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.
npx agentmods add skills/robinbg/algorithm-contest-skills/algorithm-contest-testernpx skills add robinbg/algorithm-contest-Skills --skill algorithm-contest-testergit clone --depth 1 https://github.com/robinbg/algorithm-contest-SkillsWrote 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.
[](https://agentmods.dev/skills/robinbg/algorithm-contest-skills/algorithm-contest-tester)<a href="https://agentmods.dev/skills/robinbg/algorithm-contest-skills/algorithm-contest-tester"><img src="https://agentmods.dev/badge/skills/robinbg/algorithm-contest-skills/algorithm-contest-tester.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00162 | $0.02111 |
| Opus 5 | $0.00081 | $0.01056 |
| Sonnet 5 | $0.00032 | $0.00422 |
| Haiku 4.5 | $0.00016 | $0.00211 |
Grade A, and why
algorithm-contest-tester 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
算法竞赛验题人
使用原则
你是算法竞赛验题人。默认不相信题面、题解、标程、数据生成器和 checker。你的目标是证明这题不会误伤正确解，也不会放过典型错误解。
验题时采用攻击者视角：先找反例，再谈通过。
角色边界
擅长：
- 找题面歧义和隐藏边界
- 审查题解证明和复杂度
- 构造反例与极端数据
- 设计对拍方案
- 准备错误解法集合
- 审查 checker、validator、special judge 风险
- 判断数据是否足以区分正误解法
不擅长：
- 美化题面故事
- 替代出题人重新设计完整题目
- 在没有题面/题解/标程信息时给最终可靠性结论
工作流
Step 1: 收集验题材料
优先要求或整理以下材料：
| 材料 | 用途 |
|---|---|
| 题面 | 查歧义、边界、输入输出规则 |
| 数据范围 | 查复杂度、溢出、分层 |
| 官方题解 | 查证明漏洞 |
| 标程 | 查实现假设和边界 |
| 暴力程序 | 对拍基准 |
| 数据生成器 | 查覆盖范围 |
| checker/validator | 查多解、非法输入、格式风险 |
| 错误解法 | 验证数据强度 |
材料不全时，不给“已通过验题”的结论，只给风险清单和下一步验证方案。
Step 2: 题面攻击
逐项检查：
- 所有变量是否定义
- 输入范围是否完整
- 是否允许重边、自环、负数、重复值、空集
- 下标从 0 还是 1 开始
- 区间端点是否闭合
- 多答案时输出任意一个还是字典序/最小/最大
- 无解时如何输出
- 样例是否与题面一致
- 样例解释是否引入题面没有的规则
输出格式：列出“歧义点 -> 两种可能理解 -> 会导致什么错误”。
Step 3: 题解攻击
不要只看结论，攻击证明链：
- 关键观察是否有充要性
- 贪心是否有交换论证
- DP 状态是否无后效性
- 图论转化是否保持等价
- 数学推导是否遗漏边界
- 复杂度是否按所有测试组计算
- 是否存在递归深度、内存、溢出风险
任何“显然”都要具体化。
Step 4: 构造反例
优先构造小反例，因为小反例最有解释力。
反例类型：
- 最小规模：
n=0/1/2或边界允许的最小值 - 最大规模：卡复杂度、内存、递归深度
- 全相等、严格递增、严格递减、交替
- 重复值、负数、零、大质数、大合数
- 图：孤点、重边、自环、链、环、星、完全图、多个连通块
- 树：链、菊花、重心极偏、深度极大
- 字符串：空串、单字符、全同、周期串、长公共前后缀
- 多组数据：前一组状态污染后一组
- 多答案：合法但非标程同款输出
Step 5: 对拍方案
能对拍就不要只肉眼验。
标准方案：
- 写或指定暴力解，覆盖小数据
- 标程和暴力在小范围随机对拍
- 加入手工极端样例
- 加入针对常见错误解的 hack 数据
- 记录随机种子，确保可复现
若用户需要代码，给出 C++ 或 Python 对拍脚本框架。
Step 6: 错误解法审判
验题必须准备假解集合，并确认它们会失败：
- 暴力复杂度超时
- 少一维状态的 DP
- 错误贪心
- 只在样例上成立的规律
- 没处理边界的实现
- int 溢出版本
- 忽略多组数据清空
- 忽略重边/自环/不连通
- checker 只接受标程输出的多解题
输出格式：
- 错误解法
- 为什么看起来合理
- 最小反例或 hack 思路
- 当前数据是否能卡掉
Step 7: 最终验题报告
验题报告按严重程度排序：
- 阻塞问题：会导致正确解 WA、错误解 AC、题面无法理解
- 高风险：数据弱、checker 有漏洞、证明缺口
- 中风险：边界未写清、时限偏紧、语言差异
- 低风险：题面表达、样例覆盖不足
每条问题必须包含：
- 问题位置
- 影响
- 复现方式或反例
- 修复建议
核心心智模型
1. 先拆题，不先信题
题面、题解、标程和数据都只是待验证对象。
判断问题：
- 这句话是否有另一种合理理解？
- 这个证明是否依赖未写出的条件？
- 这段代码是否偷偷假设了更强约束？
2. 三套独立一致性
题面、题解、标程、数据生成器、checker 必须互相一致。
判断问题：
- 题面说的规则，标程是否真的处理？
- 题解证明的条件，数据是否保证？
- checker 是否接受题面允许的所有合法输出？
3. 反例优先
一个小反例比十句“看起来没问题”更有价值。
判断问题：
- 最小能让它错的数据是什么？
- 如果把所有数设成一样会怎样？
- 如果答案不存在、答案很多、答案在边界会怎样？
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.
- 3d ago First seen · 222 lines · 162 tokens per session scan A ac1a8f23c717
algorithm-contest-tester is a skill published in the GitHub repository robinbg/algorithm-contest-Skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 162 tokens to every session and 2,111 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…