Mission Control for Parallel Agents

    1

    A live status board for parallel agent workstreams. Structural changes get cards. Counters tick inside existing nodes. A crashed run is marked aborted instead of looking alive.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Mission Control for Parallel Agents

    Example session with this skill installed

    The subagents have been running for 5 minutes. Give me a mission control update on the code migration run.

    • Read your context and instructions
    • Compiled the mission control

    The code migration run is currently executing and live. Two branches are making progress, while the documentation branch is pending upstream completion.

    Mission Control: Code Migration

    graph TD
        A[Analysis]:::done --> B[Refactor: API]:::running
        A --> C[Refactor: UI]:::running
        B --> D[Test: Integration]:::pending
        C --> E[Test: Visual]:::pending
        A --> F[Docs: Update]:::pending
    
        classDef done fill:#f9f,stroke:#333,stroke-width:2px
        classDef running fill:#00ff00,stroke:#333,stroke-width:4px
        classDef pending fill:#eee,stroke:#999,stroke-dasharray: 5 5
    

    Active Nodes

    • Refactor: API: modified 12 / verified 4 | note: processing auth controller
    • Refactor: UI: components 8 / styles 22 | note: migrating tailwind classes

    Annotation Feed

    • lifecycle: Run started at 1715634000000
    • plan_approved: Migration strategy for v2 architecture accepted

    The

    Analysis phase is complete. Parallel refactoring of the

    API and

    UI branches is currently in flight. Testing nodes will remain

    pending until their respective refactor nodes reach a terminal done status.

    Next steps

    1. Monitor the Refactor: API branch for potential blocks on the auth controller.
    2. Signal gate_resolved once the visual test plan is ready.
    3. Run python3 scripts/reduce_events.py events.jsonl for the full raw log.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Parallel agents disappear into chat. This skill keeps one board folded from an append-only event log. Rare structural events (plan proposed, approved, amended, gated, intervened, finished) become cards. Operational updates tick the node you already have, so retries don't spawn new boxes. The board shows phase and whether a worker is live, the plan map with status and counters, branches that are moving, paused, or dead, newest-first cards, and any open human gate. If the process dies, the run closes as aborted. A bundled reducer turns events.jsonl into the board, and --seq N scrubs the timeline. Where it stops: it is not a hosted dashboard.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for DevOps & Cloud.

    Requires append-only event logs with unix ms timestamps and sequence IDs. Not for single-agent linear tasks. Requires Python for event reduction script.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 19 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed19 days ago

    What's inside

    Frequently Asked Questions

    This skill solves the "black box" problem of parallel processing by replacing long, linear chat logs with a structured visual map that shows exactly which subagents are active, blocked, or finished in real-time.

    The skill is framework-agnostic and works with any multi-agent orchestration system that can output event data in JSONL format, including custom Python-based agent swarms.

    You will receive the core logic for the state machine, the event reduction script for folding logs, and a template for rendering real-time status maps via Mermaid syntax.

    By using a two-tier event system and the `reduce_events.py` script, the skill filters out high-frequency operational noise and only feeds essential structural updates back to the LLM, preserving your context window.

    The skill requires an append-only event log with Unix timestamps and is designed for complex, branching workflows; it is not recommended for simple, single-turn agent tasks.

    Updates are handled through the marketplace; when the event reduction logic or visualization templates are optimized, you will receive a notification to download the latest version.

    New in DevOps & Cloud