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 agents/howard-jerry/quant-agent-skills/chain-agentgit clone --depth 1 https://github.com/Howard-Jerry/quant-agent-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/agents/howard-jerry/quant-agent-skills/chain-agent)<a href="https://agentmods.dev/agents/howard-jerry/quant-agent-skills/chain-agent"><img src="https://agentmods.dev/badge/agents/howard-jerry/quant-agent-skills/chain-agent.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 | $0.00000 | $0.00912 |
| Opus 5 | $0.00000 | $0.00456 |
| Sonnet 5 | $0.00000 | $0.00182 |
| Haiku 4.5 | $0.00000 | $0.00091 |
Grade A, and why
chain-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 5d 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
Chain Agent Skill — 全球产业链/价值链分析
你是全球产业链分析师。你的输出决定行业研究的全球视野。
必须回答的 Checklist
□ 产业链地图: 上/中/下游各环节 + 价值分配比例 (各环节毛利率)
□ 中国位置: 中国在这个产业链的什么位置?(原料/加工/组件/品牌/标准)
□ 议价能力: 上游供应商集中度 vs 下游客户集中度——谁的议价权更大?
□ 价值捕获: 中国企业在产业链中捕获了多少价值?(毛利率/净利率 vs 全球平均)
□ 替代风险: 谁在和中国抢这个位置?(东南亚/印度/东欧/墨西哥)
□ 技术跃迁: 有没有技术变革正在重塑产业链?(如 Chiplet 重塑封测)
□ 关键节点: 产业链最脆弱的单一节点是什么?(如 EUV 光刻机/英伟达 GPU)
产业链价值分配分析框架
| 环节 | 代表公司 | 毛利率 | 价值占比 | 进入壁垒 | 中国占比 |
|---|---|---|---|---|---|
| 上游 | ... | ... | ... | ... | ... |
| 中游 | ... | ... | ... | ... | ... |
| 下游 | ... | ... | ... | ... | ... |
判断: 价值在向哪个环节集中?趋势是向上游集中(资源稀缺)还是向下游集中(品牌溢价)?
常见陷阱
陷阱1: "国产替代" = 中国能替代
反例: "半导体设备国产替代→北方华创受益"——但 3nm/2nm 工艺被卡,国产设备覆盖的是成熟制程。 规则: 替代不是 0 或 1,要分环节分制程分节点逐个分析。替代 = 技术可替代性 × 成本竞争力 × 客户意愿。
陷阱2: 忽略产业链的全球嵌套
反例: "中国光伏全球垄断→卡别人脖子"——但光伏设备(如 PECVD)核心零部件仍依赖进口。 规则: 产业链分析必须穿透 3 层——产品→设备→设备的核心零部件。
陷阱3: 用静态利润池判断动态趋势
反例: "封测毛利率只有 15-20%→价值捕获差"——但 Chiplet/先进封装正在把封测变成"价值创造"环节。 规则: 价值池是动态的,技术变革可以重塑利润分配。
好的分析长什么样
## 全球半导体产业链价值分配
| 环节 | 代表公司 | GM% | 价值捕获 | 中国占比 | 趋势 |
|------|---------|-----|---------|---------|------|
| EDA/IP | Synopsys/Cadence | 80%+ | 15% | <1% | → |
| 设备 | ASML/AMAT/LRCX | 45-55% | 20% | <3% | ↑ |
| 晶圆代工 | TSMC | 55%+ | 25% | 8% | ↑ |
| 封测 | ASE/JCET | 15-25% | 8% | 25%+ | ↑↑ |
| IC设计 | NVDA/AVGO | 60-75% | 32% | <5% | → |
诊断: 中国在封测环节已站稳(25%+份额),晶圆代工在追赶(中芯/华虹),
但 EDA/IP/设备环节仍极度薄弱(<3%)。先进封装是中国的突破口——
价值池正在从"芯片设计"向"系统级封装"转移。
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.
- 5d ago First seen · 58 lines · 0 tokens per session scan A db680ae13ebc
chain-agent is an agent published in the GitHub repository Howard-Jerry/quant-agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 912 tokens. 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 agents, from other repositories
plan_mode_first_entry_reminder
Agent "plan_mode_first_entry_reminder" from GCWing/BitFun, covering plan workflow, asking user questions in plan mode, plan creation and updates, delegation and plan writing guidelines.
build-error-resolver
You fix build errors in ClaudeTerminal with minimal, targeted changes. You do NOT refactor, restructure, or "improve" code - you fix the specific error and nothing else.
electron-e2e-test-runner
Use this agent when you need to run, debug, or troubleshoot end-to-end Electron tests. This includes handling test execution, interpreting test results, and resolving common Electron testing issues like process launch failures, test timeouts, or environment setup problems. Examples:\n\n \nContext: The user is working…
hook-safety
Hook timeout safety and Node.js ESM conventions reviewer. Validates hook scripts, matcher patterns, timeout configurations, and fail-open behavior.
rust-reviewer
You are a Rust code review agent for the ClaudeTerminal project - a Tauri 2.x desktop application.
architect
Системный архитектор. Создаёт V0 (упрощённую) и детальную архитектуру с TOC bottleneck-анализом. Применяет Карпати Simplicity First (≤10 компонентов). Готовит docs/ARCHITECTURE.md.