@wrongstack/core 0.276.4 → 0.277.0

package/dist/{worktree-manager-DBdl_5rs.d.ts → worktree-manager-C4YIf1Fa.d.ts}

@@ -1,4 +1,4 @@
-import { E as EventBus } from './brain-BLOyN5ZP.js';
+import { E as EventBus } from './brain-CCfuEOdp.js';
 
 /**
  * Lifecycle of a single worktree handle.

package/instructions/leader-after-task.md

@@ -23,6 +23,12 @@ Rules:
 - Items marked `auto="true"` must include the exact input content for copy-paste.
 - Order by priority. Keep each suggestion to one line.
 - Skip during multi-step operations — only show after completion.
+- **If the live `ctx.todos` list still has any `pending` or `in_progress` item,
+  omit the `<next_steps>` tag entirely.** Finishing the in-flight todo list
+  takes priority over offering new prompt options; the runtime gates
+  `<next_steps>` parsing on the same condition so emitting it mid-task would
+  just be parsed-and-discarded, but skipping it keeps the output focused.
+  Re-arm the tag on the turn where the last todo flips to `completed`.
 - If nothing is pending, omit the tag entirely.
 
 **After a significant task**, also post a status update to the inter-agent

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@wrongstack/core",
-  "version": "0.276.4",
+  "version": "0.277.0",
   "license": "MIT",
   "description": "WrongStack core: kernel, types, defaults, and shared utilities for the WrongStack CLI agent.",
   "repository": {
@@ -111,7 +111,7 @@
   ],
   "wrongstackApiVersion": "0.1.10",
   "devDependencies": {
-    "@types/node": "^25.9.3",
+    "@types/node": "^26.0.1",
     "tsup": "^8.5.1",
     "typescript": "^6.0.3"
   },

package/skills/output-standards/SKILL.md

@@ -22,6 +22,7 @@ extract structured data from agent responses.
 5. **Items are prompt inputs** — not imperative instructions. Write what the user would type, not what they should do.
 6. **Items marked `auto="true"` must include input content** — the user can copy and submit it directly.
 7. **Keep concise** — max 5 items unless the task genuinely requires more.
+8. **Skip `<next_steps>` whenever the live `ctx.todos` list still has open items** — any `pending` or `in_progress` todo means the in-flight task list is not done, and surfacing new prompt options would race the todo loop (YOLO+auto could pick the top suggestion and pivot away from the unfinished work; `/next 1` would replace the next todo with an arbitrary prompt). Finish the todo list first, re-arm the tag on the turn where the last todo flips to `completed`. The runtime enforces the same gate, so emitting it mid-task is parsed-and-discarded — the rule exists to keep the output focused, not to override runtime behavior.
 
 ## Output Format
 

package/skills/research-web/SKILL.md

@@ -44,7 +44,7 @@ Not every research task needs the same approach. Match the workflow to the need:
 **Pattern**:
 ```
 search("React latest stable version 2025")  →  discover version
-fetch("https://react.dev/versions")          →  confirm from authoritative source
+fetch("https://react.dev/versions")          →  verify against authoritative source
 context_manager add_note("## Research: React version\n- 19.2.0 (March 2025)\n- Source: react.dev")
 ```
 **Budget**: 1 search + 1 fetch = ~2000 tokens. Done in one turn.