release: v1.4.0 — Prompt & Template Improvements

.claude-plugin/marketplace.json

@@ -8,7 +8,7 @@
     {
       "name": "agent-team",
       "description": "Orchestrates parallel work via Agent Teams with automated coordination, workspace tracking, and hook enforcement",
-      "version": "1.3.0",
+      "version": "1.4.0",
       "source": {
         "source": "url",
         "url": "https://github.com/ducdmdev/agent-team-plugin.git"

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "agent-team",
   "description": "Orchestrates parallel work via Agent Teams with automated coordination, workspace tracking, and hook enforcement",
-  "version": "1.3.0",
+  "version": "1.4.0",
   "author": {
     "name": "Duc Do"
   }

CHANGELOG.md

@@ -5,6 +5,17 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.4.0] - 2026-02-28
+
+### Added
+- Re-read workspace instruction in all spawn templates (prevents context drift)
+- Team metrics section in final report template
+- Custom roles reference in Phase 1 decomposition
+
+### Changed
+- `tasks.md` workspace template now groups tasks by status (In Progress / Blocked / Pending / Completed)
+- TeammateIdle hook updated to parse grouped tasks.md format
+
 ## [1.3.0] - 2026-02-27
 
 ### Added

docs/report-format.md

@@ -52,6 +52,17 @@ This file is generated during Phase 5, step 6. It is the last file written befor
 ### Follow-up Items
 {Bulleted list of anything that needs attention after the team disbanded}
 
+### Team Metrics
+
+| Metric | Value |
+|--------|-------|
+| Tasks | {completed}/{total} |
+| Issues | {resolved}/{total} ({critical}C {high}H {medium}M {low}L) |
+| Handoffs | {count} |
+| Blocked events | {count} |
+| Remediation cycles | {0 or 1} |
+| Re-plans | {count, 0 if none} |
+
 ---
 
 ## Full Audit Trail

docs/worker-roles.md

@@ -89,6 +89,7 @@ Communication protocol — send structured messages to the lead:
 
 Rules:
 - Read and analyze only. Do not modify any files.
+- Before starting each new task, re-read workspace files (progress.md, tasks.md, issues.md) to ensure you have current state. This prevents context drift on long-running sessions.
 - Report findings with specific file references (path:line).
 - Read workspace files before asking the lead questions — the answer may already be there.
 - When blocked, message the lead immediately with the BLOCKED format above.
@@ -119,6 +120,7 @@ Communication protocol — send structured messages to the lead:
 
 Rules:
 - ONLY modify files in your owned area. If you need changes elsewhere, message the lead.
+- Before starting each new task, re-read workspace files (progress.md, tasks.md, issues.md) to ensure you have current state. This prevents context drift on long-running sessions.
 - Send STARTING before beginning each task. Send COMPLETED after finishing (include files changed).
 - Verify your work compiles/passes basic checks before marking tasks complete.
 - Read workspace files before asking the lead questions — the answer may already be there.
@@ -159,6 +161,7 @@ In COMPLETED messages, include total counts: "N issues: X high, Y medium, Z low"
 
 Rules:
 - Read and analyze only. Do not modify files.
+- Before starting each new task, re-read workspace files (progress.md, tasks.md, issues.md) to ensure you have current state. This prevents context drift on long-running sessions.
 - Include specific file:line references and fix suggestions for every high-severity issue.
 - Read workspace issues.md to avoid reporting known/duplicate issues.
 - When you find a cross-cutting issue that affects another teammate's scope, use HANDOFF.
@@ -189,6 +192,7 @@ Communication protocol — send structured messages to the lead:
 
 Rules:
 - Actively try to break or disprove what other teammates produce.
+- Before starting each new task, re-read workspace files (progress.md, tasks.md, issues.md) to ensure you have current state. This prevents context drift on long-running sessions.
 - Back every critique with evidence: specific code, concrete scenarios, or references.
 - Don't just criticize — propose alternatives when you find problems.
 - Read workspace files to understand what decisions were already made and why.
@@ -225,6 +229,7 @@ In COMPLETED messages, include total counts: "N tests: X passed, Y failed, Z ski
 
 Rules:
 - Run existing test suites and write new tests as needed to verify implementation correctness.
+- Before starting each new task, re-read workspace files (progress.md, tasks.md, issues.md) to ensure you have current state. This prevents context drift on long-running sessions.
 - Do not modify implementation code. If you find a bug, report it via HANDOFF to the lead.
 - Include reproduction steps for every failure.
 - Read workspace files before asking the lead questions — the answer may already be there.

docs/workspace-templates.md

@@ -53,9 +53,25 @@ Cross-teammate information transfers.
 
 **Last updated**: {timestamp}
 
-| ID | Subject | Owner | Status | Blocked By | Notes |
-|----|---------|-------|--------|-----------|-------|
-| {id} | {subject} | {owner} | pending / in_progress / completed | {IDs or "—"} | {brief notes} |
+## In Progress
+
+| ID | Subject | Owner | Notes |
+|----|---------|-------|-------|
+
+## Blocked
+
+| ID | Subject | Owner | Blocked By | Notes |
+|----|---------|-------|-----------|-------|
+
+## Pending
+
+| ID | Subject | Owner | Blocked By | Notes |
+|----|---------|-------|-----------|-------|
+
+## Completed
+
+| ID | Subject | Owner | Notes |
+|----|---------|-------|-------|
 ````
 
 ## issues.md

package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-team-plugin",
-  "version": "1.3.0",
+  "version": "1.4.0",
   "description": "Claude Code plugin for orchestrating parallel work via Agent Teams",
   "license": "MIT",
   "keywords": ["claude-code", "plugin", "agent-team", "orchestration", "parallel"],

scripts/check-teammate-idle.sh

@@ -54,8 +54,13 @@ if [ "$RETRY_COUNT" -ge "$MAX_RETRIES" ]; then
 fi
 
 # Count in-progress tasks owned by this teammate by parsing the markdown table.
-# Match Owner column (col 4) and Status column (col 5) in pipe-delimited table.
-IN_PROGRESS=$(awk -F'|' -v owner="$TEAMMATE" 'tolower($4) ~ tolower(owner) && tolower($5) ~ /in_progress/' "$TASKS_FILE" 2>/dev/null | wc -l | tr -d ' ')
+# The grouped format uses section headers (## In Progress) as status indicators.
+# Match Owner column (col 4) within the "## In Progress" section.
+IN_PROGRESS=$(awk -F'|' -v owner="$TEAMMATE" '
+  /^## In Progress/ { in_progress=1; next }
+  /^## / { in_progress=0 }
+  in_progress && NF >= 4 && tolower($4) ~ tolower(owner)
+' "$TASKS_FILE" 2>/dev/null | wc -l | tr -d ' ')
 
 if [ "$IN_PROGRESS" -gt 0 ]; then
   # Increment retry counter

skills/agent-team/SKILL.md

@@ -46,6 +46,7 @@ Analyze the user's task: $ARGUMENTS
    - **By layer**: data model vs API vs UI (best for full-stack features)
    - Avoid splits that create heavy cross-dependencies — if two streams need constant handoffs, merge them
 6. **Integration points** — for each pair of streams, identify where their outputs must connect (shared interfaces, API contracts, database schemas). These become explicit handoff points in Phase 2.
+7. **Check for custom roles** — if `docs/custom-roles.md` exists in the project, read it. Use custom roles alongside built-in roles when they match the task requirements.
 
 **Self-check**: "Do I have 2+ streams where each can make meaningful progress without waiting on the others? Are integration points identified?" If no, reconsider the split.