Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Simulate Before Execute

    1

    Makes your agent test a risky change away from live systems, compare it with doing nothing, and act only when a gate script or a person approves it.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Simulate Before Execute

    Simulate Before Execute

    Example session with this skill installed

    Checkout errors spike every evening. I'm thinking of either scaling the workers to 8 or cutting the timeout to 400 ms. Test both, and only change production if the evidence supports it.

    • Read your context and instructions
    • Compiled the simulate before execute

    The figures below are sample data from examples/scale-workers.json, which ships with the skill. The gate values are real output from running gate.py on that file, so you can reproduce them.

    Summary

    I tested both plans on replayed evening traffic, 3 runs each, alongside doing nothing. Scaling to 8 workers passes the gate. The timeout change doesn't.

    Terms set before testing: metric error_rate (lower is better), minimum gain 0.02, allowed actions SCALE_WORKERS (2 to 12) and SET_TIMEOUT_MS (200 to 5000).

    Results

    PlanRunsMean error rateGainSpreadRisk
    Do nothing30.0810n/an/an/a
    scale-to-830.04130.03970.0012LOW
    short-timeout30.06670.01430.0591HIGH

    Gate verdict

    {
      "decision_hash": "0e5ce5a75c4561a2",
      "recommended": "scale-to-8",
      "execution": [
        {
          "key": "0e5ce5a75c4561a2:scale-to-8:0:SCALE_WORKERS",
          "type": "SCALE_WORKERS",
          "params": {"count": 8}
        }
      ],
      "status": "auto_approved",
      "reason": "risk LOW and gain 0.03967"
    }
    

    Why the timeout plan lost

    Its error rate ranged from 0.02 to 0.15 across the 3 runs. One good run would have made it look like the winner, but the spread of 0.0591 is above the 0.05 limit, so the gate marked it HIGH risk. Its gain was also below the 0.02 minimum.

    What the test couldn't show

    • Replayed traffic may not match a real peak.
    • scale-to-8 carries one low finding: it adds 3 workers, which costs more.

    Next steps

    1. I'll rerun the gate on the current decision file and confirm the hash hasn't changed.
    2. I'll claim the key with gate.py claim, which exits with code 3 if it was already used.
    3. I'll scale to 8 workers, change nothing else, and report the real error rate against the expected 0.0413.

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

    About this skill

    An agent that can change production can also break it. This skill gives your agent a fixed routine for risky changes: test first, compare with doing nothing, and let a small script decide whether the change can go ahead without a person.

    The agent proposes. Evidence decides.

    What it does

    • Sets the terms first. The goal, the metric, the minimum gain, and a closed list of allowed actions are written down before any plan exists, so a threshold can't be chosen to suit a favourite plan.
    • Always compares with doing nothing. Every plan is measured against the same baseline, under the same conditions, across at least 3 runs.
    • Judges the evidence with a script. gate.py drops actions outside the list, clamps parameters to their limits, flags regressions and unstable results, scores the risk, and returns one of three outcomes: auto_approved, needs_human, or do_nothing.
    • Keeps a person in charge of the dangerous parts. Actions marked requires_human never pass automatically, and the agent is told it can't approve its own plan.
    • Stops double execution. Each action gets a key that can only be claimed once, using an atomic file create.

    What's in the package

    • SKILL.md: the 8-step routine your agent follows
    • scripts/gate.py: the gate, in Python standard library only, with no network calls
    • references/decision-file.md: the decision file format and the exact rules
    • references/test-methods.md: ways to test by domain (Terraform, Kubernetes, databases, feature flags, scheduling, pricing, bulk data edits) and what each one can miss
    • examples/: two decision files you can run right away

    Good fit

    • Scaling, config, routing, or schedule changes made by an agent
    • Database migrations that can be tried on a restored snapshot
    • Deciding which agent actions are safe to run without a person

    Known limitations

    • It doesn't run tests for you. You need a dry run, staging copy, replay, or simulator. Without one, the plan goes to a person.
    • It can't detect made-up results. The skill tells the agent never to invent numbers, but the gate only judges what it is given.
    • Passing isn't proof of safety. It means the plan beat doing nothing in your test. Whether that test resembles production is still your call.
    • The rules are instructions to your agent. The gate reports a verdict and the ledger records claims, but neither one blocks an agent that has direct access to production. Limit that access separately.

    Where it comes from

    The approach comes from the safety design of NEXUS, my open-source warehouse digital twin. The risk weights and approval logic are adapted from it and generalised so they work with any metric. The benchmark results published for NEXUS measure that system, not this skill.

    Requires Python 3.9+. You provide the test method. The gate judges the results it is given and can't detect made-up numbers. It doesn't block an agent that has direct access to production, so limit that access separately.

    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/gate.py. Read and write cover the decision file and the .gate-ledger folder. gate.py makes no network calls. The tools you use to test or apply a change have their own access, separate from this skill.

    Listed15 days ago

    What's inside

    Frequently Asked Questions

    It gives your agent a routine: test the change away from live systems, compare it with doing nothing, and run a gate script before acting. Risky or unproven plans go to a person. It works by instructing your agent, so also limit what the agent can access in production.

    SKILL.md with the 8-step routine, gate.py (Python standard library, no network calls), two reference guides, and two example decision files you can run.

    No. You bring the test method, such as a dry run, staging copy, replay, or simulator. The reference guide lists options by domain. If you have no way to test, the gate sends the plan to a person.

    A prompt leaves the judgement to the agent. Here the thresholds are set before testing, a script scores the results by fixed rules, and every plan is compared with doing nothing across several runs. The agent still has to follow the routine and report honest results.

    Any agent that supports the SKILL.md standard and can run a Python 3.9+ script from the terminal.

    Each action gets a unique key. Before acting, the agent claims the key, which creates a file atomically, so only the first claim succeeds. A repeat exits with code 3. If an action fails after its claim, the agent is told to stop and ask you rather than retry.

    New in Agents & Orchestration