A forensic test of the first digits in general-ledger transactions, using Benford’s Law, a statistical pattern found in many natural datasets. Large departures can point to fabricated or selectively entered numbers.

Use it to screen a deal’s ledger for suspicious numeric patterns and highlight account categories for follow-up.

It helps identify transaction data that may need investigation instead of treating unusual figures as ordinary accounting noise.

benford — Command for Claude Code by ololand-ai/ololand-plugins

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/ololand-ai/ololand-plugins

Made for: Claude Code.

Or install ololand-forensic-qoe, the plugin that ships this one along with the rest of its 10 skills, 8 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/ololand-ai/ololand-plugins/benford/github.svg)](https://agentmods.dev/commands/ololand-ai/ololand-plugins/benford)

Your own site

<a href="https://agentmods.dev/commands/ololand-ai/ololand-plugins/benford"><img src="https://agentmods.dev/badge/commands/ololand-ai/ololand-plugins/benford/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/ololand-ai/ololand-plugins/benford"><img src="https://agentmods.dev/badge/commands/ololand-ai/ololand-plugins/benford.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 720 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.00720
Opus 5.5	$0.00009	$0.00288
Sonnet 5.5	$0.00005	$0.00144
Haiku 4.5	$0.00002	$0.00072

Measured 17d ago against content hash 2aea1f4b23de, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

benford scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/ololand-forensic-qoe/commands/benford.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Benford's Law

Benford's Law describes a logarithmic first-digit distribution in suitable naturally-occurring datasets. Deviations are investigation prompts, not proof of fabricated transactions or fraud; conformity does not establish that transactions are legitimate.

Usage

/benford <deal_id>
/benford <supplied transaction list or GL file>

Arguments

Supply either a deal_id for the deal-scoped forensic workflow or a transaction list/GL file for the standalone tool. run_benford accepts transactions, not a deal or dataset identifier; each transaction dictionary needs an amount field.
Preserve signed transaction amounts. Negative amounts are evaluated by absolute magnitude; zero and unusable values are ignored. Do not drop valid credits/reversals merely because their amounts are negative.
Use the returned usable sample_size, minimum_required, and status; a file's raw row count is not the tested population or a guarantee of statistical reliability.

Execution

If the user supplied a transaction list or GL file, parse it into transaction dictionaries using the current tool schema and call run_benford(transactions). The standalone tool analyzes only that supplied payload; it does not fetch the deal's data room. If the user supplied only deal_id, call analyze_forensic_qoe(deal_id) and extract the returned Benford section. Do not pass a primitives argument or invent a transaction-fetch endpoint.
Inspect the returned status and usable sample size before interpretation. insufficient_sample, unavailable, unreliable, or uncomputed results are explicit gaps, not conformity or passing tests. Do not report placeholder zero distributions from an insufficient-sample response as measured results.
For computed results, report the returned observed/expected first-digit distributions, chi_square, Mean Absolute Deviation (mad), conformity, and most_deviant_digit when present. Preserve the response's scope and limitations.
The current standalone run_benford response does not return p_value, account-level flags, or ranked contributing transactions. Do not invent or back-calculate these and attribute them to the service. Account-specific findings or transaction follow-ups require separate actual source evidence.

Read the full file on GitHub · 53 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

17d ago Changed · +4 lines · -1 tokens per session 2aea1f4b23de
1mo ago First seen · 49 lines · 24 tokens per session scan A 484ad88f86a4

Subscribe to this mod's changes

benford is a command published in the GitHub repository ololand-ai/ololand-plugins (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 23 tokens to every session and 720 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Analytics and metrics Finance and fintech

benford

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Benford's Law

Usage

Arguments

Execution

What this file has done since we first saw it

Other commands, from other repositories

analyze-bond-rv

valuation-methods

merit-reconcile

cost-per-task

audit-checklist

scan