@brainervirus/workit-codex 1.0.0 → 1.0.2

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "workit",
-  "version": "1.0.0",
+  "version": "1.0.2",
   "description": "Adaptive engineering workflow rails for Codex",
   "author": {
     "name": "BrainerVirus"

package/dist/workit-hook.js

@@ -10489,7 +10489,10 @@ check and review kinds auto-bind the current tree and need no digests. Record
 verification evidence last: later evidence or commits can reopen fixed findings
 for re-verification, so verify, resolve, then close with nothing in between.
 decision.record {binding with taskId/workspaceId from inspect plus presented and
-approvedContent} only through a native approval question, task.close {outcome,
+approvedContent} only through a native approval question asked receipt-shaped:
+header Workit decision: <purpose>, the same label repeated in the question
+text (some host UIs do not render headers), exactly two options approved and
+rejected; ask once, never re-ask to mint a receipt. task.close {outcome,
 summary, decisionIds}. A completed native subagent run stops its bound worker
 by itself; if a worker strands in cancelling with its run verifiably over,
 repeat worker.cancel {reason} to confirm the stop. Check and review evidence

package/package.json

@@ -1,14 +1,18 @@
 {
   "name": "@brainervirus/workit-codex",
-  "version": "1.0.0",
+  "version": "1.0.2",
   "private": false,
-  "description": "Workit Codex CLI and desktop plugin",
+  "description": "Workit Codex CLI/desktop plugin — shared MCP transport, hooks, and fourteen method skills",
   "keywords": [
-    "agent",
+    "agentic-coding",
+    "ai-agents",
     "codex",
     "mcp",
+    "model-context-protocol",
+    "plugin",
     "workflow"
   ],
+  "homepage": "https://github.com/BrainerVirus/workit#readme",
   "license": "MIT",
   "repository": {
     "type": "git",
@@ -34,8 +38,8 @@
     "build": "bun scripts/build.ts"
   },
   "dependencies": {
-    "@brainervirus/workit-core": "^1.0.0",
-    "@brainervirus/workit-mcp": "^1.0.0"
+    "@brainervirus/workit-core": "^1.0.2",
+    "@brainervirus/workit-mcp": "^1.0.2"
   },
   "engines": {
     "node": ">=24"

package/skills/workit-babysit/SKILL.md

@@ -31,3 +31,8 @@ selects requirements; do not wait for a rule that can only exist after assess.
 
 PR merged per settings, or a status brief (frontier state, next action) when
 blocked on the human. Record evidence for fixes, findings for blockers.
+
+A squash merge creates a new commit on the base branch, so the pre-merge
+candidate identity changes: re-record verification and review evidence against
+the merged commit before `task.close`, or the close will report unsatisfied
+requirements.

package/skills/workit-challenge/SKILL.md

@@ -28,8 +28,10 @@ selects requirements; do not wait for a rule that can only exist after assess.
    dependency order and recompute after every answer — a wall of questions is
    not an interview.
 4. Funnel every resolution: the moment a consequential choice settles, bind it
-   with a receipt-shaped question (header `Workit decision: <purpose>`, exactly
-   `approved`/`rejected`, the approved description carrying the exact content).
+   with a receipt-shaped question — header `Workit decision: <purpose>` and the
+   same label repeated in the question text (host UIs may not render headers) —
+   exactly `approved`/`rejected` options, the approved description carrying the
+   exact content.
    If the user already stated the choice in conversation and no receipt can be
    minted, record it in task progress and reassess so the settled requirement
    retires — never re-ask to mint a receipt, and never leave it for close to

package/skills/workit-steer/SKILL.md

@@ -20,11 +20,14 @@ selects requirements; do not wait for a rule that can only exist after assess.
    blockers. Never trust memory across an interruption.
 2. Classify the steering:
    - same-task: fold into scope (reassess if facts changed), continue.
-   - new-task: `task.start` + `policy.assess`; the parked task waits.
+   - new-task: `task.pause` the parked lead task, then `task.start` +
+     `policy.assess` for the new one. Keep exactly one active lead per
+     session: external actions bind to that single active task, and a second
+     active lead makes writer authority ambiguous.
    - quick-question: answer from the parked state, then resume.
 3. Handle it with the same rigor as the parked work (no drive-by edits).
 4. Re-anchor: one-line resume brief (where we were, what changed, what
-   is next) before touching the parked work again.
+   is next), then `task.resume` the parked task before touching it again.
 
 ## Completion