Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Traceable Numbers: Verified Figures in Data Answers

    1

    Makes your agent compute every figure in code, record its source, check up/down direction and reconcile totals before answering, so it never reports +18% growth when revenue actually fell 6%.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Traceable Numbers: Verified Figures in Data Answers

    Traceable Numbers: Verified Figures in Data Answers

    Example session with this skill installed

    Using sales.db, how did net revenue change in October compared with September?

    • Read your context and instructions
    • Compiled the traceable numbers

    Summary

    Net revenue fell 7.7% in October: 1,380,395.00 TRY vs 1,495,585.00 TRY in September.

    Definition

    Net revenue = sales - refunds - discounts, by business date (Europe/Istanbul), tax and tips excluded. Both months complete.

    Checks

    • Join fan-out: order count unchanged after joining payments (split bills grouped first).
    • Reconciliation: POS net vs processor payouts within 0.3%.
    • check_numbers.py: PASS, every number traced.

    How these numbers were computed

    • oct_net_revenue = 1380395.00 (pos.db: orders, refunds)
    • sep_net_revenue = 1495585.00 (pos.db: orders, refunds)
    • mom_pct = -7.7 ((oct / sep - 1) * 100)

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

    About this skill

    The problem

    AI agents are confident with numbers they never computed. They mix gross and net, double-count rows after a join, or write "up" next to a negative change. One wrong figure in a report ends trust.

    What this skill does

    • Defines the metric first: what is counted, the period, timezone and grain.
    • Computes in code only: every figure comes from SQL or Python and is recorded as evidence with its source and query.
    • Sanity checks: join fan-out, duplicates, nulls, partial periods, percent vs ratio, averages of averages.
    • Reconciles: compares against an independent total (e.g. POS sales vs processor payouts).
    • Verifies the draft: a bundled script lists every number as traced, untraced or wrong direction, and fails until all are fixed.
    • Shows its work: a short "How these numbers were computed" section the reader can check.

    Example

    Draft: "Revenue was up 18% last month and up 7.7% vs September." Check result: UNTRACED 18, WRONG DIRECTION 7.7 <- mom_pct (-7.7). The agent fixes the draft before anyone sees it.

    Good for

    Sales and finance reports, POS and accounting exports, KPI summaries, dashboards, any answer where a number will be acted on.

    Requirements

    Python 3.8+, standard library only. No network access, no dependencies.

    Requires Python 3.8+. Small counting numbers (0-10, 12, 100) and years are skipped by default; use --include-small to check them. Numbers are matched by value, so a coincidental match with an unrelated recorded value counts as traced. Sanity checks and reconciliation are steps the agent performs with its own SQL or Python; the script does not connect to data sources.

    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 12 days ago

    Requires

    python3

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Terminal: runs the bundled scripts/check_numbers.py with Python. Read files: reads the draft answer and the evidence file. Write files: appends computed values to .evidence/evidence.jsonl in the working directory. No network access.

    Listed12 days ago

    What's inside

    Frequently Asked Questions

    It provides a programmatic verification layer that forces the agent to use Python or SQL for all calculations, logging every result to an audit trail to ensure narrative descriptions (like 'increase') match the actual math.

    A SKILL.md workflow and one standard-library Python script (scripts/check_numbers.py) with three commands: record (save a computed value with its source), check (verify a draft) and list (show recorded evidence).

    Yes, as a workflow step: the skill tells the agent to compare its result with an independent total (for example processor payouts or a bank export) and to report any gap in the answer. The comparison itself is done with the agent's own SQL or Python; the bundled script only checks that the reported numbers match recorded evidence.

    By default it skips years (1900-2100) and small counting numbers (0-10, 12 and 100), so it focuses on metrics, money and percentages. Run check with --include-small to verify those too.

    Once you add the skill to your agent's environment, you simply define your metric rules and run the provided validation script against the agent's draft to catch any untraced or incorrect figures.

    New in Research & Analysis