polygon-problems-generator: Skill for Claude Code

.agents/skills/checker-agent/SKILL.md

checker-agent is a skill for Claude Code, Codex from 7oSkaaa/polygon-problems-generator. It costs 28 tokens per session (568 once invoked), scanned A, original, MIT.

A guide for choosing or writing output checkers for Polygon, a platform for creating programming contest problems. A checker decides whether a contestant's answer should be accepted.

In plain words
What is it for?
Use it to recommend a standard checker such as token, number, or yes/no comparison, or to generate a C++ testlib.h checker when custom validation is needed.
Why use it?
It helps avoid writing a custom checker when a standard one is enough and sets rules for safely checking custom outputs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; installed under .agents/ (shared by several agents).

This is 7oSkaaa/polygon-problems-generator's own configuration. It tells Claude Code and Codex how to work on polygon-problems-generator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything polygon-problems-generator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 7oSkaaa/polygon-problems-generator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/7oSkaaa/polygon-problems-generator/main/.agents/skills/checker-agent/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/7oSkaaa/polygon-problems-generator

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for checker-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/7oskaaa/polygon-problems-generator/checker-agent/github.svg)](https://agentmods.dev/skills/7oskaaa/polygon-problems-generator/checker-agent)
Your own site
<a href="https://agentmods.dev/skills/7oskaaa/polygon-problems-generator/checker-agent"><img src="https://agentmods.dev/badge/skills/7oskaaa/polygon-problems-generator/checker-agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for checker-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/7oskaaa/polygon-problems-generator/checker-agent"><img src="https://agentmods.dev/badge/skills/7oskaaa/polygon-problems-generator/checker-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 568 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 24
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
How audits are shown
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 5.1 $0.00028 $0.00568
Opus 5.5 $0.00011 $0.00227
Sonnet 5.5 $0.00006 $0.00114
Haiku 4.5 $0.00003 $0.00057

Measured 10d ago against content hash 0e3b68c500fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

checker-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 10d 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.

.agents/skills/checker-agent/SKILL.md · 41 lines

What it actually says

Read .claude/shared.md first.

You are an expert competitive programming problem setter specialising in writing Polygon checkers using testlib.h.

Shared: Read .claude/shared.md first.

Apply the checker guidance from tutorials/polygon-hints.md, especially preferring standard checkers, not revalidating input, reading jury and participant answers identically, and covering all custom-checker termination reasons with checker tests.

Key Rules

  • Prefer standard checkers — only write custom when truly needed
  • Pick the standard checker by output shape:
    • ncmp — integers only (one or more 64-bit integers, whitespace ignored)
    • wcmp — strings or mixed tokens (default when the output is not integers only)
    • yesno — one YES/NO; nyesno — zero or more YES/NO answers (any letter case)
    • rcmp4 / rcmp6 / rcmp9 — real numbers with absolute or relative error 1E-4 / 1E-6 / 1E-9
    • lcmp — lines, extra whitespace ignored; fcmp — lines compared exactly; hcmp — one huge integer
  • Multi-test custom checker: call setTestCase(i) at the start of each test case
  • Checker tests are required even for a standard checker: checker_tests/<ok|wa|pe>_<name>.{in,out,ans} (.out = participant, .ans = jury). wcmp and ncmp never return PE, so give them only ok_ and wa_ tests. Polygon rejects an empty .out, so every checker test needs some participant output
  • Use the readAns paradigm: one function reads both ouf and ans identically
  • registerTestlibCmd(argc, argv) at the start of main
  • Use quitf(_ok, ...) / quitf(_wa, ...) / quitf(_pe, ...) for verdicts
  • No freopen — never
  • Compile with cpp17, no warnings

Recommendation Format

RECOMMENDATION: [standard checker name] OR [custom checker needed]
REASON: brief explanation

For custom checkers: return only the complete C++ code, no explanation.

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. 10d ago Changed · +7 lines 0e3b68c500fa
  2. 2mo ago First seen · 34 lines · 28 tokens per session scan A 850fd6dfdf12

Subscribe to this mod's changes

checker-agent is a skill published in the GitHub repository 7oSkaaa/polygon-problems-generator (21 stars, last pushed 11d ago), licensed MIT. It adds 28 tokens to every session and 568 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens