPUT_LIMIT_BYTES = AGENT_REPLY_JSON_LIMIT_BYTES - AGENT_REPLY_JSON_ENVELOPE_BYTES;
 var AGENT_REPLY_LIMIT_LABEL = "2 MB JSON request limit";
 var CODEX_POLL_WAKE_PATH_GUIDANCE = "Codex detected: completed background tasks may not resume Codex automatically, so keep the poll attached to the active turn.";
-var VERSION = "0.1.71";
+var VERSION = "0.1.72";
 function detectInvokingAgent(env = process.env) {
   return ["CODEX_SANDBOX", "CODEX_THREAD_ID"].some((key) => Object.hasOwn(env, key)) ? "codex" : "generic";
 }
@@ -13045,7 +13077,7 @@ Shut down the background Lavish Editor server. The server also stops itself when
 `,
     playbook: `Usage: lavish-axi playbook [playbook_id]
 
-List focused artifact guidance playbooks, or show one playbook by ID. Known IDs: diagram, table, comparison, plan, code, input, slides.
+List focused artifact guidance playbooks, or show one playbook by ID. Known IDs: diagram, table, comparison, plan, code, input, explanation, slides.
 
 ${PLAYBOOK_ROUTER_HELP}
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "lavish-axi",
-  "version": "0.1.71",
+  "version": "0.1.72",
   "packageManager": "pnpm@11.1.1",
   "description": "HTML is the new markdown. Lavish is the new editor for your HTML artifacts.",
   "type": "module",

package/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "lavish-axi",
-  "version": "0.1.71",
+  "version": "0.1.72",
   "description": "HTML is the new markdown. Lavish is the new editor for your HTML artifacts.",
   "author": {
     "name": "Kun Chen",