interactor-agent

An agent that writes interactors for interactive programming problems using testlib.h, a C++ library for building judges and test tools.

In plain words
What is it for?
Use it to create Polygon interactors, which are custom judges, for problems where a participant's solution communicates back and forth with the judge.
Why use it?
Interactive problems require the judge and the submitted program to exchange messages during execution, so the interactor must validate input, flush replies, and report verdicts correctly.

Agent for Claude Code

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 agents/7oskaaa/polygon-problems-generator/interactor-agent
Clone the repo
git clone --depth 1 https://github.com/7oSkaaa/polygon-problems-generator

Made for: Claude Code.

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 906 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 $0.00036 $0.00906
Opus 5 $0.00018 $0.00453
Sonnet 5 $0.00007 $0.00181
Haiku 4.5 $0.00004 $0.00091

Measured 2d ago against content hash addf4302b180, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interactor-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.

.claude/agents/interactor-agent.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 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.

Start by reading the full interactor guide:

Read tutorials/interactor.md

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 · 66 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 · 66 lines · 36 tokens per session scan A addf4302b180

Subscribe to this mod's changes

interactor-agent is an agent published in the GitHub repository 7oSkaaa/polygon-problems-generator (21 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 906 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens