mathodology-critic

mathodology-critic is an agent for Claude Code from sweetcornna/mathodology. It costs 19 tokens per session (237 once invoked), scanned A, original, MIT.

An adversarial reviewer for a mathematical or research submission. It checks the prompt, assumptions, model, evidence, originality, code, paper, and risk of misleading claims.

In plain words
What is it for?
Use it to review award submissions before delivery, challenge model choices, check quantitative claims and baselines, and identify reproducibility or correctness problems.
Why use it?
It finds weaknesses that a project team may overlook, including unsupported comparisons, invalid reasoning, hidden omissions, or differences between the paper and the code.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to review award submissions before delivery, challenge model choices, check quantitative claims and baselines, and identify reproducibility or correctness problems.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sweetcornna/mathodology/mathodology-critic
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/sweetcornna/mathodology

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 mathodology-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/sweetcornna/mathodology/mathodology-critic.svg)](https://agentmods.dev/agents/sweetcornna/mathodology/mathodology-critic)
Your own site
<a href="https://agentmods.dev/agents/sweetcornna/mathodology/mathodology-critic"><img src="https://agentmods.dev/badge/agents/sweetcornna/mathodology/mathodology-critic.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 237 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00237
Opus 5 $0.00010 $0.00118
Sonnet 5 $0.00004 $0.00047
Haiku 4.5 $0.00002 $0.00024

Measured today against content hash 76d98cbfdea9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mathodology-critic 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 today.

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/mathodology-critic.md · 26 lines

What it actually says

Mathodology Critic

Load the skills named above when their content is not already in context.

Read the relevant artifacts and challenge their strongest claims. Apply the review questions relevant to the model: validity, feasibility, data leakage, identifiability, baseline fairness, sensitivity, and code-to-paper consistency. Check citations or rerun calculations when needed, rather than trusting a self-assigned score or a completed process log.

Inspect figure scales, statistical meanings, uncertainty, captions and actual paper readability. Check that image2 illustrations do not add unsupported mechanisms or masquerade as numerical evidence. Reuse the existing image2 answer; reviewing existing figures alone does not require another availability question.

Report material findings with evidence, impact and a concrete fix. Separate errors from optional improvements. Do not infer a prize tier from invented thresholds or require every intermediate artifact to pass a formal gate.

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. today Changed · -55 lines · -9 tokens per session 76d98cbfdea9
  2. 8d ago First seen · 81 lines · 28 tokens per session scan A 370447997db6

Subscribe to this mod's changes

mathodology-critic is an agent published in the GitHub repository sweetcornna/mathodology (181 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 237 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

deep-paper-researcher

Token-isolated deep research agent for academic papers. Orchestrates Exa MCP (neural multi-source discovery), allenai's semantic-scholar-lookup skill (fast metadata + forward citations via asta CLI), and the semantic-scholar-deep skill (references, recommendations, batch, citation-graph BFS). Use when the user asks…

CodeAlive-AI/ai-driven-development · 210 tokens

statistical-consultant

Expert consultant for advanced statistical methods, causal inference, experimental design, and statistical validation. Use proactively for complex statistical analysis planning, methodology selection, experimental design, causal inference assessment, and rigorous statistical validation strategies. Provides analysis…

spacehendrix/clauder · 113 tokens

data-scientist

A data scientist who builds statistical models, designs experiments, and extracts actionable insights from data — separating signal from noise with rigorous methodology. Use for statistical analysis, predictive modeling, hypothesis testing, and data storytelling.

The-AI-Directory-Company/agents-and-skills · 46 tokens

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

docs-specialist

Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.

ZaxbyHub/opencode-swarm · 34 tokens

security-reviewer

A code-security review assistant that checks for common vulnerabilities, leaked secrets, unsafe input handling, and authentication or authorization problems.

xiaobei930/cc-best · 85 tokens