Borrowing it
Nothing to install: this file belongs to tasumermaf/the-adversary. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tasumermaf/the-adversary/master/.claude/agents/math-accuracy.mdgit clone --depth 1 https://github.com/tasumermaf/the-adversaryWrote 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.
[](https://agentmods.dev/agents/tasumermaf/the-adversary/math-accuracy)<a href="https://agentmods.dev/agents/tasumermaf/the-adversary/math-accuracy"><img src="https://agentmods.dev/badge/agents/tasumermaf/the-adversary/math-accuracy/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00040 | $0.00859 |
| Opus 5.5 | $0.00016 | $0.00344 |
| Sonnet 5.5 | $0.00008 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
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 2mo 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.
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
Glob/Grepthe artifact for every numeric token and its location.- For each, identify the canonical source file (not an intermediate log, not a RESULTS.md paraphrase — the record the number is computed from).
Bash: recompute from that source. Show the command and its output in the finding's evidence.(71337-64168)/64168 = 0.1117is evidence; "looks off" is not.- 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).
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.
- 2mo ago First seen · 71 lines · 40 tokens per session scan A 9f32ca416800
math-accuracy is an agent published in the GitHub repository tasumermaf/the-adversary (2 stars, last pushed 2mo ago), licensed MPL-2.0. It adds 40 tokens to every session and 859 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
integrity-verification-agent
Academic integrity gatekeeper for alterlab-research-pipeline (Stage 2.5 pre-review + Stage 4.5 post-revision). Performs 100% verification of references, citations, data, originality, and claim faithfulness. Resolves every reference's EXISTENCE and metadata deterministically via…
citation-compliance-agent
Verifies all citations in the paper draft for format correctness, cross-references in-text citations against the reference list, checks DOIs and URLs, and auto-corrects detected errors for the selected citation style.
draft-writer-agent
Writes the complete paper draft section-by-section, following the Structure Architect's outline and the Argument Builder's blueprint, weaving citations naturally into the narrative and handling revision rounds.
meta-analysis-agent
Designs and executes meta-analyses when quantitative synthesis is feasible, computing effect sizes, assessing heterogeneity, generating forest-plot data, planning subgroup and sensitivity analyses, and applying the GRADE framework; otherwise produces a structured narrative synthesis framework.
revision-coach-agent
Parses unstructured reviewer comments from any format into a structured Revision Roadmap, classifying, mapping, and prioritizing every comment; it works standalone and does not require the paper to have gone through the writing pipeline.
structure-architect-agent
Selects the optimal paper structure, designs a detailed section-by-section outline, allocates word counts, and maps evidence to sections, producing the blueprint the draft writer follows.