Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    multi agent failure mode audit

    1

    Static pre-deploy audit for LangGraph, CrewAI, and AutoGen to catch deadlocks and unbounded loops.

    $14

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    multi agent failure mode audit

    multi agent failure mode audit

    Example session with this skill installed

    Audit this LangGraph orchestration for potential deadlocks or unbounded loops. It handles customer support tickets with a retry loop on the search tool and a conditional edge back to the triage node.

    • Read your context and instructions
    • Compiled the multi agent failure

    I have completed the static audit of your LangGraph orchestration. I identified one high-severity structural cycle and one instance of context contamination.

    Multi-Agent Failure Mode Audit Results

    SeverityCategoryLocationFinding (MAST Code)
    HighDeadlocktriage_node -> search_toolFM-1.5 Unaware of Termination Conditions: The conditional edge back to triage on tool failure lacks a hard recursion_limit override or an "attempt_counter" in the state. Relying on the default limit of 25 may mask a no-progress cycle that burns tokens before failing.
    MediumContaminationsearch_tool -> responderFM-2.4 Information Withholding/Contamination: The responder node receives the FullState object. It only requires the search_results and original_query, but is currently inheriting the entire raw JSON trace from the search tool.
    LowBounded Loopsearch_retry blockFM-1.3 Step Repetition: The retry logic uses a fixed sleep with no exponential backoff. While capped, it risks hitting the same rate-limit failure 3 times in rapid succession.

    Next steps

    • Implement a max_retries integer in your GraphState and increment it at the search_tool node.
    • Update the responder node to use a select or TypedDict subset of the state to reduce context bloat.
    • Set an explicit recursion_limit in the compile() call to 15 to catch cycles earlier.

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

    About this skill

    Multi-agent systems often fail in production through "Step Repetition" or deadlock cycles that burn tokens without finishing. Observability tools catch these failures after they cost you money. This skill provides a static, pre-deploy audit of your orchestration source code to identify structural flaws in graph topology, delegation logic, and state-passing design. ## What it does - **Detects deadlocks** by tracing conditional edges and delegation paths for reachable cycles without exit conditions. - **Identifies unbounded loops** in retry logic or multi-agent handoffs that can bypass framework-level iteration caps. - **Audits termination conditions** in AutoGen or LangGraph systems to ensure every possible end-state (text, tool-call, handoff) is covered. - **Flags context contamination** where subagents inherit irrelevant or stale history that degrades performance or bloats costs. ## How it works 1. **Topology Mapping:** The skill reads your LangGraph, CrewAI, or AutoGen code to map every node, agent, and state-passing boundary. 2. **Cycle Analysis:** It checks for framework-specific risks, such as `allow_delegation=True` loops in CrewAI or unreachable exit nodes in LangGraph. 3. **Context Review:** It evaluates the scope of data passed between agents, identifying where full histories should be replaced with scoped state. ## Frameworks & tools Supports LangGraph, CrewAI, AutoGen, and custom orchestration patterns using OpenAI Agents SDK or LlamaIndex. ## Why this beats prompting it yourself Generic prompts often miss framework-specific quirks, like how CrewAI's `max_iter` fails to bound cross-agent delegation cycles. This skill applies a specific failure taxonomy (MAST) to find structural bugs that a general LLM would overlook as "valid" code. ## Use cases - Auditing a complex LangGraph topology before moving from staging to production. - Reviewing a CrewAI team for potential delegation ping-pongs between peer agents. - Validating AutoGen termination logic after adding new tool-calling capabilities. ## Known limitations This is a static code audit, not a runtime tracer. It cannot detect live data drift, spend-cap violations, or adversarial prompt injection attacks.

    Static audit only. Does not monitor live execution, dollar-denominated spend caps, or adversarial security threats. Requires source code access to orchestration logic.

    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 1 month ago

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill performs a static analysis of your code to identify structural flaws like infinite loops and deadlocks before you deploy, saving you from the high token costs and latency associated with runtime failures.

    It has named checks for LangGraph, CrewAI and AutoGen, including mixed setups where one framework calls another. Other orchestration code (a hand-written loop, the OpenAI Agents SDK, LlamaIndex agents) is reviewed with generic pattern checks for exit conditions, progress and context passing. In that case the report states that no framework-specific mechanism was checked, so don't treat it as equivalent coverage.

    No, this is a static code audit that maps your orchestration topology and delegation logic; it does not require access to your live environment or production data.

    The audit is designed to catch framework-specific risks that standard iteration caps often miss, such as delegation 'ping-pongs' in CrewAI or unreachable terminal states in LangGraph.

    The skill instructions and one dated reference file covering the MAST multi-agent failure taxonomy and the loop, delegation and termination behaviour of LangGraph, CrewAI and AutoGen. Your agent produces a ranked static audit of your code. For each finding it can also generate a suggested fix and a pre-ship checklist. There is no bundled tool and no CI/CD integration.

    The skill does not update itself. Its reference was verified on 2026-08-06 and carries a review-by date. Before relying on a specific default value or class name, check it against the current framework docs, as the skill instructs.

    New in Agents & Orchestration