screener

screener is a skill for Claude Code, Codex from ZICXR/A-Stock-Skills. It costs 115 tokens per session (689 once invoked), scanned A, original, MIT.

A Chinese-language A-share stock screener that combines built-in technical signals with custom financial and price conditions. Technical signals are rule-based patterns in market data, while custom conditions can use fields such as PE, PB, market value, or ROE.

In plain words
What is it for?
Use it to filter stocks with signals such as MACD, moving-average position, volume changes, RSI, KDJ, new highs, or limit-ups, and combine them with conditions using AND or OR. It also includes value, growth, small-cap, and momentum strategy templates.
Why use it?
It removes the need to inspect a large list of stocks one by one for the same combinations of signals and conditions. Saved YAML strategies also let users reuse screening rules.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to filter stocks with signals such as MACD, moving-average position, volume changes, RSI, KDJ, new highs, or limit-ups, and combine them with conditions using AND or OR. It also includes value, growth, small-cap, and momentum strategy templates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zicxr/a-stock-skills/screener
Install

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.

Any agent
npx skills add ZICXR/A-Stock-Skills --skill screener
Clone the repo
git clone --depth 1 https://github.com/ZICXR/A-Stock-Skills

Made for: Claude Code, Codex.

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 screener

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/zicxr/a-stock-skills/screener"><img src="https://agentmods.dev/badge/skills/zicxr/a-stock-skills/screener.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 689 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 $0.00115 $0.00689
Opus 5 $0.00057 $0.00345
Sonnet 5 $0.00023 $0.00138
Haiku 4.5 $0.00012 $0.00069

Measured 12d ago against content hash 126e434154fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

screener 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (main.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/05-quant/screener/SKILL.md · 82 lines

What it actually says

A 股股票筛选器 Skill (统一版)

何时使用

  • 用户需要技术信号筛选
  • 用户需要自定义条件筛选
  • 用户需要多条件 AND/OR 组合
  • 用户需要保存常用策略

提供能力

  • 内置信号: 12 种 (ma_cross/macd/above_ma/volume/rsi/kdj 等)
  • 自定义条件: 11 字段 × 9 操作符
  • AND/OR 组合
  • 策略保存: YAML 文件复用

使用方式

# 内置信号
python main.py screen --signals "macd_golden,above_ma20" --mode and

# 自定义条件
python main.py screen --where "pe<20" --where "roe>15"

# 组合
python main.py screen --where "pe<20" --signals "above_ma20,volume_break"

# 内置策略
python main.py screen --strategy value

# 列出策略
python main.py list

Python API

from skills.05-quant.screener.main import screen

# 自定义 + 信号
result = screen(
    conditions=[{"field": "pe", "op": "<", "value": 20}],
    signals=["macd_golden", "above_ma20"],
    mode="and",
    top_n=30,
)

内置信号

ma_cross / macd_golden / macd_death / above_ma20 / above_ma60 / volume_break / volume_shrink / rsi_oversold / rsi_overbought / kdj_golden / new_high_60 / limit_up

字段

pe / pb / ps / total_mv / circ_mv / roe / pct_change / turnover / volume_ratio / price / change_5d / change_20d

操作符

> < >= <= == != between(a,b) in not in

依赖

akshare>=1.12.0
pandas>=1.5.0
numpy>=1.22.0
pyyaml>=5.4.0

合并历史

本 Skill 由原 signal-screener + stock-screener-custom 合并而成, 节省 1 个 Skill。

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 82 lines · 115 tokens per session scan A 126e434154fc

Subscribe to this mod's changes

screener is a skill published in the GitHub repository ZICXR/A-Stock-Skills (25 stars, last pushed 2mo ago), licensed MIT. It adds 115 tokens to every session and 689 once invoked, about $0.0006 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 2026-08-30.