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/7oskaaa/polygon-problems-generator/agents-mdgit clone --depth 1 https://github.com/7oSkaaa/polygon-problems-generatorWhat 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 | $0.06734 | $0.06734 |
| Opus 5 | $0.03367 | $0.03367 |
| Sonnet 5 | $0.01347 | $0.01347 |
| Haiku 4.5 | $0.00673 | $0.00673 |
Grade A, and why
polygon-problems-generator 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 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.
How it starts
The opening of the file, as written. The whole thing — 574 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared agent context
This is the only copy of roster, layout, pipeline, and critical rules.
Specialist agents (.claude/agents/<role>.md) add only their role contract. Do not paste this file into those stubs — tell the model to Read it.
Deep references (read on demand, do not duplicate):
guidelines.md— full human checklisttutorials/polygon-hints.md— Polygon wording and testlib hintstutorials/<topic>.md— statement / validator / checker / generator / interactordocs/workflow.md— local-first loop and how to prompt a fix
Agent roster
| Agent | Role |
|---|---|
statement-agent |
LaTeX statement + editorial (statement.tex, tutorial.tex) |
validator-agent |
testlib.h input validator (validator.cpp) |
checker-agent |
Standard checker recommendation or custom checker (checker.cpp) |
interactor-agent |
testlib.h interactor for interactive problems (interactor.cpp) |
solutions-agent |
ACC / TLE / WA solutions in C++ and Java |
generator-agent |
testlib.h test generator + FreeMarker script (generator.cpp) |
reviewer-agent |
Full review; blocks on any FAIL verdict |
orchestrator |
Coordinates the pipeline; do not run other agents except through this |
Problem folder layout
problems/<name>/
├── statement/
│ ├── statement.tex
│ └── tutorial.tex
├── solutions/
│ ├── acc.cpp ← main ACC (clear, not over-optimized)
│ ├── acc_java.java
│ ├── acc_alt.cpp ← second ACC, different approach
│ ├── brute.cpp
│ └── wa.cpp
├── generators/
│ └── generator.cpp
├── validator.cpp
├── checker.cpp
└── interactor.cpp ← interactive only
Create with:
mkdir -p problems/<name>/{statement,solutions,generators,samples,validator_tests}
cp templates/validator.cpp problems/<name>/validator.cpp
cp templates/checker.cpp problems/<name>/checker.cpp
cp templates/statement/raw.tex problems/<name>/statement/raw.tex
cp templates/statement/statement.tex problems/<name>/statement/statement.tex
cp templates/statement/tutorial.tex problems/<name>/statement/tutorial.tex
cp templates/generators/generator.cpp problems/<name>/generators/generator.cpp
# interactive only: cp templates/interactor.cpp problems/<name>/interactor.cpp
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.
- 2d ago First seen · 574 lines · 6,734 tokens per session scan A 5555a9068ff2
polygon-problems-generator AGENTS.md is an instructions file published in the GitHub repository 7oSkaaa/polygon-problems-generator (21 stars, last pushed 2d ago), licensed MIT. It adds 6,734 tokens to every session, about $0.0337 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
ai-agents-for-beginners AGENTS.md
Instructions for microsoft/ai-agents-for-beginners, covering agents.md, project overview, setup commands, prerequisites and initial setup.
deep-agents-from-scratch CLAUDE.md
Instructions for langchain-ai/deep-agents-from-scratch, covering claude.md, project overview, development commands, environment setup and install dependencies using uv (preferred package manager).
building-a-coding-agent-from-scratch-course AGENTS.md
Instructions for decodingai-magazine/building-a-coding-agent-from-scratch-course, covering decode, project structure, tech stack, docs & external services and running commands.
agentic-ai-system-course AGENTS.md
Instructions for bryanyzhu/agentic-ai-system-course, covering claude.md — ai mentor's guideline, the design you are working inside, your role, the curriculum and reference systems: optional, triggered, not required.
MindTrain AGENTS.md
Instructions for shigella520/MindTrain, covering repository instructions, mindtrain target architecture, training and content integrity, safety and integrity and fast release workflow.
fluent AGENTS.md
Instructions for m98/fluent, covering 🤖 ai agent integration guide, 📚 quick start for ai agents, your role, primary reference document and 📁 file structure & usage guide.