con un clic
queue-todo-sync
Auto-sync queue DELEGATEs ↔ TODO.md on task lifecycle events
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Menú
Auto-sync queue DELEGATEs ↔ TODO.md on task lifecycle events
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Experiment orchestration framework with traffic allocation, statistical analysis, and early stopping detection. Use to test routing changes, model upgrades, and role assignments with Welch's t-test significance testing.
DEPRECATED — This skill is no longer maintained. Prometheus and Grafana infrastructure was never implemented. Use local JSON metrics analysis instead.
Scaffolds new SPEC-compliant agentic-engineers agents with a single call. Generates SKILL.md frontmatter, test scaffolds (TDD RED-phase), __init__.py, scripts/ layout, and DELEGATE/HANDBACK protocol templates. Use when creating any new automation agent, task handler, or operational tool. Validates role, model, effort, naming, and dependency graphs (circular dep detection) before writing files. Supports dry-run mode for planning without side effects.
Routine maintenance for Codex sessions: monitor queue state, close completed sub-agents, resume or escalate active work, and keep agent capacity available.
Automated cross-validation of protocol queue integrity. Scans all DELEGATEs/HANDBACKs, validates schema compliance, detects cycles, checks rate limits, generates compliance report. Enables self-referential protocol improvements.
Consolidates provider-specific AI costs into unified metrics across Anthropic, OpenAI, Google Gemini, GitHub Copilot, and Ollama. Enables apples-to-apples cost comparison and savings analysis.
| name | queue-todo-sync |
| description | Auto-sync queue DELEGATEs ↔ TODO.md on task lifecycle events |
| license | Proprietary |
| compatibility | agentic-engineers framework v5.10+. Requires Python 3.11+ |
| metadata | {"author":"agentic-engineers","version":"1.0.0","category":"queue","role":"engineer","model":"claude-haiku-4.5","effort":"medium"} |
| status | implemented |
Purpose: Automatically synchronize task queue (DELEGATE/HANDBACK files) with TODO.md to maintain a single source of truth for task tracking.
Status: ✅ Implemented and Tested
The queue-todo-sync skill provides bidirectional synchronization between:
~/.agentic-engineers/queue/incoming/ → TODO.md (add pending tasks)~/.agentic-engineers/queue/done/ → TODO.md (mark tasks complete)opencode-todo-sync command for manual invocationThe Orchestrator automatically invokes this skill:
# Full bidirectional sync
opencode-todo-sync sync
# Generate weekly report
opencode-todo-sync report
# Check for conflicts and issues
opencode-todo-sync check
import importlib
import sys
from pathlib import Path
# Import the skill module (directory has hyphen, so use importlib)
queue_todo_sync = importlib.import_module("src.skills.queue-todo-sync")
TodoSyncManager = queue_todo_sync.TodoSyncManager
manager = TodoSyncManager(
todo_path=Path("TODO.md"),
queue_path=Path.home() / ".agentic-engineers" / "queue"
)
# Sync DELEGATE to TODO
delegate_data = {
"task_id": "2026-05-18-test-task",
"role": "engineer",
"scope": "Test task for queue-todo-sync",
"effort": "medium",
"plan": ["Step 1", "Step 2"],
}
manager.sync_delegate_to_todo(delegate_data)
# Sync HANDBACK to TODO
handback_data = {
"task_id": "2026-05-18-test-task",
"status": "complete",
"timestamp": "2026-05-18T10:00:00Z",
}
manager.sync_handback_to_todo(handback_data)
# Perform full bidirectional sync
result = manager.bidirectional_sync()
print(f"Synced {result['delegates_synced']} DELEGATEs")
print(f"Synced {result['handbacks_synced']} HANDBACKs")
# Generate weekly report
report = manager.generate_weekly_report()
report.write_to_file(Path("reports/sync_report_week_1.md"))
The skill expects TODO.md to follow this format:
# TODO
## IN PROGRESS
- [ ] **TASK-ID:** Task description (Owner: role)
- [ ] **2026-05-18-test-task:** Test task for queue-todo-sync (Owner: engineer)
## COMPLETED
- [x] **TASK-001:** Completed task (Owner: engineer)
- [ ] **TASK-ID:** description (Owner: role)- [x] **TASK-ID:** description (Owner: role)## IN PROGRESS, ## COMPLETED1. DELEGATE created in ~/.agentic-engineers/queue/incoming/DELEGATE-*.yaml
2. Orchestrator invokes queue-todo-sync skill
3. Skill reads DELEGATE file
4. Skill extracts: task_id, role, scope, effort, plan
5. Skill formats as TODO line: - [ ] **TASK-ID:** scope (Owner: role)
6. Skill adds to "## IN PROGRESS" section
7. TODO.md updated
1. HANDBACK created in ~/.agentic-engineers/queue/done/HANDBACK-*.json
2. Orchestrator invokes queue-todo-sync skill
3. Skill reads HANDBACK file
4. Skill extracts: task_id, status, timestamp, quality_score
5. Skill finds matching TODO entry
6. Skill marks as complete: - [x] **TASK-ID:** ...
7. Skill optionally moves to "## COMPLETED" section
8. TODO.md updated
1. Skill reads TODO.md and queue
2. Skill detects conflicts:
- Tasks in TODO but not in queue (orphaned)
- Tasks in queue but not in TODO (missing)
- Tasks with conflicting descriptions (modified in both)
3. Skill applies merge strategy:
- TODO.md manual edits take precedence (human intent preserved)
- Queue entries are authoritative for new tasks
4. Skill generates sync report with recommendations
The skill uses a TODO.md-first merge strategy:
This ensures that manual edits to TODO.md are not overwritten by automated syncs.
The skill generates weekly reports with:
Example report:
# TODO Sync Report
**Week:** 2026-05-18 to 2026-05-24
**Generated:** 2026-05-24T10:00:00Z
## Summary
| Metric | Count |
|--------|-------|
| Total Tasks | 10 |
| Completed | 3 |
| Completion Rate | 30.0% |
| Orphaned Tasks | 1 |
| Missing Tasks | 2 |
| Conflicts | 0 |
## Recommendations
- Review 1 orphaned tasks in TODO.md
- Add 2 missing tasks to TODO.md
The Orchestrator calls this skill at two points:
Post-DELEGATE: After creating a new DELEGATE in queue/incoming/
manager.sync_delegate_to_todo(delegate_data)
Post-HANDBACK: After receiving a HANDBACK in queue/done/
manager.sync_handback_to_todo(handback_data)
The skill provides a CLI wrapper: opencode-todo-sync
# Sync command
opencode-todo-sync sync
# Report command
opencode-todo-sync report
# Check command (detect issues)
opencode-todo-sync check
DelegateEntryRepresents a DELEGATE task entry.
@dataclass
class DelegateEntry:
task_id: str
role: str
scope: str
effort: str
plan: List[str]
created_at: str
Methods:
from_yaml(yaml_content): Parse from YAMLfrom_file(file_path): Parse from fileto_todo_line(): Convert to TODO.md formatto_dict(): Convert to dictionaryHandbackEntryRepresents a HANDBACK task entry.
@dataclass
class HandbackEntry:
task_id: str
status: str
timestamp: str
quality_score: int
confidence: float
deliverables: List[str]
tests: List[str]
Methods:
from_dict(data): Parse from dictionaryfrom_file(file_path): Parse from fileto_todo_line(): Convert to TODO.md format (marked complete)to_dict(): Convert to dictionaryTodoSyncManagerMain synchronization manager.
class TodoSyncManager:
def __init__(self, todo_path: Path, queue_path: Path)
def sync_delegate_to_todo(delegate_data: Dict) -> bool
def sync_handback_to_todo(handback_data: Dict) -> bool
def detect_orphaned_tasks() -> List[Dict]
def detect_missing_tasks() -> List[Dict]
def detect_conflicts() -> List[SyncConflict]
def resolve_conflict(conflict: SyncConflict) -> str
def bidirectional_sync() -> Dict
def generate_weekly_report(week_start: str = None) -> SyncReport
SyncReportRepresents a weekly sync report.
@dataclass
class SyncReport:
week_start: str
week_end: str
total_tasks: int
completed_tasks: int
orphaned_tasks: int
missing_tasks: int
conflicts: int
Methods:
generate(): Generate report as markdownwrite_to_file(file_path): Write report to fileThe skill includes comprehensive tests with >80% coverage:
# Run all tests
pytest src/skills/queue-todo-sync/tests/ -v
# Run with coverage
pytest src/skills/queue-todo-sync/tests/ --cov=src/skills/queue-todo-sync --cov-report=html
# Run specific test
pytest src/skills/queue-todo-sync/tests/test_sync_todo.py::TestDelegateEntry -v
The skill handles errors gracefully:
Owner: Engineer Agent
Last Updated: 2026-05-18
Status: ✅ Production Ready
This skill participates in the framework's continuous improvement cycle (see skill-improvement-feedback).
When you use queue-todo-sync during a task, include a skill_feedback entry in your HANDBACK to help improve it over time:
skill_feedback:
- skill_name: queue-todo-sync
effectiveness_score: 0.85 # required: 0.0–1.0
clarity_score: 0.90 # optional
coverage_gaps:
- "Specific scenario the skill did not address"
improvement_suggestions:
- "Concrete change that would have helped"
usage_context: "One sentence on how you used this skill"
Positive feedback is as valuable as critical feedback. Three or more feedback items for this skill automatically trigger an improvement task.