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 agentpit-io/hunter-community --skill lhb_analyzergit clone --depth 1 https://github.com/agentpit-io/hunter-communityWrote 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/agentpit-io/hunter-community/lhb_analyzer)<a href="https://agentmods.dev/skills/agentpit-io/hunter-community/lhb_analyzer"><img src="https://agentmods.dev/badge/skills/agentpit-io/hunter-community/lhb_analyzer/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/agentpit-io/hunter-community/lhb_analyzer"><img src="https://agentmods.dev/badge/skills/agentpit-io/hunter-community/lhb_analyzer.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 | $0.00059 | $0.01198 |
| Opus 5.5 | $0.00024 | $0.00479 |
| Sonnet 5.5 | $0.00012 | $0.00240 |
| Haiku 4.5 | $0.00006 | $0.00120 |
Grade A, and why
lhb_analyzer 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 6d 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.
What it actually says
龙虎榜深度分析(券商数据信封 & 三栏证据适配版)
一、数据流(已接入券商只读 MCP 与统一数据信封)
- 取数与同会话复用:
- 若同会话上下文已有当日
mcp__broker_market__get_quote或mcp__uzi__stock_deep_analysis快照,优先复用。 - 调用
mcp__broker_market__get_quote、mcp__broker_market__get_orderbook获取当日收盘价、涨跌停价、换手率、成交额与五档盘口状态。 - 调用
mcp__broker_disclosure__search_announcements与mcp__uzi__stock_deep_analysis获取交易异常波动公告与龙虎榜前五大买卖席位原始数据。
- 若同会话上下文已有当日
- 信封时间戳与缺失值校验:
- 核验
BrokerDataEnvelope的as_of(行情时间)与published_at(榜单/公告发布时间),严禁拿抓取时间(retrieved_at)冒充上榜日期。 - 若某股票当日未上龙虎榜或席位数据缺失(
null),直接如实告知“当日无龙虎榜披露数据(—)”,严禁编造席位名称或买卖金额。
- 核验
- 游资与机构席位识别:
- 对照客观席位百科(机构专用、沪深股通专用、知名游资常用营业部等)进行标签化,明确区分“营业部历史风格参考”与“当日真实买卖净额”。
- 博弈结构与封板质量判断:
- 核算买五合计占总成交比例、卖五合计占比、净买入额,判断属于机构合力、一家独大还是游资对倒混战。
二、强制三栏证据输出格式
报告必须包含以下三栏结构:
- 【已核实事实】:
- 标注
[来源:<provider> · 上榜/行情时间:<as_of>]; - 逐项列出真实涨跌幅、换手率、成交额、前五大买入/卖出席位名称及精确买卖金额、净额。
- 标注
- 【逻辑推断】:
- 基于席位结构推导的多空力量对比(如机构净买入 vs 游资一日游席位占比)、筹码集中度与次日溢价压力推演。
- 【待核实问题】:
- 营业部席位背后是否为同一资金方(公开数据无法 100% 穿透确认)、异常波动公告中公司是否提示基本面风险、次日集合竞价承接力度待观察项。
三、合规底线
- 所有席位买卖金额与占比均以工具返回真值为准,严禁心算捏造。
- 严禁输出“跟着游资必涨”“明日稳封涨停”等违规诱导话术。
参数
本技能的入参是股票(代码或名称都可以)。用户这次给的是:
$ARGUMENTS
参数为空时,先问清楚要看哪只标的再开工,不要随便挑一只演示。
工具名对照
上面正文提到的工具,在 AtomCode 里的真名是:
| 正文里的写法 | 实际要调的工具 |
|---|---|
broker_disclosure_search_announcements |
mcp__broker_disclosure__search_announcements |
broker_market_get_orderbook |
mcp__broker_market__get_orderbook |
uzi_stock_deep_analysis |
mcp__uzi__stock_deep_analysis |
broker_market_get_quote |
mcp__broker_market__get_quote |
按右边那一列调。 左边是 HunterCode opencode 版的命名,这套发行版里不存在。
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.
- 6d ago Changed · +29 lines · +24 tokens per session 3754e272acc9
- 7d ago Changed · +25 lines ee93b3013865
- 2mo ago First seen · 25 lines · 35 tokens per session scan A 465b375b4702
lhb_analyzer is a skill published in the GitHub repository agentpit-io/hunter-community (617 stars, last pushed 4d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,198 once invoked, about $0.0002 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.
lhb_analyzer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lhb_analyzeragentpit-io/hunter-community | Skill | 617 | 4d ago | Apache-2.0 | A | 59 | Claude Code |
| stripe-skillzeenie-ai/OpenCompany | Skill | 1.1k | yesterday | MIT | A | 56 | Claude Code |
| dodo-payments-skillzeenie-ai/OpenCompany | Skill | 1.1k | yesterday | MIT | A | 69 | Claude Code |
| biltborski/travel-hacking-toolkit | Skill | 1.0k | 4d ago | MIT | A | 44 | Claude Code |
| amex-travelborski/travel-hacking-toolkit | Skill | 1.0k | 4d ago | MIT | A | 47 | Claude Code |
| chase-travelborski/travel-hacking-toolkit | Skill | 1.0k | 4d ago | MIT | A | 44 | Claude Code |
| compare-flightsborski/travel-hacking-toolkit | Skill | 1.0k | 4d ago | MIT | A | 46 | Claude Code |