stats-auditor

stats-auditor is an agent for coding agents from gioviat/research-toolkit. It costs 49 tokens per session (285 once invoked), scanned A, original, MIT.

An audit guide for checking whether numbers and statistical statements in an experiment-results draft are supported by recorded experiment files.

In plain words
What is it for?
Auditing results drafts before sharing them and issuing a pass-or-fail assessment for the draft as a whole.
Why use it?
It catches untraceable numbers, missing variation, mismatched statistical tests, and wording that claims more than the data supports.

Agent

Part of the research-toolkit plugin — 7 skills, 5 agents, 1 hook shipped together

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.

agentmods
npx agentmods add agents/gioviat/research-toolkit/stats-auditor
Clone the repo
git clone --depth 1 https://github.com/gioviat/research-toolkit

Or install research-toolkit, the plugin that ships this one along with the rest of its 7 skills, 5 agents, 1 hook.

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.

agentmods badge for stats-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/gioviat/research-toolkit/stats-auditor.svg)](https://agentmods.dev/agents/gioviat/research-toolkit/stats-auditor)
Your own site
<a href="https://agentmods.dev/agents/gioviat/research-toolkit/stats-auditor"><img src="https://agentmods.dev/badge/agents/gioviat/research-toolkit/stats-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 285 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.00285
Opus 5 $0.00024 $0.00143
Sonnet 5 $0.00010 $0.00057
Haiku 4.5 $0.00005 $0.00028

Measured 3d ago against content hash d13003866165, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stats-auditor 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 3d 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.

agents/stats-auditor.md · 17 lines

What it actually says

You audit a results draft against the raw experiment outputs. You do not re-run experiments; you check consistency between claims and recorded data.

For every numeric claim in the draft:

  1. Locate the source file in experiments/results/ that produced it. If none exists, flag it as untraceable — this blocks the draft regardless of how plausible the number looks.
  2. Check that variation across seeds/runs is reported alongside the number, not just a point estimate.
  3. Check that the stated statistical test (if any) is appropriate for the comparison being made and that the reported test statistic or p-value/CI matches what's in the raw output.
  4. Check that the wording matches the strength of evidence: no causal language for observational comparisons, no "significant" without a reported test.

Output a list: for each claim, [traceable: yes/no], [variation reported: yes/no], [test matches: yes/no/n-a], and a one-line note on any discrepancy. End with a clear pass/fail verdict for the draft as a whole.

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.

  1. 3d ago First seen · 17 lines · 49 tokens per session scan A d13003866165

Subscribe to this mod's changes

stats-auditor is an agent published in the GitHub repository gioviat/research-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 285 once invoked, about $0.0002 per session on Opus 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 2026-08-31.