Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Evidence-Backed Root Cause

    1

    Makes your agent cite a real line for every claim in an incident report. A script confirms each quote exists in your files and limits the confidence it can report.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Evidence-Backed Root Cause

    Evidence-Backed Root Cause

    Example session with this skill installed

    Checkout started returning 500s this evening. The files are in ./incident. Find out why, and only tell me what you can back up.

    • Read your context and instructions
    • Compiled the evidence-backed root cause
    • Generated the data export

    This uses the sample incident in examples/, which ships with the skill. The checker output is real output from running verify_rca.py on those files, so you can reproduce it. The staging test in the sample report is part of the sample data.

    Summary

    Likely cause: release v412 cut the payment service's database pool from 40 to 4. Status supported, confidence 0.9.

    What supports it

    HandleSourceQuote
    E1deploys.log:32026-03-04T18:55:12Z payment-service v412 rollout complete
    E2config.diff:6+ pool_size: 4
    E3payments.log:32026-03-04T19:02:07Z ERROR pool timeout: waited 30000ms for connection
    E4db-metrics.csv:42026-03-04T19:05:00Z,18,4

    What else was considered

    The database became slow (H2). Rejected: E4 shows query p95 at 18 ms during the incident.

    Checker result

    {
      "status": "supported",
      "hypothesis": "H1",
      "stated_confidence": 0.9,
      "confidence": 0.9,
      "confidence_cap": 0.95,
      "citation_validity": 1.0,
      "independent_kinds": 4,
      "reasons": [],
      "dropped_citations": []
    }
    

    The same incident with a made-up story

    examples/bad-report.json blames a database failover and states 0.95 confidence. The checker rejects it:

    {
      "status": "unsupported",
      "stated_confidence": 0.95,
      "confidence": 0.0,
      "citation_validity": 0.0,
      "reasons": [
        "no valid evidence supports the conclusion",
        "0 independent evidence kind(s), 3 are needed for more than 0.75",
        "the cause was not verified by a test or a fix",
        "cause_evidence must name a valid supporting item",
        "no alternative hypothesis was considered"
      ],
      "dropped_citations": [
        "H1: E1 is invalid (quote not found in source)",
        "H1: E9 does not exist"
      ]
    }
    

    Next steps

    1. Restore pool_size to 40 or roll back v412.
    2. Confirm that pool timeouts stop in payments.log.
    3. Add a review or alert for large pool size changes.

    db-metrics.csv

    CSV · data export

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    About this skill

    During an outage, a plausible wrong answer costs more than "I don't know yet". This skill makes your agent show its work: every claim cites a handle, every handle points to an exact line in a real file, and a script checks those lines before any confidence is reported.

    What it does

    • Checks every citation. verify_rca.py looks for each quote in the cited file. Quotes that aren't there, and handles that don't exist, are dropped and listed.
    • Limits confidence by fixed rules. It takes the lower of the agent's own number and a cap. The cap falls for unexplained contradictions, few independent evidence kinds, no verification, and no alternative considered. It never goes above 0.95.
    • Checks that the cause came first. If the cited cause is dated after the symptom began, the report is unsupported.
    • Requires a real alternative. A rival with equal support and nothing against it holds confidence at 0.5.
    • Gives a clear result. supported, tentative, or unsupported, with reasons and an exit code.

    What's in the package

    • SKILL.md: the investigation routine your agent follows
    • scripts/verify_rca.py: the checker, in Python standard library only, with no network calls, reading only inside the folder you name
    • references/report-format.md: the report format and the exact rules
    • references/evidence-guide.md: where to look first, common traps, and causes that are easily confused
    • examples/: a sample incident with one report that passes and one that fails

    Good fit

    • Outages, error spikes, latency regressions, and failed deployments
    • Postmortems that need to hold up under questions
    • Teams who want to check an agent's conclusions quickly

    Known limitations

    • It confirms a quote exists, not what it means. An agent can still misread a real line.
    • It can't catch faked source files. Evidence must come from your real systems.
    • Passing doesn't prove the cause. It means the reasoning meets fixed rules.
    • The thresholds are judgement calls. They're adapted from a benchmarked system and aren't calibrated to your environment.
    • You supply the data. It doesn't connect to your log or metric tools, so export what you need to a folder first.

    Where it comes from

    The approach comes from Sentinel, my open-source AIOps platform, where cited evidence and capped confidence are part of the investigation pipeline. The benchmark results published for Sentinel measure that system, not this skill.

    Requires Python 3.9+ and exported incident files. Confirms that quotes exist, not what they mean, and can't detect faked source files. Confidence stops at 0.95. Thresholds are judgement calls, not calibrated to your environment.

    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 15 days ago

    Requires

    Python 3.9+

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Terminal runs scripts/verify_rca.py. Read covers the incident folder you name. Write covers the report file. The script makes no network calls and reads only inside the folder you pass to --root.

    Listed15 days ago

    What's inside

    Frequently Asked Questions

    It catches quotes that aren't in the files you point it to: they're dropped, listed, and lower the confidence. It can't catch a faked source file, or a real line that the agent has misread.

    SKILL.md with the investigation routine, verify_rca.py (Python standard library, no network calls), two reference guides, and a sample incident with one passing and one failing report.

    Python 3.9+ and your incident data saved as files in one folder: logs, metric exports, deploy history, config diffs.

    It's the lower of the agent's stated number and a cap. The cap starts at 0.95 and falls for invalid citations, unexplained contradictions, few independent evidence kinds, no verification, and no credible alternative. The exact rules are in references/report-format.md.

    No. The script runs locally and makes no network calls. Your agent's own provider may still see what the agent reads, so mask secrets and personal data as you normally would.

    No. Export what you need to files first, since only files can be checked. If your agent has access to those tools, it can save the output to the incident folder.

    New in Testing & Debugging