Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sweetcornna/mathodologynpx agentmods add skills/sweetcornna/mathodology/mathodology-workbenchWrote 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/skills/sweetcornna/mathodology/mathodology-workbench)<a href="https://agentmods.dev/skills/sweetcornna/mathodology/mathodology-workbench"><img src="https://agentmods.dev/badge/skills/sweetcornna/mathodology/mathodology-workbench/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/skills/sweetcornna/mathodology/mathodology-workbench"><img src="https://agentmods.dev/badge/skills/sweetcornna/mathodology/mathodology-workbench.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 | $0.00042 | $0.01592 |
| Opus 5.5 | $0.00017 | $0.00637 |
| Sonnet 5.5 | $0.00008 | $0.00318 |
| Haiku 4.5 | $0.00004 | $0.00159 |
Grade A, and why
mathodology-workbench 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 yesterday.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mathodology Workbench
The other skills guide judgment; this one executes. scripts/mtd.py (Python 3.9+,
standard library only) links the five stages of a contest through files, so each
stage reads what the previous one actually produced:
| Stage | Produces | Executable support |
|---|---|---|
| Problem brief | problem/questions.json: per question, deliverables, metrics, inputs, assumptions, dependencies |
mtd.py brief lists the numbered questions; you fill in the rest |
| Experiments | code under code/, a recorded run per execution |
mtd.py run -- python code/q1.py logs command, seed, inputs, outputs, exit code; placeholder scripts and stub functions are flagged |
| Results | results/*.json in the contract below, written by code |
validation, provenance and staleness against the code that produced them |
| Figures | images drawn by scripts that read results | traces script → data → image; flags stale, missing, corrupt or low-resolution figures |
| Paper | LaTeX citing \res{q1.rmse}, or Markdown citing {{res:q1.rmse}} |
mtd.py sync writes paper/results.tex and booktabs tables in paper/tables/; checks numbers, refs, cites, figures and the compile log, and math and citations in Markdown |
Run it from the workspace (or pass --root); the path below is relative to a
project with the skill installed:
python3 .claude/skills/mathodology-workbench/scripts/mtd.py init --paper-template # or --paper-template cumcm
python3 .claude/skills/mathodology-workbench/scripts/mtd.py brief # after the statement is in problem/
python3 .claude/skills/mathodology-workbench/scripts/mtd.py run --seed 1 -- python code/q1.py
python3 .claude/skills/mathodology-workbench/scripts/mtd.py status # every stage; --json for tools
python3 .claude/skills/mathodology-workbench/scripts/mtd.py check --compile # exit 1 on errors
A workspace is a folder with .mathodology/, or with problem/ and paper/ as
Mathodology Studio creates them. Contracts and every check are described in
references/contracts.md.
--paper-template NAME starts from a contest skeleton instead of the generic
one: cumcm, mcm, stats, huawei, mathorcup or apmcm. It also sets
"contest" in .mathodology/config.json, so check adds the format rules that
were read in that contest's official text: no table of contents for CUMCM,
the 25-page limit for MCM/ICM, anonymity. The skeletons and checks record the
rules as of the date in references/contest-formats.md.
The current official rules always take precedence. For 华为杯, MathorCup and APMCM
the format rules were not verified, so the skeleton only organizes content.
Choose the template from the problem statement and the user's words: the
contest name, the year, the problem letter and the submission instructions
usually settle it. Say which contest you chose before running init. Ask the
user, with the agent's question tool when it has one, when the evidence is
unclear or points to a contest without a skeleton (华数杯 and others take
generic), and before relying on a skeleton whose rules are unverified. When
"contest" is already set, for example by Mathodology Studio's new-project
dialog, keep it unless the user says otherwise. init never replaces an
existing paper/main.tex.
What ships with it
28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 410 B
- hooks/hooks.json 954 B
- references/contest-formats.md 5.5 KB
- references/contracts.md 8.1 KB
- scripts/mtd.py 11 KB runs code
- scripts/test_mtd.py 92 KB runs code
- scripts/workbench/__init__.py 0 B runs code
- scripts/workbench/assets.py 6.4 KB runs code
- scripts/workbench/brief.py 7.1 KB runs code
- scripts/workbench/contest.py 4.3 KB runs code
- scripts/workbench/engine.py 7.5 KB runs code
- scripts/workbench/figures.py 4.9 KB runs code
- scripts/workbench/hooks.py 9.1 KB runs code
- scripts/workbench/latex.py 16 KB runs code
- scripts/workbench/markdown.py 8.0 KB runs code
- scripts/workbench/numbers.py 10 KB runs code
- scripts/workbench/report.py 2.8 KB runs code
- scripts/workbench/results.py 16 KB runs code
- scripts/workbench/runs.py 7.2 KB runs code
- scripts/workbench/stubs.py 2.9 KB runs code
- scripts/workbench/workspace.py 5.9 KB runs code
- templates/paper/contests/apmcm/main.tex 1.7 KB
- templates/paper/contests/cumcm/main.tex 2.0 KB
- templates/paper/contests/huawei/main.tex 2.0 KB
- templates/paper/contests/mathorcup/main.tex 1.6 KB
- templates/paper/contests/mcm/main.tex 2.5 KB
- templates/paper/contests/stats/main.tex 3.4 KB
- templates/paper/main.tex 1.1 KB
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.
- yesterday Changed · +19 lines 1b88d4ebffb8
- 9d ago First seen · 87 lines · 42 tokens per session scan A d0889031ec1c
mathodology-workbench is a skill published in the GitHub repository sweetcornna/mathodology (320 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 1,592 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 2026-10-29.
mathodology-workbench compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mathodology-workbenchsweetcornna/mathodology | Skill | 320 | yesterday | MIT | A | 42 | Claude Code, Codex |
| semantic-scholar-deepCodeAlive-AI/ai-driven-development | Skill | 167 | yesterday | MIT | A | 163 | Claude Code |
| fortranMindrally/skills | Skill | 297 | 29d ago | Apache-2.0 | A | 95 | Claude Code |
| juliaMindrally/skills | Skill | 297 | 29d ago | Apache-2.0 | A | 22 | Claude Code |
| deep-learning-pytorchMindrally/skills | Skill | 297 | 29d ago | Apache-2.0 | A | 33 | Claude Code |
| nlp-natural-language-processingMindrally/skills | Skill | 297 | 29d ago | Apache-2.0 | A | 28 | Claude Code |
| numpy-best-practicesMindrally/skills | Skill | 297 | 29d ago | Apache-2.0 | A | 22 | Claude Code |