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 skills add AoleiC/ai-mock-trade --skill journalgit clone --depth 1 https://github.com/AoleiC/ai-mock-tradeWrote 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/skills/aoleic/ai-mock-trade/journal)<a href="https://agentmods.dev/skills/aoleic/ai-mock-trade/journal"><img src="https://agentmods.dev/badge/skills/aoleic/ai-mock-trade/journal/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/skills/aoleic/ai-mock-trade/journal"><img src="https://agentmods.dev/badge/skills/aoleic/ai-mock-trade/journal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00100 | $0.01820 |
| Opus 5.5 | $0.00040 | $0.00728 |
| Sonnet 5.5 | $0.00020 | $0.00364 |
| Haiku 4.5 | $0.00010 | $0.00182 |
Grade A, and why
journal 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
柚子 AI Skill — 本地状态读写
柚子 AI agent 的本地状态持久化入口。负责读写 data/regime-state.json 与 memory/dynamic-strategy.md，与 mock（接口调用：行情 / 交易 / 总结上报）物理隔离、各自独立 cli。盯盘 / 复盘总结全文（data/watch-summary-{date}.md / data/review-summary-{date}.md）由调度器从 run log 自动归档，不经本 skill（总纲 §7.1 / §10.1）。
agent 调用本 skill 的唯一方式是
skills/journal/cli.py（见下方「CLI 调用方式」），禁止编写临时 .py 脚本去 import skills.journal——临时脚本写到项目工作目录之外会触发external_directory权限拦截，整轮中断。
函数签名、入参、返回字段的权威定义在 journal.py 的 docstring，本文件只做索引。
字段结构、枚举值、默认值——请直接读对应函数的 docstring。
工作区根 = 项目根目录（脚本所在的最外层目录，下载解压即得、可任意重命名）。
CLI 调用方式（agent 唯一入口）
skills/journal/cli.py 是 journal skill 的通用方法调用器：一行命令调用 journal 模块任意方法，结果以 JSON 输出到 stdout。
python skills/journal/cli.py <method> [位置参数...] [--key value ...]
python skills/journal/cli.py --list # 列出全部可用方法
python skills/journal/cli.py --help # 打印用法
注意：本 skill 不带
module.前缀（mock 是market.get_summary，journal 是read_regime_state），因为 journal skill 单模块。
高频调用：
| 用途 | 命令 |
|---|---|
| 当日生效阶段（盘中第 0 步） | cli.py read_regime_state --trade_date 2026-09-09 |
| 当前动态策略 | cli.py read_dynamic_strategy |
写操作（参数在调用前校验，未知参数会报错不会误写）：
python skills/journal/cli.py write_dynamic_strategy --content '...'
python skills/journal/cli.py regime_rebuild --raw @raw.json --write_back true --before_date 2026-09-09
参数与输出约定：
- 类型按方法签名注解自动转换：dict/list 走 JSON（支持
@文件路径引用）；具名参数支持--key value与--key=value - 成功：方法返回值原样 JSON 输出；返回 None 时输出
{"ok": true} - 失败：输出结构化错误 JSON（
{code, error, method, ...}）+ 退出码非零。code: 400参数错、404方法不存在、500执行异常
快速开始
from skills.journal.journal import (
read_regime_state, regime_advance, regime_rebuild,
read_dynamic_strategy, write_dynamic_strategy,
)
认证
本 skill 为纯本地文件读写，无需认证，不依赖 cookie / secret_key。
总结上报（HTTP 接口）见 mock skill 的 report.submit_summary。
一、市场阶段状态机（裁决层执行权威）
读写 data/regime-state.json（滚动单文件，原子覆盖写，不按日清理）。转移规则人审表述见 memory/strategies/00-regime-machine.md，执行唯一权威是本节三个方法，agent 只读输出、禁止手工推演转移表。
What ships with it
3 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.
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.
- 1mo ago Changed 966422061d7e
- 1mo ago Changed 0a0d6d6ab5cd
- 1mo ago Changed · -75 lines · -5 tokens per session ecbf068640b5
- 1mo ago Changed · +25 lines a700923cbd7c
- 1mo ago First seen · 179 lines · 105 tokens per session scan A 07549428de95
journal is a skill published in the GitHub repository AoleiC/ai-mock-trade (29 stars, last pushed 4d ago), licensed MIT. It adds 100 tokens to every session and 1,820 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 2026-08-30.
Other skills, from other repositories
iflytek-ocr-invoice
An image-reading tool that extracts structured information from Chinese invoices, receipts, bills, and tickets. OCR means turning text in a photo or scan into computer-readable data.
tushare-finance
A Python connection to Tushare Pro, a service that provides data about Chinese financial markets through many data interfaces.
stock-analysis
A stock-research tool for analysing individual companies and their share prices. It retrieves current market data and uses indicators such as MACD and RSI to study trends and possible price levels.
antinet-four-color-cards
A document-analysis skill that organises findings into four card types: facts, explanations, risks, and actions. It is intended for financial reports and legal documents.
okx-sentiment-tracker
Use this skill when the user asks about: 'any crypto news', 'latest news', 'market update', 'daily briefing', 'BTC news', 'ETH news', 'news on SOL', 'search SEC ETF', 'regulation news', 'Bitcoin halving', 'is BTC bullish or bearish', 'coin sentiment', 'sentiment trend', 'trending coins', 'top bullish coins', 'bearish…
okx-cex-smartmoney
A command-line tool for analysing prominent traders on OKX, including leaderboard rankings, positions, trade records, combined signals, and signal history. “Smart money” here means traders identified by the service as notable or high-performing.