clawctl

Coordination layer for OpenClaw agent fleets (tasks, messaging, activity feed, dashboard).

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "clawctl" with this command: npx skills add lludlow/clawctl

Setup

clawctl init                        # create the database
export CLAW_AGENT=your-name         # set identity (falls back to $USER with warning)
export CLAW_DB=~/.openclaw/clawctl.db  # optional, this is the default

Operational Rhythm

Follow this pattern every session:

  1. clawctl checkin — register presence, see unread count
  2. clawctl inbox --unread — read messages before picking up work
  3. clawctl next — find highest-priority actionable task (or clawctl list --mine)
  4. clawctl claim <id> then clawctl start <id> — take ownership and begin
  5. clawctl msg <agent> "update" --task <id> — coordinate during work
  6. clawctl done <id> -m "what I did" then clawctl next — complete and move on

Only claim tasks assigned to you or matching your role. Completing an already-done task is a safe no-op.

Decision Tree

SituationCommand
New taskclawctl add "Subject" -d "Details"
Find workclawctl next then clawctl claim <id>
Blockedclawctl block <id> --by <blocker-id> and notify via clawctl msg
Finishedclawctl done <id> -m "Result"
Hand offclawctl msg <agent> "Ready for you" --task <id> --type handoff
Ready for reviewclawctl review <id>
Catch upclawctl feed --last 20 or clawctl summary
Link artifactsAdd --meta '{"note":"path/to/file"}' to done, claim, start, or block

Task Statuses

pending → claimed → in_progress → done
                  ↘ blocked ↗    ↘ cancelled
                  ↘ review  ↗

list excludes done/cancelled by default. Use --all for history (newest first).

Commands

Tasks

CommandDescription
add SUBJECTCreate task. -d desc, -p 0|1|2 priority, --for AGENT assign, --parent ID
listActive tasks. --mine, --status STATUS, --owner AGENT, --all
nextHighest-priority actionable task for current agent
claim IDClaim task. --force overrides ownership, --meta JSON
start IDBegin work (in_progress). --meta JSON
done IDComplete. -m note, --force, --meta JSON
review IDMark ready for review. --meta JSON
cancel IDCancel task. --meta JSON
block ID --by OTHERMark blocked. --meta JSON
boardKanban board grouped by status

Messages

CommandDescription
msg AGENT BODYSend message. --task ID, --type TYPE (comment, status, handoff, question, answer, alert)
broadcast BODYAlert all agents
inboxRead messages. --unread for unread only

Fleet

CommandDescription
checkinHeartbeat — update presence, report unread count
register NAMERegister agent. --role TEXT
fleetAll agents with status and current task
whoamiIdentity, role, and DB path

Monitoring

CommandDescription
feedActivity log. --last N, --agent NAME, --meta
summaryFleet overview with counts and recent events
dashboardWeb UI. --port INT, --stop, --verbose

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Botcoin Miner

Mine BOTCOIN by solving AI challenges on Base with stake-gated V3 mining.

Registry SourceRecently Updated
Automation

Skills

Talent advisor skill for AI agents, built by Artemys. Helps your human clarify career direction, build a compelling professional profile, discover relevant o...

Registry SourceRecently Updated
Automation

Claw Recall

Searchable conversation memory that survives context compaction. Indexes session transcripts into SQLite with full-text and semantic search so your agent can...

Registry SourceRecently Updated
Automation

Agent News Digest

키워드 기반 뉴스 수집 및 3줄 요약 에이전트

Registry SourceRecently Updated