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.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 5.1 | $0.00093 | $0.00937 |
| Opus 5 | $0.00046 | $0.00468 |
| Sonnet 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 7d 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.
- 7d 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 (9 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 937 once invoked, about $0.0005 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
mspm0-ccs
Tool-neutral CLI agent rules for TI MSPM0 development with Code Composer Studio, Keil/uVision, CMake/GCC/OpenOCD, SysConfig, and DriverLib. Use when an agent needs to inspect or modify MSPM0 projects, edit .syscfg configuration, avoid generated SysConfig/build files, use DriverLib APIs, validate SysConfig output…
mspm0-skill
Tool-neutral CLI agent rules for TI MSPM0 development with SysConfig, DriverLib, CCS, Keil/uVision, CMake/GCC/OpenOCD, and supported board references. Use when an agent needs to inspect or modify MSPM0 projects, validate SysConfig output, package examples, or work on NUEDC embedded firmware.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
bash
Command-line interface for the Zengram system. Use this to store, search, and retrieve shared memories from any terminal-based agent or script.
iot-expert
Expert-level IoT systems, embedded devices, edge computing, and IoT protocols. Use when the user mentions embedded, edge computing, MQTT, sensors, or firmware, or when the task involves IoT Architecture, IoT Protocols, Embedded Systems, or Device Design.
embedded-debugging
Debug embedded firmware on real hardware through the jlink-mcp server — crashes, hangs, peripheral misconfiguration, silent devices. Covers loading ELF symbols for source-level backtraces, supplying an SVD for named peripheral fields, and the halt/read/resume discipline. Use whenever debugging a microcontroller over a…