Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Agentic Run Failure Forensics

    1

    Trace multi-agent failures, separate roots from symptoms, and design the smallest evidence-producing rerun.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Agentic Run Failure Forensics

    Agentic Run Failure Forensics

    Example session with this skill installed

    Objective: Add CSV export and prove it passes tests. Plan v2 requires an independent reviewer to inspect the diff and run pytest tests/test_export.py. Implementer: “CSV export is complete. I did not run tests.” Handoff: “All requirements satisfied.” Reviewer: “Approved based on the implementer report.” Ledger: tests=complete. No test result supplied; export.py is untracked. Why did this multi-agent run fail?

    • Read your context and instructions
    • Compiled the agentic run failure

    EVIDENCE COVERAGE — Plan and roles: PRESENT. Test execution: MISSING. Repository state: PRESENT and conflicts with completion. SUPPORTED FINDING F-01 — FM-3.2 No or Incomplete Verification. Evidence: implementer says tests were not run; reviewer approved from self-report; no test record exists. COMPLETION CONTRADICTION — ledger tests=complete is an assertion, not proof. ROOT/CASCADE CANDIDATE — missing executable gate → unsupported approval → false completion record. MINIMAL RERUN — freeze the diff, run the named test in a clean state, capture result and git status, and block completion when evidence is absent.

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

    About this skill

    Your agents finished. The evidence says the run did not.

    Agentic Run Failure Forensics turns plans, agent traces, handoffs, tool effects, progress ledgers, review reports, tests, git state, and final artifacts into an evidence-bound failure report. It distinguishes observed facts from agent claims, maps supported behavior to the published MAST taxonomy, exposes stale ledgers and false-completion signals, and proposes the smallest rerun that can test a repair hypothesis.

    What it produces

    • Evidence coverage across objective, plan, roles, handoffs, tool effects, verification, repository state, and final result.
    • Intended-versus-observed run reconstruction without filling missing steps.
    • Supported MAST failure classifications with exact evidence pointers and alternatives.
    • Root/cascade map separating entry conditions, contributors, propagation, symptoms, and impact.
    • Ledger and completion contradictions, including reviewer passes that conflict with tests or artifacts.
    • Repair layer selection, minimal rerun plan, and a regression fixture.

    Why it is different

    This is not a generic log summary or another debugging prompt. Dedicated reference protocols govern MAST classification, artifact normalization, evidence status, causal restraint, cascade mapping, repair selection, privacy, and injection isolation. Twelve forward cases cover complete and partial traces, single-agent exclusion, role conflict, handoff loss, premature termination, false reviewer passes, stale ledgers, embedded injection, multiple entry conditions, tool outages, and secret redaction.

    Best for

    • Teams using multi-agent coding or research workflows.
    • Superpowers-style planning, implementation, review, and verification runs.
    • Claude Code, Codex, Cursor, and other agent-host users with inspectable artifacts.
    • Engineers investigating loops, lost handoffs, stale state, or unsupported completion claims.

    Boundaries

    The skill does not debug single-agent prompts, repair code, execute agents, prove causality, certify security, or guarantee that a proposed repair will work. It does not treat MAST as exhaustive. Partial traces produce bounded findings and missing-evidence requests, not reconstructed history.

    Independent product: Designed for Superpowers-style and other multi-agent workflows. Not affiliated with or endorsed by obra, Anthropic, OpenAI, Cursor, or any agent framework.

    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 artifacts from at least two agent roles. Partial traces produce bounded findings and missing-evidence requests, not reconstructed history. A causal root is reported only when a transfer mechanism is supported; otherwise the output lists root candidates. It does not repair code or execute reruns. Runtime compatibility was not forward-tested.

    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

    Money-back guarantee

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

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    Permissions

    No special permissions declared or detected

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This skill analyzes complex multi-agent traces to identify the specific moment a workflow diverged, distinguishing between true root causes and the symptoms that follow. It specifically solves the problem of 'false completions,' where an agent claims success despite failing tests or ignoring ledgers.

    It is designed for any multi-agent workflow that produces inspectable artifacts, including Superpowers-style chains, Claude Code, and custom coding/research agents. While it works best with full traces, it can also process partial data by providing bounded findings and identifying exactly where evidence is missing.

    Upon purchase, you receive the full forensics protocol, evidence-mapping templates, and the specific instruction sets required to implement the MAST failure classification system. It also includes the 'Twelve Forward Cases' logic for handling diverse failure modes like handoff losses and tool outages.

    No, this skill is a diagnostic and forensic tool that produces an evidence-bound report and a rerun plan; it does not directly modify your code or execute agents. It serves as a specialized analysis layer that tells you exactly where your agents failed so you can apply the correct repair manually or through your existing pipeline.

    The skill uses the Multi-Agent System Taxonomy (MAST) to provide a standardized language for failures, mapping every classification to exact evidence pointers. This allows teams to track reliability trends over time rather than treating every failure as a unique, one-off event.

    New in Agents & Orchestration