mesh-flow (version 2) for general ai agentic (codex, claude code, opencode)

    2

    Transform brittle prompt chains into robust, artifact-driven DAG workflows with hard gates and explicit traces.

    $6

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    mesh-flow (version 2) for general ai agentic (codex, claude code, opencode)

    Example session with this skill installed

    Compile my project.yaml and run the resulting execution plan to check for any blocked nodes or pending gates.

    • Read your context and instructions
    • Compiled the mesh-flow version 2

    $ mesh compile project.yaml
    ✓ Topology validated (5 nodes)
    ✓ Artifact contracts resolved
    ✓ Emitted: execution-plan.json

    $ mesh run execution-plan.json
    [1/5] draft-plan: DONE (Artifact: plan_v1)
    [2/5] review: BLOCKED (Gate: human_approval required)
    Waiting for operator...

    mesh compile project.yaml

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

    About this skill

    Artifact-Driven DAG Orchestration

    Modern AI agents often fail because of brittle, implicit prompt-chaining. Mesh Flow solves this by providing a robust compile-then-run DAG system that moves orchestration logic out of prompts and into a structured framework. It ensures your multi-agent workflows are predictable, verifiable, and governed by hard-coded logic rather than model probabilities.

    What it does

    • Decouples Topology from Logic: Define your workflow in a single project.yaml identifying nodes by what artifacts they consume and produce.
    • Strict Validation: The compiler checks for circular dependencies, missing artifact producers, and schema violations before execution starts.
    • Enforced Hard Gates: Implement human-in-the-loop approvals, artifact presence checks, and custom verifiers that models cannot bypass.
    • Standardized Adapter Contract: Provides a uniform interface for all skill nodes, ensuring consistent trace logging and error reporting.

    Why use this skill

    Unlike simple sequential prompting, Mesh Flow offers a professional state machine with three distinct failure states (failed, blocked, rejected) and automated recovery paths. It includes a CLI for local validation, execution, and generating Mermaid visualizations of your agent's decision graph. This is essential for developers building production-grade agentic systems where reliability and observability are non-negotiable.

    • Requires Node.js and npm for local CLI execution.
    • No native support for state persistence across multiple CLI sessions.
    • YAML schema version strictly tied to TypeScript source definitions.

    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

    1 use

    Times used to date

    Money-back guarantee

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

    Trust & safety

    Security scan

    Security scan passed 6 months ago

    Requires

    tsx
    Node.js

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed6 months ago

    What's inside

    Frequently Asked Questions

    Mesh Flow replaces fragile, purely text-based prompting with a structured Directed Acyclic Graph (DAG) system, ensuring your agents follow strict logic gates, validate data schemas, and handle errors predictably rather than "hallucinating" their way through a process.

    This skill is designed for highly modular agentic frameworks like Codex, Claude Code, and OpenCode, and it integrates seamlessly with any TypeScript-based environment that can interpret standardized YAML workflow definitions.

    The package includes the core DAG compiler, a CLI tool for local workflow validation and Mermaid diagram generation, a standardized adapter contract for node creation, and comprehensive documentation for the YAML schema.

    Setup involves installing the Mesh Flow package via your preferred manager and initializing a `project.yaml` file to define your artifacts; the included CLI then validates your topology and prepares the environment for execution.

    Mesh Flow provides explicit state management with 'blocked' and 'rejected' states, allowing you to insert "hard gates" where a human or an automated verifier must sign off before the workflow proceeds to the next node.

    Version 2 introduces a more robust artifact-driven architecture and a standardized adapter contract, ensuring that traces and logs are consistent across all nodes in your DAG for better production observability.

    New in Agents & Orchestration