@yemi33/minions 0.1.621 → 0.1.622

package/CHANGELOG.md

@@ -1,5 +1,10 @@
 # Changelog
 
+## 0.1.622 (2026-04-08)
+
+### Fixes
+-  add 'When to Stop' to all playbooks missing explicit stop conditions
+
 ## 0.1.621 (2026-04-08)
 
 ### Fixes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@yemi33/minions",
-  "version": "0.1.621",
+  "version": "0.1.622",
   "description": "Multi-agent AI dev team that runs from ~/.minions/ — five autonomous agents share a single engine, dashboard, and knowledge base",
   "bin": {
     "minions": "bin/minions.js"

package/playbooks/ask.md

@@ -38,11 +38,13 @@ Keep it concise but complete. Write for a senior engineer who wants the real ans
 
 ### 4. Status
 
+## When to Stop
+
+Your task is complete once you have written your answer to the inbox file. Do NOT modify code, create PRs, or continue exploring beyond the question. Stop after writing.
+
 ## Rules
 - Do NOT modify any code unless the question explicitly asks you to.
 - Do NOT create PRs or branches — this is a read-only task.
-- Do NOT checkout branches in the main working tree.
-- Read `notes.md` for all team rules before starting.
 
 ## Team Decisions
 {{notes_content}}

package/playbooks/decompose.md

@@ -62,3 +62,7 @@ Keep the total number of sub-items between 2 and 5. If the task genuinely cannot
 {{pr_create_instructions}}
 
 {{pr_comment_instructions}}
+
+## When to Stop
+
+Your task is complete once you have output the JSON decomposition block. The engine parses it from your output. Do NOT begin implementing the sub-items. Stop after outputting the JSON.

package/playbooks/implement-shared.md

@@ -71,5 +71,6 @@ After implementation:
    - Re-run the build
    - If it fails 3 times, report the build errors in your findings and stop
 
-## Signal Completion
+## When to Stop
 
+Your task is complete once you have committed and pushed your changes to the shared branch. Do NOT create a PR — the engine creates one when all plan items are done. Stop after pushing.

package/playbooks/plan-to-prd.md

@@ -100,5 +100,6 @@ Rules for items:
 - For `shared-branch`: agents commit to a single branch — one PR is created automatically when all items are done
 - For `parallel`: each agent creates its own branch and PR
 
-## Signal Completion
+## When to Stop
 
+Your task is complete once you have written the PRD JSON file to `{{team_root}}/prd/{{prd_filename}}`. The engine will detect the file and begin dispatching work. Do NOT create branches, PRs, or modify project code. Stop after writing the JSON file.

package/playbooks/plan.md

@@ -91,8 +91,9 @@ High-level design decisions and rationale.
 - The engine will automatically chain this plan into a PRD conversion step
 - Focus on being thorough but actionable — the PRD agent needs clear items to convert
 
-## Signal Completion
+## When to Stop
 
+Your task is complete once you have written the plan file to `{{team_root}}/plans/{{plan_file}}`. Do NOT begin implementation. Stop after writing the plan.
 
 ## Team Notes
 {{notes_content}}

package/playbooks/test.md

@@ -64,4 +64,8 @@ Include:
 - Localhost URL if applicable
 
 
+## When to Stop
+
+Your task is complete once you have run the tests, written findings to the inbox file, and (if applicable) created a PR with new tests. Stop after writing findings.
+
 Do NOT remove worktrees — the engine handles cleanup automatically.