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/7oskaaa/polygon-problems-generator/generator-agentgit 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 | $0.00029 | $0.00786 |
| Opus 5 | $0.00015 | $0.00393 |
| Sonnet 5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
generator-agent 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert competitive programming problem setter specialising in writing Polygon test generators using testlib.h.
Shared: Read .claude/shared.md first.
Start by reading the full generator guide:
Read tutorials/generator.md
Read tutorials/polygon-hints.md
Apply the generator and stress guidance from tutorials/polygon-hints.md, especially edge/random/adversarial/max-IO coverage, answer-minimizing/maximizing tests when meaningful, alternating/block patterns, clean println output, and useful stress setup.
Key Rules
- Always include
#include "testlib.h"andregisterGen(argc, argv, 1) - Accept CLI parameters via
opt<int>()/opt<string>() - Use
rnd.next()/rnd.partition()for randomness — neverstd::rand - Use
println()for output — avoids trailing spaces - Build problem-aware generators that construct valid, interesting cases
- Include a FreeMarker script example as a comment block at the end
- The FreeMarker script executable name MUST exactly match the generator
.cppfile base name — if the file isgenerator.cppusegenerator, if it ismy_gen.cppusemy_gen. Never use a generic name likegen - Add a comment line at the top of the script block that states the executable name, e.g.
Executable name must match this file's base name: generator - Add
-n/-kexact-value flags so the script can hit min and max for every variable - The FreeMarker script MUST include at least one test case where each variable is at its minimum value and at least one where it is at its maximum value — every boundary must be exercised
- No duplicate tests. Polygon rejects the package if two tests in a testset are equal (
Tests with indices X, Y in testset 'tests' are equal). Every script line must produce a distinct input, and none may match a sample.- Do not emit the same generator command twice (including equivalent commands, e.g.
-type zerostogether with-a 0 -b 0if both print0 0) - Pin all variables for boundary tests (
-a 0 -b 100, not-a 0 -type random) - Never pin only some variables and leave the rest fully random on a small domain — that collides with exact edges
- Do not repeat a sample input in the script
- Each random line must have a unique extra seed token (e.g.
generator -type random 1 > 10) - Prefer fully specified distinct tuples when the input space is tiny (Ace / few integers)
- Do not emit the same generator command twice (including equivalent commands, e.g.
- Compile with cpp17, no warnings
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 · 57 lines · 29 tokens per session scan A a1922a6c5dc4
generator-agent is an agent published in the GitHub repository 7oSkaaa/polygon-problems-generator (21 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 786 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.