What is a-share-strategy-library?

A stateful library for maintaining A-share strategy research, including market hypotheses, scenarios, daily reviews, holdings-based actions, and tradable stock ideas. A-shares are shares listed on mainland Chinese stock exchanges.

It imports user materials as hypotheses, checks them against public news and market evidence, updates daily entries, and expires or downgrades stale items.

It keeps research organized over time and prevents unverified or outdated ideas from being treated as current trading conclusions.

a-share-strategy-library — Skill for Codex by minguncle

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 minguncle/a-share-agent-skills --skill a-share-strategy-library

Clone the repo

git clone --depth 1 https://github.com/minguncle/a-share-agent-skills

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/minguncle/a-share-agent-skills/a-share-strategy-library/github.svg)](https://agentmods.dev/skills/minguncle/a-share-agent-skills/a-share-strategy-library)

Your own site

<a href="https://agentmods.dev/skills/minguncle/a-share-agent-skills/a-share-strategy-library"><img src="https://agentmods.dev/badge/skills/minguncle/a-share-agent-skills/a-share-strategy-library/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/minguncle/a-share-agent-skills/a-share-strategy-library"><img src="https://agentmods.dev/badge/skills/minguncle/a-share-agent-skills/a-share-strategy-library.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,322 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.

Model	Per session	Once invoked
Fable 5.1	$0.00101	$0.01322
Opus 5.5	$0.00040	$0.00529
Sonnet 5.5	$0.00020	$0.00264
Haiku 4.5	$0.00010	$0.00132

Measured 2mo ago against content hash 25dc48a60294, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

a-share-strategy-library 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 2mo 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.

skills/experimental/a-share-strategy-library/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use this skill when the task is not just “analyze today,” but “update the stateful system that governs today’s analysis.”

Experimental Status

This skill is workspace-oriented and stateful. It assumes the user has explicitly initialized and wants to maintain a local strategy_library/ directory. It is optional and should not be the default first install for new users.

Core Rule

Treat the strategy library as a state machine, not a notes folder.

Import user materials as high-weight hypotheses first
Do not upgrade user materials directly into trading conclusions
Require at least one public news/policy evidence item and one price/flow/sentiment evidence item before promoting a hypothesis
Expire or downgrade stale items instead of carrying them forward by habit

Default Workflow

1. Load The Right Layer

Read only the files needed for the task:

strategy_library/hypotheses/*.yaml: hypothesis state
strategy_library/cycles/*.yaml: active scenario priors
strategy_library/daily/YYYY-MM-DD.yaml: current daily entry
strategy_library/library_config.yaml: fixed defaults and output contract

Read references/maintenance-loop.md when the task requires the full update loop, status transitions, or filtering rules.

2. Import Or Update Hypotheses

If a companion maintenance script exists in the current workspace, use it for new bundles when a new material source arrives. Otherwise update the structured files manually while preserving schema consistency.

Allowed status progression:

unverified
partially_verified
verified
invalidated
expired

Do not skip directly from user material to verified unless public evidence is already present in the same turn.

3. Reweight Scenario Cards

Scenario cards in strategy_library/cycles/ are priors that must be reweighted with current evidence.

When updating weights:

state which scenario is primary now
separate 1-3d and 3-10d implications
lower weights when the scenario lacks fresh confirmation
do not let old macro narratives dominate after price and flow have stopped confirming them

Read the full file on GitHub · 153 lines

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.

2mo ago First seen · 153 lines · 101 tokens per session scan A 25dc48a60294

Subscribe to this mod's changes

a-share-strategy-library is a skill published in the GitHub repository minguncle/a-share-agent-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 101 tokens to every session and 1,322 once invoked, about $0.0004 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 2026-08-31.

Finance and fintech Research

a-share-strategy-library next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
a-share-strategy-libraryminguncle/a-share-agent-skills	Skill	2	6mo ago	MIT	A	101	Codex
sector-rotationHKUDS/Vibe-Trading	Skill	38k	yesterday	MIT	A	39	Claude Code, Codex
twitter-readerhimself65/finance-skills	Skill	3.5k	2d ago	MIT	A	110	Claude Code
strategy-pivot-designertradermonty/claude-trading-skills	Skill	3.7k	2d ago	MIT	A	28	Claude Code, Codex
energy-procurementhashgraph-online/awesome-codex-plugins	Skill	1.5k	yesterday	Apache-2.0	A	93	Claude Code, Codex
airdrop-hunting-guidenirholas/three.ws	Skill	269	yesterday	Apache-2.0	A	54	Claude Code, Codex
multi-expert-analyzerdigoal/blog	Skill	8.6k	2d ago	GPL-2.0	A	292	Codex