What is a-fund-monitor?

A monitor for Chinese stock-fund values that reports intraday estimates and published closing net values through Telegram on a schedule.

Running fund-value checks manually or on weekday cron schedules, retrieving estimates or closing net values, marking delayed QDII funds, and sending results to a Telegram chat.

It separates estimated daytime values from official later values and accounts for delayed publication, helping avoid reporting stale closing data.

a-fund-monitor — Skill for Claude Code by aAAaqwq

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 aAAaqwq/AGI-Super-Team --skill a-fund-monitor

Clone the repo

git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team

Made for: Claude Code.

Or install agi-super-team, the plugin that ships this one along with the rest of its 194 skills, 1 agent.

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/aaaaqwq/agi-super-team/a-fund-monitor/github.svg)](https://agentmods.dev/skills/aaaaqwq/agi-super-team/a-fund-monitor)

Your own site

<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/a-fund-monitor"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/a-fund-monitor/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/aaaaqwq/agi-super-team/a-fund-monitor"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/a-fund-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,387 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00033	$0.01387
Opus 5	$0.00016	$0.00694
Sonnet 5	$0.00007	$0.00277
Haiku 4.5	$0.00003	$0.00139

Measured 12d ago against content hash 301e3b3978f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

a-fund-monitor 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 3 executable files (scripts/fund_estimate.sh, scripts/fund_monitor.py, scripts/fund_nav.sh), 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/a-fund-monitor/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A股基金监控

A股基金净值监控，支持盘中实时估值和盘后实际净值，通过 OpenClaw cron 推送到 Telegram 私聊。

架构

fund_monitor.py (纯 Python，无外部依赖)
  ├── estimate 模式 → fundgz.1234567.com.cn (盘中实时估值)
  └── nav 模式      → api.fund.eastmoney.com/f10/lsjz (收盘净值)

OpenClaw cron (isolated agentTurn)
  ├── 09:30-19:00 → estimate 模式（收盘后先推估值，净值当晚才公布）
  └── 19:00 之后  → nav 模式（收盘实际净值）
  └── stdout → delivery announce → Telegram 私聊

关键路径: skills/a-fund-monitor/scripts/（本仓库）

手动执行

# 盘中估值（控制台输出）
python3 scripts/fund_monitor.py estimate

# 收盘净值（控制台输出）
python3 scripts/fund_monitor.py nav

Cron 定时任务

OpenClaw cron，使用 Asia/Shanghai 时区。

北京时间	模式	数据源
10:30	盘中估值	fundgz 接口
12:30	盘中估值	同上
14:30	盘中估值	同上
22:00	收盘净值	lsjz 接口（避开 20:30 数据未发布，QDII 滞后 1 天）

合并为 1 个 cron job: 04a185b2-f8ae-454e-b454-bc1944ca5c00

Cron:     30 10,12,14,22 * * 1-5 (Asia/Shanghai)
Runtime:  isolated agentTurn (changqing)
Model:    minimax/MiniMax-M3 (fallback: deepseek/deepseek-v4-pro)
Timeout:  300s
Delivery: announce → telegram:8518085684 (Daniel 私聊)

v2.1.1 (2026-06-22) 调整：20:30 → 22:00。多数基金 21:00-22:30 才陆续发布 NAV，旧时间会拿到 4-5 天前的旧数据。同时叠加「今日过滤 + QDII 标记 + HTTP 重试」三重防护。

模式判断逻辑

北京时间 ∈ [09:30, 19:00) → estimate
北京时间 ∈ [19:00, 次日)  → nav

投递目标: telegram:8518085684（Daniel Li 私聊），accountId changqing

添加/删除基金

编辑 fund_monitor.py 中的 FUNDS 列表：

FUNDS = [
    ("003304", "前海开源核心资源A"),
    # ... 添加 ("代码", "简称")
]

API 参考

详见 references/eastmoney-api.md。

变更记录

日期	版本	变更
2026-06-22	v2.1.1	20:30 → 22:00 避免旧数据；脚本升级为「今日过滤 + QDII 标记 🌏 + HTTP 重试」；cron model 改为 minimax primary（避开 glm-5.1 限流）；timeout 提到 300s
2026-05-25	v2.1.0	4 个 cron 合并为 1 个(逗号分隔小时)；从 Hermes 迁移到 OpenClaw cron；推送目标改为 Daniel 私聊(8518085684)；超时提至 180s；19:00 前走估值避免陈旧数据
2026-05-22	v2.0.0	初始 Hermes cron 版本

Pitfalls

超时：14 只基金顺序请求，API 偶发慢速，cron timeout 设为 180s。
NAV 涨跌幅字段：东方财富 lsjz API 的涨跌幅字段是 JZZZL（净值增长率），不是 NAVCHGRT。
估值 API 返回 JSONP：fundgz.1234567.com.cn 返回 jsonpgz({...}); 格式，需正则提取 JSON。
HTTP 请求头：两个 API 都需要 Referer: https://fund.eastmoney.com/ 和 User-Agent，否则可能 403。
NAV 发布时间不均：多数基金 21:00-22:30 才陆续发布 NAV（QDII 滞后 1 天），脚本已升级为「今日过滤 + QDII 标记 🌏 + HTTP 重试 2 次」。未发布基金显示「⏳ 待发布 (上次: 日期)」，不混进平均。
早期 20:30 触发坑：v2.1.0 之前用 20:30 跑 nav 会拿到 4-5 天前的旧数据（脚本只取 items[0] 不过滤日期），已升级为今日过滤。
QDII 基金估值时间：广发纳斯达克100联接的估值时间显示为 04:00（美股收盘时间），非 A 股 15:00。
周末/节假日：cron 1-5 仅排除周末，中国法定节假日仍会触发（产出的是上一交易日数据）。

Read the full file on GitHub · 105 lines

Files

What ships with it

4 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.

12d ago First seen · 105 lines · 33 tokens per session scan A 301e3b3978f7

Subscribe to this mod's changes

a-fund-monitor is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (92 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,387 once invoked, about $0.0002 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.

Analytics and metrics Claude Code Finance and fintech agent-orchestration agent-skills ai-agent-framework ai-agents developer-tools

a-fund-monitor