메뉴
Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a db_path field.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/aden-hive/hive --skill hive-colony-progress-tracker명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | hive.colony-progress-tracker |
| description | Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a db_path field. |
| metadata | {"author":"hive","type":"default-skill","visibility":["worker"]} |
Applies when your spawn message has db_path: and colony_id: fields. The DB is your durable working memory — tells you what's done, what to skip, which SOP gates you owe.
Access via terminal_exec running sqlite3 "<db_path>" "...". Tables: tasks (queue), steps (per-task decomposition), sop_checklist (hard gates).
If your spawn message includes a task_id: field, the queen pre-assigned a specific row to you. Claim that row by id — do not use the generic next-pending pattern below:
sqlite3 "<db_path>" <<'SQL'
UPDATE tasks SET status='claimed', worker_id='<worker-id>',
claim_token=lower(hex(randomblob(8))),
claimed_at=datetime('now'), updated_at=datetime('now')
WHERE id='<task_id>' AND status='pending'
RETURNING id, goal, payload;
SQL
Empty output → another worker raced you or the row is already done. Stop and report. Non-empty → that row is yours, proceed to "Load the plan".
If your spawn message did NOT include task_id: — you are a generic fan-out worker racing on a shared queue. Use the generic next-pending claim:
sqlite3 "<db_path>" <<'SQL'
UPDATE tasks SET status='claimed', worker_id='<worker-id>',
claim_token=lower(hex(randomblob(8))),
claimed_at=datetime('now'), updated_at=datetime('now')
WHERE id=(SELECT id FROM tasks WHERE status='pending'
ORDER BY priority DESC, seq, created_at LIMIT 1)
RETURNING id, goal, payload;
SQL
Empty output → queue drained, exit. Otherwise the returned id is yours. Never SELECT-then-UPDATE — races.
sqlite3 "<db_path>" "SELECT seq, id, title, status FROM steps WHERE task_id='<task-id>' ORDER BY seq;"
sqlite3 "<db_path>" "SELECT key, description, required, done_at FROM sop_checklist WHERE task_id='<task-id>';"
Skip any step where status='done'. That's the point — don't redo completed work.
Before tool calls:
sqlite3 "<db_path>" "UPDATE steps SET status='in_progress', worker_id='<worker-id>', started_at=datetime('now') WHERE id='<step-id>';"
After success (one-line evidence: path, URL, key result):
sqlite3 "<db_path>" "UPDATE steps SET status='done', evidence='<what you did>', completed_at=datetime('now') WHERE id='<step-id>';"
sqlite3 "<db_path>" "SELECT key, description FROM sop_checklist WHERE task_id='<task-id>' AND required=1 AND done_at IS NULL;"
sqlite3 "<db_path>" "UPDATE sop_checklist SET done_at=datetime('now'), done_by='<worker-id>', note='<why>' WHERE task_id='<task-id>' AND key='<key>';"
Never mark a task done while this SELECT returns rows. This gate exists specifically to stop you from declaring success while skipping required steps.
# Success:
sqlite3 "<db_path>" "UPDATE tasks SET status='done', completed_at=datetime('now'), updated_at=datetime('now') WHERE id='<task-id>' AND worker_id='<worker-id>';"
# Unrecoverable failure:
sqlite3 "<db_path>" "UPDATE tasks SET status='failed', last_error='<one sentence>', completed_at=datetime('now'), updated_at=datetime('now') WHERE id='<task-id>' AND worker_id='<worker-id>';"
The AND worker_id=? guard means a reclaimed row won't accept your write — treat zero rows affected as "your claim was revoked, stop."
After done/failed → claim the next task. Exit only when claim returns empty.
busy_timeout=5000 handles most contention silently.SELECT status, count(*) FROM tasks GROUP BY status;SELECT id, goal, status FROM tasks WHERE worker_id='<worker-id>';failed for audit.