agentic/code/addons/agent-loop/skills/mission-control/SKILL.md
Orchestrate multi-loop background operations via the Mission Control dashboard — start sessions, dispatch missions, monitor, and stop
npx skillsauth add jmagly/aiwg mission-controlInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You orchestrate multi-loop background operations using the Mission Control dashboard.
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
| Pattern | Example | Action |
|---------|---------|--------|
| Background tasks | "run these tasks in the background" | Start session + dispatch |
| Parallel orchestration | "orchestrate X and Y in parallel" | Start session + dispatch each |
| Monitor loops | "monitor background tasks" | aiwg mc status or aiwg mc watch |
| Start session | "start a mission control session" | aiwg mc start |
| Check status | "how are the background tasks doing?" | aiwg mc status --json |
| Stop missions | "stop background work" | aiwg mc stop |
When triggered:
Determine intent:
aiwg mc start + aiwg mc dispatchaiwg mc statusaiwg mc stopFor new background orchestration — Mission Control has a four-step lifecycle: start → dispatch → run → status. Missions stay queued until mc run launches them as ralph loops; status syncs back to mc.session.json automatically when mc status or mc watch is called.
# 1. Start a named session (creates the state file)
aiwg mc start --name "Sprint 4 Construction"
# 2. Dispatch missions (queues them — does NOT execute)
# --completion is REQUIRED; `mc run` will skip missions without one.
# --max-iterations N caps ralph iterations per mission (default: 10).
aiwg mc dispatch <session-id> "Fix auth service" --completion "npm test passes" --priority high --max-iterations 50
aiwg mc dispatch <session-id> "Add pagination" --completion "all list endpoints paginated"
aiwg mc dispatch <session-id> "Write integration tests" --completion "coverage > 80%" --max-iterations 25
# 3. RUN — drains the queue by launching each mission as a detached ralph
# loop. Without this step missions sit in QUEUED forever (#1439).
aiwg mc run <session-id>
# 4. Monitor — `mc status` polls each ralph loop's session-state.json and
# syncs progress back to mc (queued → running → done|failed|aborted).
aiwg mc status <session-id>
aiwg mc watch <session-id>
For monitoring:
# Dashboard view
aiwg mc status
# Machine-readable for agent orchestration
aiwg mc status --json
# List all sessions
aiwg mc list
For lifecycle management:
# Pause all running missions
aiwg mc pause <session-id>
# Resume paused session
aiwg mc resume <session-id>
# Stop (abort all)
aiwg mc stop <session-id>
# Stop (let running missions finish, cancel queued)
aiwg mc stop <session-id> --drain
Report the result inline — summarize session state and mission progress.
User: "Run these three features in parallel: auth fix, pagination, and test coverage"
Action:
aiwg mc start --name "Parallel Features"
aiwg mc dispatch <id> "Fix auth service" --completion "auth tests pass"
aiwg mc dispatch <id> "Add pagination to list endpoints" --completion "paginated responses"
aiwg mc dispatch <id> "Increase test coverage" --completion "coverage > 80%"
Response: "Started Mission Control session 'Parallel Features' with 3 missions queued. Use aiwg mc status to monitor progress."
User: "How are the background tasks doing?"
Action:
aiwg mc status
Response: "Mission Control 'Parallel Features': 1/3 done, 2 running (auth fix complete, pagination at loop 3/10, coverage at loop 2/10)."
User: "Stop the background tasks, let running ones finish"
Action:
aiwg mc stop <session-id> --drain
Response: "Draining session: 1 queued mission cancelled, 2 running missions will complete naturally."
If the user's intent is ambiguous:
data-ai
Report which research-corpus radar sidecars are overdue for refresh. Computes staleness (days since last refresh vs the cadence window) for every radar, sorted most-overdue-first. Runs via `aiwg corpus radar-status`.
data-ai
Aggregate research-corpus radar sidecars into a corpus or per-cluster freshness report — totals, overdue count, per-cluster / per-GRADE / per-trajectory breakdowns, an overdue table, and per-radar rationale snippets. Runs via `aiwg corpus radar-report`.
testing
Scaffold radar/freshness sidecars for research-corpus REFs. Pulls title/authors from the citation sidecar and GRADE from the analysis doc, defaults the refresh cadence from GRADE and the cluster from a corpus-local map, and stamps documentation/radar/REF-XXX-radar.md. Runs via `aiwg corpus radar-init`.
data-ai
Compute an entity's publication trajectory — per-year paper counts, topic drift, hot-streak detection (≥3 consecutive A-grade years), and career phase. Runs via `aiwg corpus profile-temporal`.