More screenshots

    Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+20 more

    mission preflight gate

    0

    A fail-fast preflight gate that verifies prerequisites, safety, and completion witnesses before agents start execution.

    $5

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    0 installsSecurity scanned
    mission preflight gate

    mission preflight gate

    Example session with this skill installed

    Run preflight for a mission to scrape 50 product pages from an e-commerce site, extract pricing to a CSV, and upload it to a specific S3 bucket. I have the URL list and AWS CLI configured.

    • Read your context and instructions
    • Compiled the mission preflight gate
    • Generated the data export

    PREFLIGHT VERDICT: GO_WITH_LIMITS

    MISSION

    • Goal: Extract pricing data from 50 unique URLs and store as a structured CSV.
    • Deliverable: pricing_export_2023_10_27.csv
    • Output target: s3://market-data-bucket/pricing/
    • Completion witness: S3 HEAD request confirms object existence and non-zero byte size after upload.

    READINESS

    • Tools: HTTP Scraper (AVAILABLE), CSV Parser (AVAILABLE), AWS CLI (PRESENT_UNVERIFIED).
    • Auth/permissions: AWS credentials present; S3 PutObject permission assumed but not tested.
    • Inputs: URL list (50 entries) - EXISTS and REACHABLE.
    • Budget/quota: Token budget for LLM extraction is SUFFICIENT for 50 small pages.

    SIDE EFFECTS

    • Class: IRREVERSIBLE_OR_EXTERNAL_COMMITMENT (S3 Upload)
    • Retry/idempotency: Overwrite existing file on S3 if filename matches; max 3 retries on upload failure.
    • Rollback: Manual deletion of S3 object if data is corrupted.
    • Approval boundary: None (below $5 estimated cost).

    STOP CONDITIONS

    • Terminate if more than 5 URLs return 403 Forbidden.
    • Terminate if S3 upload fails after 3 attempts.

    BLOCKERS / LIMITS

    • LIMIT: AWS S3 write permission is unverified. If PutObject fails, the mission will BLOCK.
    • LIMIT: Site-wide rate limiting on the target domain is unknown; backoff is set to 2s.

    NEXT SMALLEST SAFE ACTION

    • Perform a HEAD request on the first 3 URLs to verify access and check the S3 bucket's write-readiness with a small metadata-only test file.

    Next steps

    1. Run the connection test for the first 3 URLs.
    2. Verify S3 write permissions with a zero-byte test file.
    3. Proceed with full batch scraping if tests pass.

    mission-preflight-gate.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.

    What you get

    Define falsifiable completion witnesses to ensure tasks actually finished.Audit side-effect safety to prevent accidental data loss or double-spend.Verify tool and API availability before consuming expensive tokens.Enforce idempotency and rollback strategies for all write operations.

    About this skill

    The problem

    Autonomous agents often waste significant time and tokens on missions destined to fail due to missing API keys, stale inputs, or ambiguous success criteria. Starting a multi-step workflow without verifying resource availability or side-effect safety leads to expensive retries and inconsistent state.

    What it does

    • Enforces a strict pre-execution contract including verifiable goals, deliverables, and completion witnesses.
    • Validates tool availability, authentication status, and input schema freshness without performing destructive actions.
    • Categorizes side-effect risks and defines idempotency, retry, and rollback strategies before the first write occurs.
    • Identifies budget and deadline bottlenecks to prevent agents from starting tasks they cannot finish.
    • Provides a standardized preflight verdict to gate execution behind safety checks or human approval.

    Why this beats prompting it yourself

    Standard prompts often suffer from optimism bias, where agents assume tools work or files exist. This skill implements a systematic "fail-fast" logic that treats unknown states as blockers, preventing common pitfalls like accidental double-billing or silent failures after a successful exit code.

    Use cases

    • Gating high-token autonomous research agents before they start scraping.
    • Verifying deployment environments and permissions before executing CI/CD tasks.
    • Preventing duplicate API calls in payment or messaging workflows through idempotency checks.
    • Ensuring multi-file refactoring tasks have a verified rollback path before editing source code.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 19 days ago

    • Passed all security checks, Safe to install

    Listed19 days ago

    What's inside

    Frequently Asked Questions