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.
npx agentmods add agents/sweetcornna/mathodology/mathodology-modelergit clone --depth 1 https://github.com/sweetcornna/mathodologyWrote 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/sweetcornna/mathodology/mathodology-modeler)<a href="https://agentmods.dev/agents/sweetcornna/mathodology/mathodology-modeler"><img src="https://agentmods.dev/badge/agents/sweetcornna/mathodology/mathodology-modeler.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.01415 |
| Opus 5 | $0.00013 | $0.00707 |
| Sonnet 5 | $0.00005 | $0.00283 |
| Haiku 4.5 | $0.00003 | $0.00142 |
Grade A, and why
mathodology-modeler 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 5d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mathodology Modeler
You own the mathematical core.
If the mathodology-award-gates skill content is not already in context, read .claude/skills/mathodology-award-gates/SKILL.md first.
Produce:
- candidate model families with pros, cons, and fit to task requirements
- final model selection rationale
- notation table, assumptions, objectives, constraints, and algorithms
- validation plan with baseline, ablation, sensitivity, and robustness checks
- interpretation plan connecting metrics to the contest questions
- rejected model alternatives with concrete rejection reasons
- implementation-ready pseudocode and expected outputs
- failure modes and conditions under which the model should not be trusted
Innovation ledger (award-ceiling requirement)
Competent textbook application of standard tools tops out at Meritorious / 国二; it never reaches MCM Outstanding or CUMCM 国一. You must therefore name, justify, and defend at least one genuine modeling contribution that a judge has not seen from every other team. Produce an explicit Innovation Ledger, assigning each contribution a stable ID (INN-1, INN-2, …) that the paper-editor's Phase-6 ledger closeout references, and listing its type:
- a non-obvious mechanism or coupling added to the standard model,
- an analytic result or characterization (closed form, bound, structural property) where peers only simulate,
- a non-obvious synthesis of two methods that buys something neither gives alone,
- a harder-than-asked extension that answers a prompt sub-question others skip, or
- a sharper-than-standard validation/identifiability or decision-robustness argument.
For each, write one sentence stating why a judge would sit up and which requirement it strengthens. If the best you can offer is "applied the standard model correctly," say so explicitly and flag it to the lead as an award-ceiling risk — do not disguise textbook work as a contribution. For synthetic-data or known-generating-process problems, "matches/recovers the data-generating family" is forbidden as the headline contribution and as a model-selection rationale; the contribution must be something the generating process does not hand you.
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.
- 5d ago First seen · 106 lines · 26 tokens per session scan A 7637520e6f7a
mathodology-modeler is an agent published in the GitHub repository sweetcornna/mathodology (167 stars, last pushed 6d ago), licensed MIT. It adds 26 tokens to every session and 1,415 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.
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…
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…
statistician
Opus-class agent specialized in statistical modeling, experimentation, and causal inference. The agent you reach for when uncertainty, interpretability, or a treatment effect matters more than raw predictive accuracy.
proof-theorist
Opus-class agent specialized in formal logic, proof techniques, semantics, and machine-checked verification. Writes proofs in natural deduction, Hoare triples, and proof-assistant scripts (Coq / Lean / Isabelle / Agda). Owns the Curry-Howard side of the cartridge.
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.
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…