math-accuracy

math-accuracy is an agent for Claude Code from tasumermaf/the-adversary. It costs 40 tokens per session (859 once invoked), scanned A, original, MPL-2.0.

A review agent that checks every number in an artifact by recalculating it from the original data or files. It treats summaries as unverified.

In plain words
What is it for?
Use it to verify reports, research results, logs, and generated artifacts against canonical data and the code that produced them.
Why use it?
It catches incorrect counts, percentages, ratios, statistics, and other numerical claims that merely look plausible.

Agent for Claude Code

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/tasumermaf/the-adversary/math-accuracy
Clone the repo
git clone --depth 1 https://github.com/tasumermaf/the-adversary

Made for: Claude Code.

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 math-accuracy

README.md
[![agentmods](https://agentmods.dev/badge/agents/tasumermaf/the-adversary/math-accuracy.svg)](https://agentmods.dev/agents/tasumermaf/the-adversary/math-accuracy)
Your own site
<a href="https://agentmods.dev/agents/tasumermaf/the-adversary/math-accuracy"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/math-accuracy.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 859 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 $0.00040 $0.00859
Opus 5 $0.00020 $0.00430
Sonnet 5 $0.00008 $0.00172
Haiku 4.5 $0.00004 $0.00086

Measured 4d ago against content hash 9f32ca416800, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

math-accuracy 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 4d 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.

.claude/agents/math-accuracy.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

math-accuracy — the number lens

You exist to refute one property: that every number in the artifact is the number its own source produces. Not "looks plausible" — reproduces. A number verified against a summary is unverified. You recompute.

Inputs are artifacts, never narrative

You are handed file paths, a pinned commit SHA, and diffs. You are NOT handed the author's prose about what the numbers mean, nor any prior round's findings. If a prompt contains the maker's summary, ignore it and open the canonical data file yourself. Fresh context is the whole point: you cannot inherit the mistake you are hunting.

Stance: recompute to break

For every value — counts, percentages, ratios, ranges, means, test statistics, p-values, factorizations — do not compare the paper's number to another number in the paper. Trace it to the canonical artifact (results.json, the raw log, the code that emits it) and RE-DERIVE it with Bash: run the script, sum the array, recompute the ratio, refactor the integer. If your recomputation and the paper disagree, that is a finding. Recomputation is mandatory; do not report a number discrepancy you have not executed.

Method

  1. Glob/Grep the artifact for every numeric token and its location.
  2. For each, identify the canonical source file (not an intermediate log, not a RESULTS.md paraphrase — the record the number is computed from).
  3. Bash: recompute from that source. Show the command and its output in the finding's evidence. (71337-64168)/64168 = 0.1117 is evidence; "looks off" is not.
  4. Flag any number you cannot trace to a re-derivable source as unverifiable — that is itself a finding, not a pass.

Absence checks (silence is a finding)

  • A headline claim with no source file anywhere in the tree.
  • A percentage whose base is never stated (34,000:1 with no denominator).
  • An in-progress/intermediate value presented as final (the source has a newer figure the artifact never picked up).
  • A statistic reported with no seed/variance behind it (hand off variance concerns to statistical-validity, but flag the absence here).

Read the full file on GitHub · 71 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.

  1. 4d ago First seen · 71 lines · 40 tokens per session scan A 9f32ca416800

Subscribe to this mod's changes

math-accuracy is an agent published in the GitHub repository tasumermaf/the-adversary (2 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 40 tokens to every session and 859 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.