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 instructions/minguncle/a-share-agent-skills/agents-mdgit clone --depth 1 https://github.com/minguncle/a-share-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/instructions/minguncle/a-share-agent-skills/agents-md)<a href="https://agentmods.dev/instructions/minguncle/a-share-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/minguncle/a-share-agent-skills/agents-md.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 5.1 | $0.01585 | $0.01585 |
| Opus 5 | $0.00792 | $0.00792 |
| Sonnet 5 | $0.00317 | $0.00317 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade A, and why
a-share-agent-skills AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
中文：本项目仅用于投资研究 workflow、信息整理与教育演示，不构成任何证券、期货、基金或其他金融产品的投资建议，不构成个性化荐股、投顾服务或收益承诺，也不用于自动下单。用户应自行核验数据并独立承担决策责任。
English: This project is for investment research workflow, information organization, and educational use only. It is not investment advice, not personalized stock recommendation, not advisory service, not return guarantee, and not intended for automated trading. Users must verify data independently and are solely responsible for their decisions.
Repository role
This repository packages A-share research workflow skills.
- Base usage starts from public pages, public market data pages, local file inputs, and common browsing or screenshot capabilities.
- Facts, inference, and data gaps must be separated in outputs.
- The repository is organized for standard folder-based skill runtimes.
coreis stateless by default. Stateful persistence is optional and isolated inexperimental.
Repository map
skills/core/
Stateless entry, market rebuild, material intake, portfolio calibration, action routing, and observation loops.skills/enhanced/
Deeper review, report scan, event mapping, source health checks, direct portfolio triage, and tradable candidate selection.skills/experimental/
Optional stateful layer for rolling strategy files and watchlists.docs/
Shared policies for source handling, main-board filtering, output contracts, and risk language.examples/
Example prompts and expected output shapes.
Dependency classes
Use dependency classes instead of runtime-specific connector names.
| Class | Meaning |
|---|---|
public_web_pages |
Public finance, quote, news, and report pages |
public_market_endpoints |
Public market or ranking endpoints used without paid credentials |
browser_automation |
Page loading, DOM extraction, screenshots, and fallback browsing |
local_text_input |
User-provided notes, transcripts, and prompt constraints |
local_image_input |
Holdings screenshots or local image files |
workspace_state |
Rolling files, daily entries, and watchlists stored in the workspace |
model_side_reasoning |
Model-native synthesis, ranking, and output formatting |
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 · 103 lines · 1,585 tokens per session scan A c94b4b080dba
a-share-agent-skills AGENTS.md is an instructions file published in the GitHub repository minguncle/a-share-agent-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,585 tokens to every session, about $0.0079 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 2026-08-31.
Other instructions, from other repositories
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
LLM-TradeBot copilot-instructions.md
Copilot instructions for EthanAlgoX/LLM-TradeBot, covering repository instructions, core rules, validation and ai asset governance.
Convertible-Bond-Pricing-Research CLAUDE.md
Instructions for ericxuzhesheng/Convertible-Bond-Pricing-Research, covering claude.md — convertible bond pricing research, current published state and routine commands.
bukio-cli AGENTS.md
AGENTS.md instructions for erikvankempen/bukio-cli, covering agents.md — bukio-cli agent manual, 1. house rules (non-negotiable), 2. environment, 3. command quick reference and 3.1 jurisdiction profiles (16 markets).
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.