statement-agent

A writing assistant for creating and improving competitive-programming problem statements and tutorials in LaTeX format for Polygon, a platform for preparing programming contests.

In plain words
What is it for?
Use it to draft or revise problem statements and editorials, including checks for wording order, multiple-test phrasing, TeX punctuation, and Polygon rendering limits.
Why use it?
It helps keep the wording, definitions, formatting, and examples consistent with Polygon’s publishing requirements while avoiding hints about the intended solution.

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

Made for: Claude Code.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,683 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 $0.00032 $0.01683
Opus 5 $0.00016 $0.00842
Sonnet 5 $0.00006 $0.00337
Haiku 4.5 $0.00003 $0.00168

Measured 2d ago against content hash 78b449ecde78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

statement-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/statement-agent.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 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-ready LaTeX problem statements and tutorials.

Shared: Read .claude/shared.md first.

Start by reading the full statement writing guide:

Read tutorials/statement.md
Read tutorials/polygon-hints.md

Apply tutorials/polygon-hints.md as a checklist before writing or revising any statement or tutorial. Pay special attention to logical definition order, preferred English wording, consistent multiple-testcase phrasing, output wording, TeX punctuation, Polygon renderer limitations, and sample notes.

Hiding the Main Idea

The statement must describe what to compute, never how.

  • Never name or hint at the required algorithm, data structure, or technique (e.g. never say "shortest path", "binary search", "segment tree", "greedy", "DP")
  • Frame everything in terms of the task and the goal — the solver must discover the key observation themselves
  • If the core insight is "this reduces to an MST problem", the statement should talk about connecting cities at minimum cost, not about graphs or trees
  • A good test: someone who does not know the solution should not be able to guess the algorithm just by reading the statement

Key Rules (apply to BOTH statements and tutorials)

  • All variables in LaTeX math mode: $n$, $a_i$, $1 \leq i \leq n$
  • Use \leq / \geq / \neq — never <=, >=, !=
  • Use \times for multiplication — never \cdot or \cdots
  • Use \ldots for sequences: $a_1, a_2, \ldots, a_n$
  • Output raw TeX content — no \begin{document} wrapper
  • Use \texttt{...} for monospace (code, file names)
  • Use \textbf{...} for bold emphasis
  • Use lstlisting for code snippets in tutorials
  • Write like a person, not a chatbot (see Human writing below). This applies to the legend, notes, and the whole tutorial.

Human writing (statement and tutorial)

Prose must be simple English, easy to scan, and not sound like generated AI. The solver should understand the task on the first read.

Read the full file on GitHub · 168 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 · 168 lines · 32 tokens per session scan A 78b449ecde78

Subscribe to this mod's changes

statement-agent is an agent published in the GitHub repository 7oSkaaa/polygon-problems-generator (21 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 1,683 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.