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 instructions/handsomezr-netizen/mathmodel-skill/agents-mdgit clone --depth 1 https://github.com/handsomeZR-netizen/mathmodel-skillWhat 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 | $0.00604 | $0.00604 |
| Opus 5 | $0.00302 | $0.00302 |
| Sonnet 5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
mathmodel-skill AGENTS.md 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 3d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository instructions
This repository contains the mathmodel-skill product. When working inside this repository, act as a maintainer: do not start the ten-stage contest workflow merely because modeling-related files are present.
Sources of truth
SKILL.mddefines runtime behavior and trigger boundaries.references/stage_00_kickoff.mdthroughreferences/stage_09_review.mdcontain stage details and must be loaded lazily at runtime.competitions/<competition>/contains competition-specific rules, heuristics, overlays, and paper structures.templates/shared/decision_log.jsonis the canonical persistent-state template..codex-plugin/plugin.json,agents/openai.yaml, andskills/mathmodel-skill/SKILL.mdare packaging metadata or thin discovery shims. Do not duplicate the workflow into them.
Maintenance rules
- Preserve the trigger boundary: this skill is for CUMCM, MCM/ICM, and Diangong Cup contest work, not generic data analysis or ordinary paper review.
- Treat official contest rules as time-sensitive. Keep a verification date and primary source in
competitions/<competition>/current_rules.md; official current-year material always overrides repository guidance. - Treat empirical distributions and
winning_patterns.mdas observations or maintainer heuristics, never official thresholds or award predictors. - Keep user artifacts relative to the user's working directory (
state/,results/,figures/,paper_workspace/,paper_output/). Resolve repository resources relative to the installed skill root. - Keep
SKILL.mdconcise and dispatch stage-specific detail intoreferences/. - Do not add runtime claims about awards, token savings, or elapsed time without a reproducible benchmark.
- When changing behavior, update the README, tests, plugin version, state schema, and relevant competition docs together.
- Do not vendor or reintroduce templates, examples, papers, or binary assets without a clear redistribution license. Keep runtime dependencies and external-source boundaries accurate in
THIRD_PARTY_NOTICES.md.
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.
- 3d ago First seen · 40 lines · 604 tokens per session scan A a5e36c656642
mathmodel-skill AGENTS.md is an instructions file published in the GitHub repository handsomeZR-netizen/mathmodel-skill (245 stars, last pushed 1mo ago), licensed MIT. It adds 604 tokens to every session, about $0.0030 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 instructions, from other repositories
TFG-TFM_EPS copilot-instructions.md
Instructions for jmrplens/TFG-TFM_EPS, covering reglas críticas, estructura del proyecto, configuración del documento, titulaciones disponibles and regla de idioma.
latexml-oxide CLAUDE.md
Instructions for dginev/latexml-oxide, covering claude.md, active priorities: faithful parity + beyond-perl arxiv runs, project overview, workspace structure and internal documentation.
talisman-skill AGENTS.md
Instructions for jeunecraack/talisman-skill, covering talisman — agent playbook (v1), when to run, workflow (8 phases), key features and repo structure.
scientific-writing CLAUDE.md
Instructions for koljaschoepe/scientific-writing, covering scientific writing framework, schnellstart, workflow, befehle and regeln für generierte texte.
mcp-ads-arxiv CLAUDE.md
Instructions for estevesjh/mcp-ads-arxiv, covering academic research & token optimizer skill, core directives, local-first, pre-flight survey protocol and acquisition order (handled by getpaper).
Academic-Writing CLAUDE.md
Instructions for AlessandroCaforio/Academic-Writing, covering project brain - thesis: automation & political ideology, memory protocol, github repository, project structure (updated 2026-02-16) and data sources.