report-cli: Skill for Claude Code

.claude/skills/report-cli-simple/SKILL.md

report-cli-simple is a skill for Claude Code from manymore13/report-cli. It costs 44 tokens per session (1,377 once invoked), scanned A, original, MIT.

A command-line tool for finding, viewing, filtering, exporting, and downloading research reports. It covers industry, company, strategy, macroeconomic, and morning reports; a macroeconomic report studies broad conditions such as inflation or growth.

In plain words
What is it for?
Listing industries, searching reports by type, date, industry, or stock code, exporting search results to CSV, and downloading selected reports as PDFs.
Why use it?
It separates searching for reports from downloading their PDF files, reducing the risk of downloading more files than intended. It also provides rules for selecting a specific result before downloading it.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is manymore13/report-cli's own configuration. It tells Claude Code how to work on report-cli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything report-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to manymore13/report-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/manymore13/report-cli/master/.claude/skills/report-cli-simple/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/manymore13/report-cli

Made for: Claude Code.

Wrote 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.

agentmods badge for report-cli-simple

README.md
[![agentmods](https://agentmods.dev/badge/skills/manymore13/report-cli/report-cli-simple/github.svg)](https://agentmods.dev/skills/manymore13/report-cli/report-cli-simple)
Your own site
<a href="https://agentmods.dev/skills/manymore13/report-cli/report-cli-simple"><img src="https://agentmods.dev/badge/skills/manymore13/report-cli/report-cli-simple/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.

agentmods 80×15 button for report-cli-simple

Your own site · 80×15
<a href="https://agentmods.dev/skills/manymore13/report-cli/report-cli-simple"><img src="https://agentmods.dev/badge/skills/manymore13/report-cli/report-cli-simple.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,377 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.01377
Opus 5.5 $0.00018 $0.00551
Sonnet 5.5 $0.00009 $0.00275
Haiku 4.5 $0.00004 $0.00138

Measured 1mo ago against content hash f66accd93dd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

report-cli-simple 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 1mo 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.

.claude/skills/report-cli-simple/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

研报工具

安装

pip install report-cli

重要:先理解这两个命令的区别

用户意图 用这个命令 说明
查看、搜索、查询、了解、有哪些 report query 只查看列表,不下载文件
下载、保存、下载PDF report download 下载 PDF 文件到本地

规则:除非用户明确说"下载"或"保存",否则一律用 report query。

命令

列出行业

report list              # 所有行业
report list -s 游戏      # 搜索行业

查询研报

# 行业研报
report q -i 1046 -s 5                    # 游戏行业,5条
report q -i 1046 --begin 2025-01-01      # 按日期筛选

# 策略报告
report q -t strategy -s 10

# 宏观研究
report q -t macro -s 10

# 券商晨报
report q -t morning -s 10

# 个股研报
report q -t stock -c 600519 -s 5         # 茅台
report q -t stock -c 000001 -s 5         # 平安银行

# 导出CSV
report q -i 1046 --save-csv

下载PDF

report d -i 1046 -s 5 -o ./reports       # 下载游戏行业5篇
report d -i 1046 -s 5 -n 5 -o ./reports  # 查5篇,只下载第5篇
report d -i 1046 -n 1,3,5 -o ./reports   # 只下载第1、3、5篇
report d -t strategy -s 5 -o ./reports   # 下载策略报告
report d -t stock -c 600519 -o ./reports # 下载茅台研报

如果用户说"下载第X篇",必须用 -n X 参数,不能全部下载。先 query 确认序号,再 download -n。

更新

report update

参数速查

参数 说明 示例
-t 类型: industry/stock/strategy/macro/morning -t strategy
-i 行业代码 -i 1046
-c 股票代码 -c 600519
-s 数量 -s 10
-p 页码 -p 2
-o 输出目录 -o ./reports
--begin 开始日期 YYYY-MM-DD --begin 2025-01-01
--end 结束日期 YYYY-MM-DD --end 2025-12-31
-n 指定下载第几条 -n 5 或 -n 1,3
--save-csv 保存为CSV 加在 query 命令后

行业代码

代码 行业 代码 行业
422 物流 1033 电池
428 电力 1036 半导体
448 通信设备 1037 消费电子
451 房地产开发 1038 光学光电子
457 电网设备 1040 中药Ⅱ
459 元件 1042 医药商业
465 化学制药 1044 生物制品
473 证券Ⅱ 1045 房地产服务
474 保险Ⅱ 1046 游戏Ⅱ
475 银行Ⅱ 1225 服装家纺
481 汽车零部件 1231 航空装备Ⅱ
482 一般零售 1232 航天装备Ⅱ
538 化学制品 1238 IT服务Ⅱ
545 通用设备 1239 白色家电
727 医疗服务 1241 黑色家电
736 通信服务 1250 煤炭开采
737 软件开发 1252 化妆品
738 多元金融 1253 医疗美容
910 专用设备 1257 农业综合Ⅱ
1031 光伏设备 1258 饲料
1032 风电设备 1259 养殖业
1263 摩托车及其他 1277 白酒Ⅱ
1267 造纸 1280 食品加工
1271 酒店餐饮 1281 休闲食品
1282 饮料乳品 1287 工业金属

Read the full file on GitHub · 139 lines

Changes

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.

  1. 1mo ago First seen · 139 lines · 44 tokens per session scan A f66accd93dd5

Subscribe to this mod's changes

report-cli-simple is a skill published in the GitHub repository manymore13/report-cli (56 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 1,377 once invoked, about $0.0002 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 2026-08-30.