Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Agent Tool Budget Gate

    1

    Check recorded tool calls against explicit count, duration and error limits. Get deterministic PASS/FAIL reports without replaying a run.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Agent Tool Budget Gate

    Agent Tool Budget Gate

    Example session with this skill installed

    Run the bundled synthetic pass and fail completed-event JSONL examples against examples/policy.json using the packaged Python runner in a supported execution environment. Use separate new output directories. Return the measured checks, exit statuses, report paths and input hashes. Do not replay calls, change the policy or claim this tests a real customer run.

    • Read your context and instructions
    • Compiled the agent tool budget

    Agent Tool Budget Gate — Synthetic Local Demo

    Two fictional completed-event fixtures were measured locally against the same policy. This is local Python execution evidence, not a customer deployment or a paid-purchaser MCP test.

    CheckMaximumPASS fixtureFAIL fixture
    calls33 (PASS)4 (FAIL)
    total_duration_ms1000600 (PASS)1300 (FAIL)
    errors00 (PASS)1 (FAIL)
    tool:read_file22 (PASS)2 (PASS)
    tool:search11 (PASS)2 (FAIL)

    PASS fixture: 3 calls, 600 summed milliseconds, 0 errors. CLI exit 0.
    FAIL fixture: 4 calls, 1300 summed milliseconds, 1 error and 2 search calls. Four selected limits are exceeded; CLI exit 1 is expected.

    Each run writes report.md and report.json into its own new output directory. Input files and policy were not changed.

    Exact input identities

    • PASS trace SHA-256: 80416f4aedb27fcaba2d57e431805e5f309c2c92e632c7aa7b0f72eabddbbd73
    • FAIL trace SHA-256: 885c9c2adaf484cbfc27c0d54ca3ac745094f7212b79e842dd2929d3c445f6b9
    • Shared policy SHA-256: 1c7918bee760b9f14fdab60307b32783d6943f5df1eae9402f4e5521b578ddd1

    Review next

    Inspect the failing checks and the scope of the original recorded trace. Keep the negative evidence. Decide whether excess calls, errors or summed tool time require a workflow change; do not loosen budgets merely to produce PASS.

    Verdict covers only the supplied normalized completed events and explicit policy. It does not prove trace completeness, task success, safety, wall-clock latency, token consumption, or monetary cost. Durations are summed, including concurrent calls.

    The runner was checked by 32 tests on each of the two stated runtimes. Missing/invalid input returns exit 2 and must not be interpreted as a budget result.

    Each run writes report.md and report.json

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

    About this skill

    Measurable budgets for a recorded agent run

    Agent Tool Budget Gate checks local, normalized completed tool-call events against explicit limits you choose. Get a reproducible PASS/FAIL verdict for total calls, summed tool duration, errors and optional per-tool call counts.

    What you receive

    • A deterministic Python runner using only the standard library.
    • Markdown and JSON reports with each measured check and SHA-256 identities for the input and policy.
    • Strict validation: missing durations, duplicate event IDs, malformed JSON, unsupported fields and oversized inputs stop with an input error.
    • Passing and failing synthetic examples, their measured reports, an input contract and 32 self-tests.

    Workflow

    1. Supply a local JSONL with one completed tool call per line: event_id, tool, duration_ms and status (ok/error).
    2. Supply a JSON policy with your call, summed-duration and error limits; optional per-tool limits are supported.
    3. Use a coding-agent environment that provides authorized execution of the packaged Python runner with local terminal and file access.
    4. Read the verdict and evidence, then decide whether the recorded run needs review.

    Requirements and important limits

    Python 3.12+ standard library. Tested locally on Windows/Python 3.12.14 and Ubuntu/Python 3.14.4. Agensi access is through its agent connection; a downloadable ZIP is not offered to buyers. The host must support authorized packaged-runner execution. Actual paid-purchaser MCP invocation has not been validated. If that execution capability is unavailable, the skill stops and explains the unsupported environment.

    Inputs must already follow the normalized schema; native Codex/Claude/provider-log adapters are not included. Partial or cancelled calls and missing durations must be resolved during normalization. No automatic normalization or completeness guarantee is provided.

    PASS covers only supplied completed events and the chosen numeric limits. Summed duration includes concurrent calls and is not wall-clock latency. The skill does not measure API charges, tokens, task success or safety, monitor live sessions, replay tools, or enforce a tool allowlist. Unlisted tools still count toward global limits.

    The runner reads the selected trace and policy and writes a new local report directory. It does not send data, contact external services, execute recorded tool calls or modify source inputs. Reports retain tool identifiers and input hashes; avoid confidential content in tool names.

    Normalized completed-event schema only; no native provider-log adapter, live monitoring, tool replay or automatic stopping. Counts rely on supplied records. Summed duration is not wall-clock time; no token/cost/success/safety/completeness guarantee. Host support for authorized packaged Python execution is required; actual paid-purchaser MCP invocation is unvalidated. UTF-8, trace <=2 MiB/20,000 events, line <=64 KiB, policy <=64 KiB, JSON depth <=16. Inputs unchanged; new output directory required.

    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 24 days ago

    Requires

    Python 3.12+ (standard library only)
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Terminal: execute the offline Python runner. Read: only the user-selected normalized JSONL trace and JSON policy. Write: only a user-selected new local report directory. No network, browser or environment-variable access is required by the runner. Never replay recorded calls or export purchased skill files.

    Listed24 days ago

    What's inside

    Frequently Asked Questions

    Every selected numeric limit is satisfied by the supplied completed events. PASS does not establish trace completeness, task success, safety, token usage, monetary cost or wall-clock latency.

    No. Supply UTF-8 JSONL normalized to one completed tool call per line with event_id, tool, duration_ms and status (ok/error). Provider adapters and automatic normalization are not included.

    Python 3.12+ with standard library, local terminal/file access and host support for authorized execution of packaged Python resources. Tested locally on Windows/Python 3.12.14 and Ubuntu/Python 3.14.4. Actual paid-purchaser MCP invocation is unvalidated. If runner execution is unavailable, the skill reports an unsupported environment and stops.

    No. The runner reads only the two selected local inputs and writes local reports. It does not execute recorded calls, contact a service, monitor a live session or stop tools in real time.

    Completed retry attempts require separate unique event IDs. Missing durations, unsupported fields and partial/pending states are rejected. Tools absent from per_tool still count toward global budgets; per_tool is not an allowlist.

    A valid run writes report.md and report.json with measured checks and trace/policy hashes. Use a new output directory; existing directories are rejected. Exit 2 invalidates any partial output and requires review before retrying in a fresh directory.

    New in Testing & Debugging