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 skills add Jinchen-Yang/diansai-skill --skill read-problemgit clone --depth 1 https://github.com/Jinchen-Yang/diansai-skillWrote 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/jinchen-yang/diansai-skill/read-problem)<a href="https://agentmods.dev/skills/jinchen-yang/diansai-skill/read-problem"><img src="https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/read-problem/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.
<a href="https://agentmods.dev/skills/jinchen-yang/diansai-skill/read-problem"><img src="https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/read-problem.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00093 | $0.00937 |
| Opus 5.5 | $0.00037 | $0.00375 |
| Sonnet 5.5 | $0.00019 | $0.00187 |
| Haiku 4.5 | $0.00009 | $0.00094 |
Grade A, and why
read-problem 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 2mo 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.
What it actually says
read-problem —— 读题/审题(流水线入口 ①)
lane: lead · needs: multimodal(解析 PDF/图片 → 只在 lead/Claude 会话跑;队友 lane 直接用产出的 problem.yaml)
这是整条流水线的真正入口。每年题目规定都不同,一切从读懂当年题目开始——尤其先看「限制条款」(如允不允许用摄像头,直接决定 K230 上不上)。
步骤
- 定位题目:在
inputs/problem/找当年题目文件(PDF/文本/图片)。没有就提醒用户投喂,停。 - 读全文:用 Read 读题目(PDF 多模态直接读)。逐条抠:基础要求、发挥部分、评分、场地尺寸/标记、时间限制、器件/重量/尺寸限制。
- 查 KB 作背景(用 Read,不复制):
kb/01-赛事概况与赛制流程.md—— 赛制、限制条款的常见形态、评分惯例。kb/02-历年小车与控制类赛题.md—— 对照历年同类题型,识别"这是哪一类"(送药/追踪/循迹/双车/识别)。
- 抽成结构,写
design/problem.yaml(schema 见下)。限制条款单列、最显眼。 - 标注模糊点:题目没写清、或需要现场确认的(场地材质、起停判定、是否允许外部供电等),放进
ambiguities,提请用户确认——这是轻人工门,别替用户拍板硬约束。 - 更新
STATUS.md:阶段 → ②;lead 段标"题目已解析,待 /plan-solution"。
design/problem.yaml schema
title: # 题目名
year: # 年份/届
category: # 送药 | 追踪 | 循迹 | 双车 | 识别 | 其他(对照 KB02)
source: # inputs/problem/<文件名>
restrictions: # ★ 限制条款——最先看、最关键
camera_allowed: # true | false | unknown(决定 K230)
power: # 供电限制(如禁外接电源/电压上限)
size_weight: # 尺寸/重量限制
parts: # 指定/禁用器件
other: []
required_functions: # 要实现的功能
- {id: F1, desc: , level: basic|advanced, points: }
scoring: # 评分细则
- {item: , points: }
arena: {desc: , dimensions: , track: , markings: }
timing: {run_limit: , notes: }
constraints: [] # 其他硬约束
ambiguities: # 需人工确认(不要自己默认)
- {q: , why: }
注意
- 不要发明题目没写的东西;题目没明确的进
ambiguities,别填默认值(默认值正是赛场翻车点)。 - 限制条款里
camera_allowed=false时,要在产出里显著提示:本届不能上 K230,方案需走纯灰度/电磁,后续plan-solution据此选。 - 产出是给
plan-solution/select-parts用的机器可读需求,写清楚、可签字。
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.
- 2mo ago First seen · 52 lines · 93 tokens per session scan A cbbc1f0c81a2
read-problem is a skill published in the GitHub repository Jinchen-Yang/diansai-skill (12 stars, last pushed 3mo ago), licensed MIT. It adds 93 tokens to every session and 937 once invoked, about $0.0004 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 2026-08-31.
read-problem compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| read-problemJinchen-Yang/diansai-skill | Skill | 12 | 3mo ago | MIT | A | 93 | Claude Code |
| mspm0-ccsmc3545dada/mspm0-skill | Skill | 378 | 3mo ago | MIT | A | 101 | Claude Code, Codex |
| mspm0-skillIbook000/mspm0-skill | Skill | 13 | 1mo ago | MIT | A | 76 | Claude Code, Codex |
| bashZenSystemAI/Zengram | Skill | 64 | yesterday | MIT | A | 0 | Claude Code, Codex |
| volt-firmwaretonone-ai/tonone | Skill | 77 | 23d ago | MIT | A | 76 | Claude Code |
| iot-expertpersonamanagmentlayer/pcl | Skill | 44 | 11d ago | Apache-2.0 | A | 59 | Claude Code |
| volt-drivertonone-ai/tonone | Skill | 77 | 23d ago | MIT | A | 63 | Claude Code |