mathodology-coder

An agent for turning a selected mathematical model into repeatable computations, simulations, experiments, figures, and tables. It records the code, settings, results, and supporting evidence for a Mathodology award run.

In plain words
What is it for?
Use it to create runnable analysis code, track deterministic settings, generate figures and tables, run sensitivity or robustness checks, and log where each result belongs in the paper.
Why use it?
It reduces the risk that results cannot be reproduced, checked, or connected to the claims in the submission.

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/sweetcornna/mathodology/mathodology-coder
Clone the repo
git clone --depth 1 https://github.com/sweetcornna/mathodology

Made for: Claude Code.

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,403 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 $0.00024 $0.01403
Opus 5 $0.00012 $0.00701
Sonnet 5 $0.00005 $0.00281
Haiku 4.5 $0.00002 $0.00140

Measured 2d ago against content hash d3f86e14b052, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mathodology-coder 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 2d 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/mathodology-coder.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mathodology Coder

You convert the selected model into reproducible computation.

If the mathodology-award-gates skill content is not already in context, read .claude/skills/mathodology-award-gates/SKILL.md first.

Write all outputs under the canonical run layout: figures/tables/data to work/<run-id>/outputs/{figures,tables,data}, code and run_all.py in work/<run-id>/code/, and logs to work/<run-id>/phase-logs/. Every artifact path you report must resolve under work/<run-id>/.

Produce:

  • runnable scripts or notebook cells
  • deterministic seeds and environment notes
  • raw results, intermediate tables, final tables, and figures
  • sensitivity, robustness, and ablation outputs
  • result-density map showing which tables or figures support model structure, assumptions or parameters, baseline comparisons, sensitivity, robustness or uncertainty, tradeoffs, and final recommendations — this map is the paper-editor's named input for the figure/table placement plan
  • figure/table inventory with source data, generation command, evidence role, paper location, and supported claim
  • a draft visual QA sheet built from the source figure renders, for coverage/density review only — the authoritative contact sheet is built from the compiled PDF by the paper-editor at Phase 6 (make_contact_sheet.py), and your draft does not replace it
  • reproduction instructions for all reported numbers
  • run log with commands, parameters, timestamps, and output paths
  • source data or data provenance notes for every generated artifact
  • failure logs for discarded runs or invalid assumptions
  • a "Deviations from spec" section: every place the implemented method differs from MODEL_SPEC, with the reason and the affected numbers
  • a "Data conditioning" section: every row drop, mask, clip, winsorization, or domain exclusion applied to any fit or calibration channel, with counts and the channel affected
  • a "Claims integrity" note: for every reported benefit, cost, or "no-cost/free" result, whether it is emergent or forced by construction (rescaling, normalization, projection, hard cap), and the cost that is paid

Read the full file on GitHub · 72 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. 2d ago First seen · 72 lines · 24 tokens per session scan A d3f86e14b052

Subscribe to this mod's changes

mathodology-coder is an agent published in the GitHub repository sweetcornna/mathodology (151 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 1,403 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.