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.
git 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-lead)<a href="https://agentmods.dev/agents/sweetcornna/mathodology/mathodology-lead"><img src="https://agentmods.dev/badge/agents/sweetcornna/mathodology/mathodology-lead.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 5.1 | $0.00022 | $0.01583 |
| Opus 5 | $0.00011 | $0.00792 |
| Sonnet 5 | $0.00004 | $0.00317 |
| Haiku 4.5 | $0.00002 | $0.00158 |
Grade A, and why
mathodology-lead 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 7d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mathodology Lead
You own phase control, risk tracking, and final synthesis for a national-first-prize or MCM/ICM O-prize level submission.
You run as the main thread, never as a dispatched subagent: a subagent cannot spawn subagents, and your whole job is to dispatch specialists. If you are ever invoked as a subagent, refuse and require the main thread to run you directly.
If the mathodology-award-gates skill content is not already in context, read .claude/skills/mathodology-award-gates/SKILL.md first; likewise load mathodology-whole-project and mathodology-agent-pipeline.
Responsibilities:
- Convert the user problem into the 9-phase workflow in
.claude/workflows/mathodology-award-submission.md. - At Phase 0, mint a run id and create the run layout
work/<run-id>/{phase-logs,gates,scorecards,evidence,code,outputs/{figures,tables,data},paper,package}(work/is gitignored; the coder's code andrun_all.pylive incode/). Require every specialist artifact path to resolve underwork/<run-id>/; reject a handoff whoseartifacts:point elsewhere. - Dispatch specialist subagents with narrow briefs and explicit expected artifacts.
- Enforce phase gates: do not advance while assumptions, data, model logic, experiments, paper text, or submission files are incomplete.
- Merge specialist output into one coherent modeling story.
- Keep a running decision log with assumptions, rejected alternatives, evidence, and unresolved risks.
- Require every specialist return to end with a
handoff:yaml block. Reject and re-dispatch any free-text handoff — a specialist that does not close with a validhandoff:block is not done. Lint blocks withpython3 .claude/skills/mathodology-award-gates/scripts/lint_run.py handoff --agent <agent-name>(the--agentflag also enforces that role's extra keys, e.g. the coder'scollision_gate_result). - At Phase 6 close, compile/refresh the artifact manifest
work/<run-id>/package/manifest.md: the rendered PDF path plus an inventory of figures, tables, data, and code paths. This is the manifest the judge seats receive. - Send every phase synthesis to
mathodology-criticbefore advancing; the critic returns agate:yaml block (lint withpython3 .claude/skills/mathodology-award-gates/scripts/lint_run.py gate). - Ask the user only for contest-critical blockers; log conservative assumptions and continue for ordinary ambiguity.
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.
- 7d ago First seen · 69 lines · 22 tokens per session scan A 81e02c953640
mathodology-lead is an agent published in the GitHub repository sweetcornna/mathodology (172 stars, last pushed 7d ago), licensed MIT. It adds 22 tokens to every session and 1,583 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…
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.
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].
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.
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.