@winton979/task-cli 1.6.1 → 1.6.2

package/README.md

@@ -121,7 +121,7 @@ archive automatically
 /task-explore  →  TASK_READY  →  /task-implement  →  optional /task-audit
 ```
 
-`task-explore` writes the brief for a fresh-session handoff. Briefs should stay within 500 words; they may extend to 1000 only when a shorter contract would omit execution-critical information. Requirements that still do not fit should be split before implementation.
+`task-explore` writes a brief that supports a fresh-session handoff when needed. Before `TASK_READY`, it checks that a new implementation session could determine the goal, acceptance criteria, material constraints, and exclusions from the brief alone. This is a readiness check, not a requirement to start implementation in a new session. The brief preserves confirmed execution-critical context without becoming a repository snapshot; the implementing agent revalidates current repository facts. Briefs should stay within 500 words; they may extend to 1000 only when a shorter contract would omit execution-critical information. Requirements that still do not fit should be split before implementation.
 
 When more than one active brief could match, identify the intended brief when invoking `task-implement`. The implementing agent rechecks repository facts and resolves local, reversible choices from existing conventions. It asks the user only for unresolved decisions that materially affect the contract, records confirmed narrow clarifications in the active brief, and returns material goal, scope, or acceptance changes to `task-explore`.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@winton979/task-cli",
-  "version": "1.6.1",
+  "version": "1.6.2",
   "description": "Lightweight task workflow CLI for AI-assisted development",
   "license": "MIT",
   "repository": {

package/src/init.js

@@ -280,11 +280,14 @@ ${COMPLEXITY_ASSESSMENT_GUIDANCE}
 
 Cross-session Readiness
 
-Before finalizing the brief, assume implementation will start in a fresh session without the exploration conversation.
+Before finalizing the brief, verify that it would be sufficient if implementation later began in a fresh session without the exploration conversation. This is a readiness check; implementation may proceed in the current session.
 
-* Record every confirmed user decision that materially constrains behavior, scope, compatibility, security, data handling, or acceptance.
+Complete this self-check before outputting TASK_READY:
+
+* A fresh implementation session can determine the Goal, Acceptance Criteria, material constraints, and material exclusions from the brief alone.
+* Record every confirmed user decision and other confirmed execution-critical context when omitting it could materially change implementation or validation. This includes material constraints on behavior, scope, compatibility, security, data handling, acceptance, or delivery.
 * Record material exclusions when omitting them could cause plausible scope expansion.
-* Do not copy repository facts the implementing agent can discover. Include only context needed to interpret the contract.
+* Do not turn the brief into a repository snapshot. Record repository facts only when needed to interpret a confirmed constraint; the implementing agent revalidates current facts.
 * Do not output TASK_READY while a material user-owned decision remains unresolved.
 
 Task Brief Format