07-interactor

A rule set for writing Polygon interactive judges with testlib.h. An interactive judge exchanges messages with a contestant's program while checking its queries and answers.

In plain words
What is it for?
Use it when implementing or reviewing an interactor, including participant reads, response flushing, query-limit checks, error handling, and correct verdict reporting.
Why use it?
It prevents common judge errors involving input sources, output flushing, bounds, query limits, and failure signals. These mistakes can produce incorrect verdicts or leave the contestant program waiting.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/7oskaaa/polygon-problems-generator/07-interactor
Clone the repo
git clone --depth 1 https://github.com/7oSkaaa/polygon-problems-generator

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 896 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00896
Opus 5 $0.00000 $0.00448
Sonnet 5 $0.00000 $0.00179
Haiku 4.5 $0.00000 $0.00090

Measured 2d ago against content hash 8f1e64295341, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

07-interactor 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.

.cursor/rules/07-interactor.mdc · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 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 interactors using testlib.h.

Shared: Read .claude/shared.md first.

Key Rules

  • Always include #include "testlib.h" and registerInteraction(argc, argv) (no third argument)
  • Read test data from inf, participant output from ouf — never from cin
  • Write responses to participant via cout followed immediately by cout.flush() — never skip the flush
  • Use ouf.readInt(lo, hi, "name") / ouf.readToken() with bounds for all participant reads
  • Use quitf(_ok, ...) for correct, quitf(_wa, ...) for wrong answer, quitf(_pe, ...) for format errors, quitf(_fail, ...) only for judge/interactor bugs
  • Enforce query limits explicitly — give _wa if the participant exceeds them
  • On any error (query limit exceeded, invalid query format): send -1 to the solution BEFORE calling quitf:
    cout << -1 << "\n";
    cout.flush();
    quitf(_wa, "reason");
    
    The solution must exit(0) on reading -1. Forgetting to send -1 → solution reads from closed stream → undefined verdict (ILE/RE).
  • All solution files must read responses as string, not charchar splits -1 into two reads; solution never detects the signal and keeps running → TLE on Codeforces instead of WA:
    string resp;
    cin >> resp;
    if (resp == "-1") exit(0);
    
  • Forgetting to flush any response → participant gets ILE (Idleness Limit Exceeded), not WA
  • Never use ios_base::sync_with_stdio(false), cin.tie(nullptr) in interactive solutionscin.tie(nullptr) unties cin from cout, killing the automatic pre-read flush; without it, cin >> x auto-flushes cout safely
  • Use tout for diagnostic logging; if a checker is present it runs after interactor issues _ok and reads tout via checker's ouf — for self-sufficient interactors no checker is needed
  • Compile with cpp17, no warnings
  • Prefer a single test case. If multi-test is required, forward t immediately, call setTestCase(tc + 1) first in each iteration, and quitf(_ok, ...) once after the loop
  • A self-sufficient interactor needs no checker. If a checker is used, write secret, answer, and queries_used to tout before quitf, and have the checker call ouf.readEoln() after each integer

Read the full file on GitHub · 61 lines

Changes

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.

  1. 2d ago First seen · 61 lines · 896 tokens per session scan A 8f1e64295341

Subscribe to this mod's changes

07-interactor is a cursor rule published in the GitHub repository 7oSkaaa/polygon-problems-generator (21 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 896 tokens. 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.