Borrowing it
Nothing to install: this file belongs to bobby1129/stock-analysis-pro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bobby1129/stock-analysis-pro/main/AGENTS.mdgit clone --depth 1 https://github.com/bobby1129/stock-analysis-proWrote 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/instructions/bobby1129/stock-analysis-pro/agents-md)<a href="https://agentmods.dev/instructions/bobby1129/stock-analysis-pro/agents-md"><img src="https://agentmods.dev/badge/instructions/bobby1129/stock-analysis-pro/agents-md/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/instructions/bobby1129/stock-analysis-pro/agents-md"><img src="https://agentmods.dev/badge/instructions/bobby1129/stock-analysis-pro/agents-md.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 | $0.03151 | $0.03151 |
| Opus 5.5 | $0.01260 | $0.01260 |
| Sonnet 5.5 | $0.00630 | $0.00630 |
| Haiku 4.5 | $0.00315 | $0.00315 |
Grade A, and why
stock-analysis-pro AGENTS.md scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 新闻搜索: Google News RSS (curl --proxy http://127.0.0.1:10809) 最稳定；百度易触发验证码；Bing国际版 curl 无法解析需浏览器。 How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stock-analysis-pro Agent备忘
项目核心文档。Agent 动本项目前先读此文件；改动代码必须同步更新此文档。 相关文档: DESIGN.md(设计)、USAGE.md(用法)、DAILY_CONTENT.md / DAILY_CONTENT_PROJECT.md(抖音内容)、IGNITION_RADAR_DESIGN.md(点火雷达)、PROGRESS.md。
数据源与接口
- industry_screener.py: 新浪行情 + 同花顺F10主营业务；剔除北交所；成交额 /10000 转亿。
- 概念资金流(两套口径, 2026-09-30主力口径上线):
- 主力口径(默认): 同花顺官方
stockpage.10jqka.com.cn/stock_page/api/v1/stockpage/funds/?code=<885码>&marketId=48= 超大单/大单/中单/小单四档，与同花顺APP"主力资金"同口径(用户对照APP验证一致)。主力净额=超大单+大单。四单净额之和恒为0(按委托单大小双侧记账)。封装在collectors/ths_mainforce.py，无需hexin-v，375概念约70秒，当日缓存cache/ths_mainforce_YYYYMMDD.json(仅15:05后生成的缓存有效)。 - 全口径(gnzjl): akshare
stock_fund_flow_concept("即时")= 全量387概念，净额=主动买-主动卖(主动口径)。网页版只返回涨幅TOP50有采样偏差(弃用)。资金榜需过滤宽基桶(融资融券/股通/国企改革等)，但"国家大基金持股"是真题材不可误杀。 - 两口径不可相加：主力=按委托单大小分档("谁在买")，主动=按成交方向("买方急不急")。背离信号: 主力流出≥0.5亿+主动流入≥2亿=⚠派发嫌疑；反向=吸筹嫌疑。
- 概念名→885码映射:
data/ths_concept_885_mapping.json，由scripts/build_ths_885_mapping.py生成(概念详情页隐藏域clid，375概念约4分钟)，季度刷新(挂concept-mapping-check cron)。
- 主力口径(默认): 同花顺官方
- 概念板块日K历史(collectors/ths_board_hist.py): 直连
d.10jqka.com.cn/v4/line/bk_<885码>/01/<year>.js(hexin-v cookie, 与akshare同法生成), 不碰被风控的q.10jqka详情页, 375概念全量约2分钟零封禁(2026-10-12实测)。缓存cache/concept_amount_history.json(近70交易日成交额, git不提交), generate_matrix 前置 ensure_history_fresh 幂等刷新。用途: 板块量比=今日K线额/自身20日均额(时序自比, 免疫成分股数量/天生活跃度截面偏置)。口径坑: gnzjl流入+流出≈0.65×真实成交额, 与K线额不同口径, 量比统一用K线口径; gnzjl总额仅作离群校验(K线今日额<gnzjl总额×0.4→数据异常降级NaN)。 - 一级行业板块日K(同collector): 881码日K同一接口可拉(
bk_881xxx), 90行业约20秒。映射data/ths_industry_881_mapping.json(aksharestock_board_industry_name_ths()直接返回881码, 无需爬详情页; scripts/build_ths_industry_mapping.py 生成, 季度刷新), 缓存cache/industry_amount_history.json。用途: 点火雷达事件卡片板块量比标签(LLM标签是行业级, 行业881优先匹配, 概念885兜底; generate_ignition内 ensure_industry_history_fresh 幂等刷新)。 - 个股全市场资金流用新浪。
- 个股日K线(tencent_kline, industry_screener.py与daily_report.py各一份): 主源腾讯
web.ifzq.gtimg.cn fqkline(qfq前复权)，2026-10-13起备源新浪quotes.sina.cn CN_MarketDataService.getKLineData，腾讯WAF拦截(返回501/HTML)时自动切换。备源口径对齐: ①复权——新浪K线原始为不复权, 用因子接口finance.sina.com.cn/realstock/company/{symbol}/qfq.js做 raw/f 前复权还原(茅台500根对照东财qfq: 不复权误差3.71%→还原后0.38%; 因子失败退回不复权并打警告); ②volume——新浪单位为股, /100换手对齐腾讯(实测比值恰100)。验证脚本scripts/verify_kline_fallback.py。⚠勿扩散红线: 新浪K线只有volume(成交量)、没有成交额(元)——历史上"成交量趋势"曾误把volume当成交额酿成单位错误。所有需成交额的地方(TOP10/TOP50/板块总额等)严禁调用tencent_kline/sina_kline_fallback，成交额一律走腾讯实时qt.gtimg.cn index37(万)或同花顺K线。当前备源合法消费方: 点火雷达L3(分位/首放/形态)、fetch_stock_indicators(连涨/分位)、daily_report(calc_multi_day_change/技术指标)——全部只吃close/volume。 - 涨跌家数(collectors/breadth.py fetch_breadth): 新浪Market_Center.getHQNodeData全量翻页(hs_a~56页,约15秒)优先——2026-09-30与同花顺APP对照验证一致(涨2566/跌2824/平181 vs APP 2567/2824/170)；东财push2兜底(同日返回2393/2730与APP偏差大,口径存疑,且时好时坏)；腾讯getBoardRankList弃用(aStock板块仅4606只覆盖不全)。涨跌停用akshare涨停池(fetch_limit_stats)。同花顺无直接家数接口(zdfb页chameleon反爬,iwencai本机DNS不通)。plans/daily_report.py的fetch_market_breadth已委托collector,勿再重复实现。
- 同花顺/东财字段映射必须打印验证，不可假设。
- 服务器为 ARM(aarch64)，akshare 同花顺接口依赖 py_mini_racer 软链修复（venv 重装后需重建软链）。
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.
- 11d ago Changed · +2 lines · +321 tokens per session 3841bd917241
- 12d ago Changed · +3 lines · +775 tokens per session 5698c61d9035
- 16d ago Changed · +1 lines · +173 tokens per session 75d98c25e4fc
- 17d ago Changed · +9 lines · +552 tokens per session 116c9110fbb2
- 24d ago Changed · +1 lines · +196 tokens per session 98c8238adf94
- 25d ago Changed · +4 lines · +342 tokens per session fb735b8580d0
- 27d ago First seen · 32 lines · 792 tokens per session scan A 1416fd81ec96
stock-analysis-pro AGENTS.md is an instructions file published in the GitHub repository bobby1129/stock-analysis-pro (25 stars, last pushed 11d ago), licensed MIT. It adds 3,151 tokens to every session, about $0.0126 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-28.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.