Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Ticket Execution Workflow

    1

    The orchestrator — runs all 9 other skills in deterministic order, from Jira ticket to merged, reviewed, recorded code. One entry point for an entire ticket's lifecycle.

    $4.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Ticket Execution Workflow

    Ticket Execution Workflow

    Example session with this skill installed

    Continue with PROJ-112 — build the post-implementation Jira update skill end to end.

    • Read your context and instructions
    • Compiled the ticket execution workflow

    Summary

    Ran all 10 phases end to end for PROJ-112: fetched the ticket, investigated the real repo, planned and implemented, verified and checked every acceptance criterion, stopped for review, published only after explicit approval, and recorded the real merge in Jira.

    PhaseStatus
    1-7 (intake → acceptance criteria)Complete, no blockers
    8. Human review checkpointHalted here — nothing pushed yet
    9. Approved publicationResumed after "yes, push" → PR opened with --base develop
    10. Jira updatepost-publish, then post-merge → status: Done
    {
      "issueKey": "PROJ-112",
      "phases": {
        "jira-ticket-intake": { "status": "complete" },
        "repository-investigation": { "status": "complete" },
        "human-review-publish-review": { "status": "complete" },
        "human-review-publish-publish": { "status": "complete" },
        "post-implementation-jira-update": { "status": "complete" }
      },
      "haltedAtPhase": null,
      "haltReason": null
    }
    

    Next steps

    • Nothing — PROJ-112 is fully shipped and Jira reflects it honestly. The next "continue with PROJ-XXX" starts a fresh 10-phase run.

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

    About this skill

    This is the entry point: say "continue with PROJ-113" and it runs the other nine skills in this bundle in deterministic order — intake, investigate, plan, branch, implement, verify, check acceptance criteria, stop for human review, publish only on approval, then update Jira at every real milestone. It doesn't reimplement what those skills do; it sequences them, carries each phase's output forward as the next phase's input, and halts the whole run the moment any phase's own stop condition fires — never silently skipping ahead.

    It resumes cleanly, too: after a human's review response (approve, reject, or ambiguous), it picks up exactly where it left off, reusing everything already produced — never re-running completed phases just because time passed. An ambiguous approval is never guessed at; it asks and stays halted.

    Built to recover from the real failure that can happen even in a careful workflow: a publish-phase mistake (e.g. a PR merged into the wrong base branch) gets fixed with only reversible operations — a revert and a clean re-merge, never a force-push or history rewrite — and turned into a standing rule, not a one-off patch.

    This is the flagship of the Ticket-to-Shipped workflow: it composes the other 9 skills in this bundle. Works great as the entry point once you own the full set, or on its own if you've already built equivalent phase skills.

    Needs the other 9 skills in this bundle (or equivalents with matching inputs/outputs) actually present — this is an orchestrator, not a replacement for them. An ambiguous human reply always halts for clarification rather than guessing, so expect occasional back-and-forth at the review checkpoint by design. Never performs a destructive action under any circumstance, including recovery from a publish mistake — recovery is always via revert/re-merge, never a force-push.

    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 any payment.

    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 18 days ago

    Requires

    Jira MCP
    Local Git repository
    Your project's test and build tools
    Git

    Permissions

    Read Files
    Terminal / Shell
    Network Access

    Composes the other 9 skills in this bundle — never expands what any individual phase is allowed to do, and still requires real human approval before anything externally visible.

    Listed18 days ago

    What's inside

    Frequently Asked Questions

    This skill acts as a master orchestrator that sequences Jira updates, codebase analysis, and testing into a strict 10-phase pipeline, preventing the 'context drift' or skipped steps that often occur when using standalone prompts for complex coding tasks.

    It is designed to work with any agentic framework that supports MCP (Model Context Protocol) and tool-calling, specifically coordinating between Jira, Git, and your local build environment (like npm or Maven).

    Yes, the workflow includes a mandatory human-in-the-loop checkpoint where the agent pauses and saves its progress to a 'resumeState' object, allowing you to approve or adjust the plan before any code is published.

    The skill requires access to the Jira MCP for ticket management and the appropriate repository sub-skills (like Git or filesystem tools) to execute the implementation and testing phases.

    The workflow uses a deterministic state-management system that saves the audit trail and context at each phase, ensuring the agent doesn't lose its place even if the underlying model session times out or requires a restart.

    New in Agents & Orchestration