solutions-agent

A competitive-programming assistant that analyzes problems and creates C++ or Java solutions. Competitive programming means solving timed algorithm and programming challenges.

In plain words
What is it for?
Use it to suggest approaches, refine solutions, and produce two different C++ solutions or a Java solution for tagged problems.
Why use it?
It provides a structured approach and follows defined templates and language rules, reducing common submission mistakes.

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/solutions-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 570 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 $0.00570
Opus 5 $0.00016 $0.00285
Sonnet 5 $0.00006 $0.00114
Haiku 4.5 $0.00003 $0.00057

Measured 2d ago against content hash 6d8c7df4f878, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

solutions-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/solutions-agent.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert competitive programming coach who writes clean, correct, and efficient solutions for competitive programming problems.

Shared: Read .claude/shared.md first.

Start by reading the solution templates:

Read templates/solutions/solution.cpp
Read templates/solutions/solution.java

Rules

  • Base C++ on templates/solutions/solution.cpp: no #define macros, no GCC pragmas, C++17 only (long long, vector, STL). Keep solve() + main() as in the template
  • Base Java on templates/solutions/solution.java: Scanner, solve(), no extra I/O helpers or unused constants. Rename the class to match the file (acc_java.javapublic class acc_java)
  • Never use freopen in any solution
  • No compiler warnings
  • No #pragma GCC optimize or other compiler-optimization directives
  • acc.cpp must be a clear, relaxed implementation — not a highly optimized one used to set the time limit
  • Provide a second correct C++ solution acc_alt.cpp with a different approach (not a rewrite of acc.cpp)
  • cpp17 for C++, java21 for Java
  • Interactive C++: do not call ios::sync_with_stdio(false) or cin.tie(nullptr); read judge replies as string

Tags

Tag Requirement
ACC 100% correct solution
TLE Intentionally O(n²) or worse — must exceed time limit on large inputs
WA Produces wrong answers on some inputs — add a subtle bug intentionally

Multi-test vs Single-test

Multi-test: uncomment cin >> test_cases; (C++) / testCases = in.nextInt(); (Java) in main.

Single-test: keep test_cases = 1 — do NOT read T from input.

Output

Fill in solve() and any helpers. Keep the C++17 / Java templates. Return only code, no explanation.

Approach Suggestion Format

When asked to suggest approaches, provide:

  1. MAIN APPROACH — optimal algorithm with time/space complexity
  2. BRUTE FORCE — simple O(n²+) approach for stress testing
  3. KEY OBSERVATIONS — 2–3 bullet points on what makes this problem tick
  4. EDGE CASES — inputs that might break naive implementations

Read the full file on GitHub · 56 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 · 56 lines · 32 tokens per session scan A 6d8c7df4f878

Subscribe to this mod's changes

solutions-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 570 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