Skip to content
Agentmart
Submit a tool

mission-control-agent-integration

Umbrella skill for integrating an agent with Mission Control, the orchestration and observability control plane.

Skill by jaydubya818

IndexedMIT★ 2
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/jaydubya818-mission-control-agent-integration

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Umbrella skill for integrating an agent with Mission Control, the orchestration and observability control plane. Use this skill when an agent needs to interact with Mission Control and you must route to the right focused skill — registration, heartbeats, task lifecycle, approvals, deliverables, memory, budget, or run logging. All interactions use Convex mutations and queries; there is no REST API.

Use cases: backend, productivity, finance, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/mission-control-agent-integration

What's inside

Skill name
mission-control-agent-integration
Description
Umbrella skill for integrating an agent with Mission Control, the orchestration and observability control plane. Use this skill when an agent needs to interact with Mission Control and you must route to the right focused skill — registration, heartbeats, task lifecycle, approvals, deliverables, memory, budget, or run logging. All interactions use Convex mutations and queries; there is no REST API.
License
MIT
Compatibility
convex-backend
Instructions
47 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Agent Skills spec issues

  • name: "mission-control-agent-integration" does not match folder "MissionControl"

Files (200)

  • hooks.py · .claude/hooks/scripts/
  • settings.json · .claude/
  • code-simplifier.mdc · .cursor/rules/
  • tdd-verification.mdc · .cursor/rules/
  • .cursorrules
  • .dockerignore
  • .env.example
  • .gitattributes
  • bug_report.md · .github/ISSUE_TEMPLATE/
  • config.yml · .github/ISSUE_TEMPLATE/
  • feature_request.md · .github/ISSUE_TEMPLATE/
  • capability-control.yml · .github/workflows/
  • ci.yml · .github/workflows/
  • remote-sandbox-image.yml · .github/workflows/
  • .gitignore
  • config.json · .taskmaster-ai/
  • state.json · .taskmaster-ai/
  • tasks.json · .taskmaster-ai/tasks/
  • example_prd.txt · .taskmaster-ai/templates/
  • AGENTS.md
  • ARM_PRD_v2.2.docx
  • CLAUDE.md
  • CONTRIBUTING.md
  • FORK_BOUNDARY.md
  • LICENSE
  • QUICK_START.sh
  • README.md
  • SECURITY.md
  • SKILL.md
  • bj.yaml · agents/
  • coder.yaml · agents/
  • compliance.yaml · agents/
  • coordinator.yaml · agents/
  • designer.yaml · agents/
  • finance.yaml · agents/
  • learner.yaml · agents/
  • operations.yaml · agents/
  • qa.yaml · agents/
  • research.yaml · agents/
  • sofie.yaml · agents/
  • storyteller.yaml · agents/
  • strategist.yaml · agents/
  • health.ts · api/
  • release.ts · api/
  • Dockerfile · apps/mission-control-ui/
  • components.json · apps/mission-control-ui/
  • index.html · apps/mission-control-ui/
  • nginx.conf · apps/mission-control-ui/
  • package.json · apps/mission-control-ui/
  • favicon.svg · apps/mission-control-ui/public/
  • ActivityFeed.tsx · apps/mission-control-ui/src/
  • AddPersonModal.tsx · apps/mission-control-ui/src/
  • AgentDashboard.tsx · apps/mission-control-ui/src/
  • AgentDetailFlyout.tsx · apps/mission-control-ui/src/
  • AgentRegistryView.tsx · apps/mission-control-ui/src/
  • AgentSettingsPanel.tsx · apps/mission-control-ui/src/
  • AgentsFlyout.tsx · apps/mission-control-ui/src/
  • AlertRulesModal.tsx · apps/mission-control-ui/src/
  • AnalyticsDashboard.tsx · apps/mission-control-ui/src/
  • AnalyticsView.tsx · apps/mission-control-ui/src/
  • …and 140 more

SKILL.md (first lines)

# Mission Control — Agent Integration

This skill teaches agents how to interact with Mission Control, the orchestration and observability control plane. All interactions use **Convex** mutations and queries — there is no REST API.

## Architecture

- **Database:** Convex (serverless, real-time)
- **Functions:** Convex queries (read-only), mutations (writes), actions (external APIs)
- **Real-time:** All data changes are automatically pushed to connected clients

## Skill Routing Table

Pick the focused skill for the job. Full API contracts live in each skill's `skills/<name>/SKILL.md`.

| When you need to... | Skill | Key API |
|---------------------|-------|---------|
| Announce yourself before any other work | [mission-control-register-agent](skills/mission-control-register-agent/SKILL.md) | `api.agents.register` |
| Stay alive and discover pending work | [mission-control-heartbeat](skills/mission-control-heartbeat/SKILL.md) | `api.agents.heartbeat` |
| Claim, create, or transition tasks | [mission-control-task-lifecycle](skills/mission-control-task-lifecycle/SKILL.md) | `api.tasks.assign` / `api.tasks.transition` / `api.tasks.create` |
| Get sign-off for YELLOW/RED-risk actions | [mission-control-request-approval](skills/mission-control-request-approval/SKILL.md) | `api.approvals.request` |
| Submit finished work or post to task threads | [mission-control-submit-deliverable](skills/mission-control-submit-deliverable/SKILL.md) | `api.contentDrops.submit` / `api.messages.create` |
| Persist knowledge across sessions | [mission-control-record-memory](skills/mission-control-record-memory/SKILL.md) | `api.agentDocuments.upsert` |
| Record spend and respect budget limits | [mission-control-budget-control](skills/mission-control-budget-control/SKILL.md) | `api.agents.recordSpend` |
| Log each execution turn | [mission-control-run-logging](skills/mission-control-run-logging/SKILL.md) | `api.runs.create` |

## Key Rules

1. **Always send heartbeats** — Missing for 2 minutes = quarantine
2. **Use idempotency keys** — Prevent duplicate creates on retries
3. **Respect your budget** — Check budgetRemaining in heartbeat response
4. **Follow the state machine** — Don't skip states (INBOX → ASSIGNED → IN_PROGRESS → ...)
5. **Submit deliverables as content drops** — Don't just complete tasks; submit the actual work
6. **Deposit memories** — Persist important context for future sessions
7. **Log activities** — Keep the audit trail honest

## Quick Start Checklist

1. Call `api.agents.register` with your name, emoji, role, and allowed task types
2. Start a heartbeat loop (every 30-60 seconds)
3. Check `pendingTasks` and `claimableTasks` in heartbeat response
4. Claim an INBOX task → transition to ASSIGNED → IN_PROGRESS
5. Do the work, post progress messages
6. Submit a content drop with the deliverable
7. Transition task to REVIEW → DONE
8. Deposit session memory before shutting down

From jaydubya818/MissionControl, MIT.

More from jaydubya818/MissionControl

Signals

Stars
2
Forks
1
Open issues
4
Last commit
Oct 10, 2026 (19 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from jaydubya818

Cite this page

mission-control-agent-integration skill. Agent Mart. https://agentmart.dev/skills/jaydubya818-mission-control-agent-integration (last updated 2026-10-24)