Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    NaCl for Codex

    2

    Graph-first analysis, specifications and software delivery in Codex, with ten bundled workflow conductors.

    Free

    Security scanned
    NaCl for Codex

    NaCl for Codex

    Example session with this skill installed

    Using the bundled init planner, show a read-only project creation plan for an empty example directory. Do not apply it or configure a graph.

    • Read your context and instructions
    • Compiled the nacl for codex

    Recorded execution of the bundled Node.js project-creation planner, extracted from this package. This is a deterministic command check, not an end-to-end model session. The example directory remained empty after execution; no config, Git repository, graph, or MCP was created. The VERIFIED status below applies only to plan generation.

    {
      "contract": "nacl-project-bootstrap-v1",
      "operation": "project-creation-plan",
      "status": "VERIFIED",
      "code": "PROJECT_CREATION_PLAN_READY",
      "projectRoot": "/private/tmp/nacl-agensi-public-demo-20261007",
      "projectId": "8a21a85c-5737-40d6-a38a-4e1eb3b21f95",
      "projectName": "NaCl example",
      "projectDescription": "",
      "techStack": "",
      "gitAction": "initialize-and-commit",
      "config": {
        "action": "create",
        "path": "/private/tmp/nacl-agensi-public-demo-20261007/config.yaml",
        "sha256": "c13d66d4337dbb4a2ab574a124c35e026bb3c4d1701da5a30a672e210b5bbb4d"
      },
      "agents": {
        "action": "create",
        "path": "/private/tmp/nacl-agensi-public-demo-20261007/AGENTS.md",
        "sha256": "6a761175981ea4fd8384c8b0899f08491f30b92029755966acf94cecbfcb7392"
      },
      "planHash": "2c3c5d2b07448bd90f7aff4a26890fd595e06701ab4c4fc98fc9fcc57d4322e8",
      "confirmation": "CREATE_NACL_PROJECT:2c3c5d2b07448bd90f7aff4a26890fd595e06701ab4c4fc98fc9fcc57d4322e8"
    }
    

    Applying any setup would require the exact fresh confirmation from the selected plan. Graph bootstrap and post-restart MCP verification are separate steps and were not executed in this example.

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

    About this skill

    NaCl is an open-source framework for software delivery with Codex. Requirements, system specifications, relationships, and delivery evidence live in a user-operated Neo4j project graph.

    Included in this download

    One installable nacl-codex skill that routes to ten self-contained conductors: init, business analysis, system analysis, team lead delivery, verification, diagnosis, fixes, bounded goals, Markdown migration, and documentation publishing. Each conductor includes its required references and runtime resources. Built from the Codex 0.2.2 package.

    Installation and first use

    Place the complete nacl-codex folder in your Codex skills directory and start a new task/session. Invoke $nacl-codex and ask it to inspect or initialize your project. The nested conductor names are internal routes, not ten additional registered slash commands.

    Project setup

    The init conductor first produces a read-only plan. Applying project/graph setup requires the exact confirmation token from that plan. Bootstrap configures a per-project Neo4j Community graph and project-local MCP in .codex/config.toml. Open a new task after bootstrap so Codex can discover the MCP; initialization is verified only after actual health, read, and separately confirmed write/read-back checks.

    Requirements and scope

    Codex Desktop/CLI with local file/shell tools and project MCP support, Node.js 20+, and Docker/Compose for local graph setup. Pinned dependency downloads require HTTPS. Python is required by applicable Markdown migration workflows. This package targets Codex; use the separate NaCl for Claude Code listing in Claude Code.

    MIT licensed. Source and documentation: https://github.com/ITSalt/NaCl. The ten conductor frontmatters and resource closure passed local checks. This Agensi entrypoint is a new adapter and has not yet completed an end-to-end agent/project acceptance run. This is an Agensi download, not an official OpenAI catalog publication.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scanned

    Verified clean 12 days ago

    • Free to download with an account

    Listed12 days ago

    What's inside

    Frequently Asked Questions