More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    dual model airlock

    1

    Orchestrate cross-model code generation and independent 4-point audits between Gemini, Claude, and Aider CLI agents.

    $5

    /mo

    Subscription · cancel anytime

    Secure checkout via Stripe

    • Always the latest version
    • Delivered live to your agent via MCP
    • Cancel anytime, access ends at period end
    Security scanned
    dual model airlock

    dual model airlock

    Example session with this skill installed

    Use the claude worker to perform a 4-point review on api/auth_handler.py to check for security and concurrency issues.

    • Read your context and instructions
    • Compiled the dual model airlock

    I have initiated the cross-model audit of api/auth_handler.py using the Claude CLI worker. The secondary model has evaluated the code against the 4-point rubric.

    Audit Result: FAIL

    CategoryStatusFindings
    Correctness & ConcurrencyFAILPotential race condition in update_session_token at line 42; missing mutex lock during write.
    Security & IntegrityFAILUnsafe string formatting in SQL query at line 108; susceptible to injection if input is not sanitized.
    Performance & ComplexityPASSEfficient O(1) lookups; standard library used correctly for cryptographic operations.
    VerdictFAILHigh severity defects identified. Remediation required for concurrency and security.

    Execution Receipt

    {
      "task_id": "v8j2n9k1",
      "status": "completed",
      "exit_code": 0,
      "duration_sec": 14.2,
      "receipt_hash": "a1b2c3d4e5f6g7h8",
      "worker": "claude"
    }
    

    Next steps

    1. Apply the suggested mutex lock to the update_session_token function in api/auth_handler.py.
    2. Replace the raw string formatting at line 108 with parameterized SQL queries.
    3. Re-run the review command to verify the fix and flip the verdict to PASS.
    $5/mo

    Subscription · always the latest version

    • Secure checkout via Stripe
    • Cancel anytime
    • Delivered live via MCP

    About this skill

    Single-model coding often suffers from confirmation bias and hallucinated fixes. Dual-Model-Airlock solves this by orchestrating a secondary CLI agent to audit, verify, or execute tasks outside the primary context window.

    What it does

    • Cross-model delegation dispatches scoped coding tasks to a secondary CLI agent with strict timeout and directory boundaries.
    • Independent code auditing runs a 4-point structured rubric through a second model to catch bugs the authoring model missed.
    • Consensus verification compares outputs from two independent models to synthesize a single verified patch for complex problems.
    • Environment discovery identifies available local CLI agents including Claude, Gemini, Codex, and Aider.
    • Integrity tracking generates execution receipts with status codes, duration, and SHA-256 integrity digests for every task.

    How it works

    1. Run a discovery check to identify available CLI coding agents in the local environment.
    2. Define a bounded task specification including objectives, allowed files, constraints, and verification commands.
    3. Dispatch the task or file review to a worker agent using the airlock_runner.py script.
    4. Process the returned JSON execution receipt or audit verdict to finalize the code changes.

    Frameworks & tools

    The skill utilizes a Python-based runner to interface with CLI tools like Claude Code, Google Gemini CLI, Aider, and Codex. It supports local execution and includes an optional REST gateway for multi-threaded orchestration.

    Why this beats prompting it yourself

    Manual multi-model workflows are prone to context leakage and inconsistent review standards. This skill enforces a deterministic 4-point audit protocol and provides structured JSON receipts, ensuring that code is verified by a fresh model instance without the confirmation bias of the original chat session.

    Use cases

    • Audit critical security modules using a secondary model before a pull request merge.
    • Delegate unit test generation to a background CLI agent while you continue architectural work.
    • Resolve complex race conditions by forcing a consensus between two different LLM architectures.
    • Automate a ping-pong resolution loop to fix bugs identified during the cross-review process.

    Known limitations

    Requires Python and local installation of supported CLI agents. Task delegation is restricted to locally accessible files and directory boundaries.

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

    Requires Python and local installation of supported CLI agents like Claude or Aider. Task delegation is restricted to locally accessible files and directory boundaries.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    Software
    GitPython 3.10+
    Optional
    Claude Code CLIGemini CLICodexAider

    Works with any installed CLI coding agent on PATH (claude, gemini, codex, or aider). Zero external pip packages required.

    Permissions

    Terminal / Shell
    Read Files

    Reads the target project file and invokes the user's locally installed CLI coding agent subprocess (claude, gemini, codex, or aider) to run cross-model verification.

    Listed2 days ago

    What's inside

    Frequently Asked Questions

    This skill mitigates LLM 'confirmation bias' by forcing code to be audited or generated by a secondary, independent model instance that doesn't share the primary model's context or assumptions.

    The skill currently supports Claude Code, Google Gemini CLI, Aider, and Codex, provided they are installed and accessible via your local terminal environment.

    No, for security and integrity, the Airlock is designed to work with locally installed CLI agents and files within your specified directory boundaries to ensure data privacy and strict execution control.

    You will receive the core Python-based airlock runner script, the 4-point structured audit rubric templates, a REST gateway for multi-threaded tasks, and full documentation for environment discovery.

    The skill uses a discovery check to identify available agents on your machine and generates SHA-256 integrity digests for every task to ensure the code returned is exactly what the agent produced.

    Yes, the inclusion of an optional REST gateway allows you to integrate the Airlock into your existing CI/CD pipelines or larger agentic workflows for automated pre-merge code verification.

    New in Agents & Orchestration