@fernado03/zoo-flow 0.11.2 → 0.11.3

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@fernado03/zoo-flow",
-  "version": "0.11.2",
+  "version": "0.11.3",
   "description": "Structured workflow templates for AI coding assistants",
   "type": "module",
   "bin": {

package/templates/claude-code/.claude/skills/engineering/commit-and-document/SKILL.md

@@ -30,7 +30,8 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 
 ## Complete
 
-Return completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - commit hash
 - files changed
 - documentation updated

package/templates/claude-code/.claude/skills/engineering/diagnose/SKILL.md

@@ -128,7 +128,8 @@ Write `<session-dir>/root-cause.md`:
 
 Write `<session-dir>/diagnosis.md` with full log (hypotheses, instrumentation results, timeline).
 
-Return completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - `<session-dir>/root-cause.md` path
 - root cause summary
 - fix applied

package/templates/claude-code/.claude/skills/engineering/explore/SKILL.md

@@ -43,7 +43,7 @@ Look for:
 
 ## 4. Report findings
 
-Return completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
 
 - modules/components identified
 - key dependencies and relationships

package/templates/claude-code/.claude/skills/engineering/feature/SKILL.md

@@ -50,7 +50,8 @@ Delegate to implementer profile via `Agent` tool. Implementer executes:
 
 ## 5. Verify and report
 
-Implementer returns completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - feature implemented
 - tests status (all passing)
 - recommended next command (typically `/verify` then `/review` then `/commit-and-document`)

package/templates/claude-code/.claude/skills/engineering/fix/SKILL.md

@@ -41,7 +41,8 @@ Delegate to implementer profile via `Agent` tool. Implementer executes:
 
 ## 4. Verify and report
 
-Implementer returns completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - root cause identified
 - fix implemented
 - regression test added

package/templates/claude-code/.claude/skills/engineering/grill-with-docs/SKILL.md

@@ -29,7 +29,8 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 
 ## Complete
 
-Return completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - documentation location
 - key findings and insights
 - recommended next command (typically `/feature` or `/refactor` if changes needed)

package/templates/claude-code/.claude/skills/engineering/improve-codebase-architecture/SKILL.md

@@ -33,7 +33,8 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 
 ## Complete
 
-Return completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - architecture proposal location
 - key improvements identified
 - recommended next command (typically `/refactor` to implement changes)

package/templates/claude-code/.claude/skills/engineering/prototype/SKILL.md

@@ -28,7 +28,8 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 
 ## Complete
 
-Return completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - prototype location
 - findings and insights
 - recommendations for next steps (proceed with design, explore alternative, or abandon)

package/templates/claude-code/.claude/skills/engineering/refactor/SKILL.md

@@ -42,7 +42,8 @@ Delegate to implementer profile via `Agent` tool. Implementer executes:
 
 ## 4. Verify and report
 
-Implementer returns completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - what was refactored
 - structural improvements achieved
 - tests status (all passing)

package/templates/claude-code/.claude/skills/engineering/review/SKILL.md

@@ -125,7 +125,8 @@ Write `<session-dir>/synthesis.md` with:
 - Prioritized findings by severity
 - Result line: `approve` / `approve with nits` / `changes requested` / `blocked`
 
-Return completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - `<session-dir>/synthesis.md` path
 - brief result line (approve / approve with nits / changes requested / blocked)
 - recommended next command

package/templates/claude-code/.claude/skills/engineering/scaffold-context/SKILL.md

@@ -38,7 +38,8 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 
 ## Complete
 
-Return a summary with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - CONTEXT.md location
 - sections added/updated
 - recommended next command (typically `/explore` to deepen understanding, or `/feature`/`/refactor` to start work)

package/templates/claude-code/.claude/skills/engineering/setup-matt-pocock-skills/SKILL.md

@@ -42,7 +42,8 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 
 ## Complete
 
-Return a summary with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - configuration files updated
 - conventions document location
 - recommended next command (typically `/verify` to ensure config is valid)

package/templates/claude-code/.claude/skills/engineering/tdd/SKILL.md

@@ -54,7 +54,8 @@ After green, suggest `/verify`, then `/review`, then `/commit-and-document` for
 
 ## Complete
 
-Return a summary with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - what was implemented (behaviours, interfaces)
 - tests written (count, pass/fail)
 - status (complete / blocked with reason)

package/templates/claude-code/.claude/skills/engineering/to-issues/SKILL.md

@@ -30,7 +30,8 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 
 ## Complete
 
-Return completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - issues directory location
 - issue count and summary
 - dependency graph

package/templates/claude-code/.claude/skills/engineering/to-prd/SKILL.md

@@ -33,7 +33,8 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 
 ## Complete
 
-Return completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - PRD location
 - summary of requirements
 - recommended next command (typically `/to-issues` to break down into tasks)

package/templates/claude-code/.claude/skills/engineering/triage/SKILL.md

@@ -30,7 +30,8 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 
 ## Complete
 
-Return completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - triage document location
 - prioritized list summary
 - recommended next command (typically `/fix` for bugs, `/feature` for features, or `/refactor` for tech debt)

package/templates/claude-code/.claude/skills/engineering/tweak/SKILL.md

@@ -19,7 +19,8 @@ Use for small known fixes.
 
 ## Complete
 
-Return a summary with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - what was changed (file paths, line ranges)
 - status (complete / blocked with reason)
 - recommended next command

package/templates/claude-code/.claude/skills/engineering/update-docs/SKILL.md

@@ -27,7 +27,8 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 
 ## Complete
 
-Return completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - documentation files updated
 - summary of changes
 - recommended next command (typically `/verify` to ensure docs are accurate)

package/templates/claude-code/.claude/skills/engineering/verify/SKILL.md

@@ -32,7 +32,8 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 
 ## Complete
 
-Return completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - verification commands run
 - pass/fail status for each
 - recommended next command (typically `/review` if passed, or `/fix` if failed)

package/templates/claude-code/.claude/skills/engineering/zoom-out/SKILL.md

@@ -68,7 +68,8 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 
 ## Complete
 
-Return completion with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - `<session-dir>/synthesis.md` file path
 - high-level structure summary
 - recommended next command (typically `/explore` for deeper dive, or `/feature`/`/refactor` if changes needed)

package/templates/claude-code/.claude/skills/productivity/grill-me/SKILL.md

@@ -14,7 +14,8 @@ description: Interview the user about a plan or design until reaching shared und
 
 ## Complete
 
-Return a summary with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - decision tree branches resolved (count)
 - key decisions made (summary)
 - status (complete / blocked with reason)

package/templates/claude-code/.claude/skills/productivity/handoff/SKILL.md

@@ -15,6 +15,7 @@ argument-hint: "What will the next session be used for?"
 
 ## Complete
 
-Return a summary with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - handoff file path (OS temp dir)
 - status (complete / blocked with reason)

package/templates/claude-code/.claude/skills/productivity/teach/SKILL.md

@@ -109,7 +109,8 @@ The user will sometimes express preferences of how they want to be taught, or th
 
 When the user ends the teaching session or says "done" / "stop teaching":
 
-Return a summary with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - lessons created (count, paths)
 - mission status (created / updated)
 - learning records updated (count)

package/templates/claude-code/.claude/skills/productivity/write-a-skill/SKILL.md

@@ -53,7 +53,8 @@ Add when: deterministic op; repeated code; explicit error handling needed.
 
 ## Complete
 
-Return a summary with:
+**COMPLETION PROTOCOL**: Your final text message is your return value. Output this summary, then STOP — do not call any more tools.
+
 - skill created (name, path)
 - files written (SKILL.md, references, scripts)
 - status (complete / blocked with reason)

package/templates/claude-code/CLAUDE.md

@@ -122,6 +122,29 @@ Agent(
 )
 ```
 
+### Agent Completion Protocol
+
+**Critical**: When delegating to an agent via the `Agent` tool, the agent must understand how to return its work:
+
+1. **Your final text message IS the return value** - The parent agent receives exactly what you write as your last message
+2. **Output the completion summary, then STOP** - Do not call any more tools after writing your completion
+3. **Be complete in your final message** - Include all required information (files changed, status, recommendations)
+
+Add this to your agent prompts:
+```
+COMPLETION PROTOCOL:
+Your final text message is your return value to the parent agent.
+When you finish, output a summary with:
+- What was done
+- Status: complete / blocked (with reason)
+- Files changed (if any)
+- Recommended next command (if any)
+
+Then STOP - do not call any more tools or take any more actions.
+```
+
+This is similar to how ultracode's Workflow tool handles subagent completion.
+
 ### Multi-Phase Commands
 
 Commands like `/fix`, `/feature`, and `/refactor` involve multiple phases: