Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Teamnpx agentmods add skills/aaaaqwq/agi-super-team/coin-vp-scannerWrote 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/aaaaqwq/agi-super-team/coin-vp-scanner)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/coin-vp-scanner"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/coin-vp-scanner/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/aaaaqwq/agi-super-team/coin-vp-scanner"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/coin-vp-scanner.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 | $0.00000 | $0.01873 |
| Opus 5 | $0.00000 | $0.00937 |
| Sonnet 5 | $0.00000 | $0.00375 |
| Haiku 4.5 | $0.00000 | $0.00187 |
Grade A, and why
coin-vp-scanner 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 today.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚡ coin-vp-scanner — 量价能高杠杆短线突破扫描（skill）
项目代码：
~/projects/coin-vp-scanner/（scanner.py + 回测/规律/耗时 全套工具） 版本 v4 · 判定逻辑：确定性结构突破（非黑箱）· 目标：1-30min 吃到自适应小 TP 本 SKILL.md 是操作索引；报告模板见下方「六」。
⚠️ 别和
5minbtc混用 —— 两个都是交易 skill 但赌的不是同一件事。 本 skill = 抓"价格放量破位了"（全市场永续、结构规则、直接做合约）；5minbtc= 赌"市场定价错了"（单标的 BTC、5min K线、真 OFI 净流 vs 预测市场 token 价EV = p − P、仅 paper）。 完整对照表见 5minbtc SKILL.md 的「与 coin-vp-scanner 的分工」。 一句话选型：要抓突破 → 用本 skill；要赌错价 → 用 5minbtc。
触发
coin-vp / vp扫描 / 量价能 / 突破信号 / 扫币 / R2突破 / 短线币
一、是什么（一句话）
全量扫币安 USDT 永续，只报"量价能结构突破"的高确定性信号—— 放量 + 强实体 + 收盘破 1h 结构位 + 趋势同向，每个信号带完整判定链和交易参数。
二、快速开始
python3 ~/projects/coin-vp-scanner/scanner.py # 标准扫描 (默认 10m 币池, 12%风险)
python3 ~/projects/coin-vp-scanner/scanner.py --min-vol 5m --vol-min 1.5 --body-min 0.4 --risk 20
# 激进档: 更宽币池 + 更松门槛 + 20% 单笔风险
python3 ~/projects/coin-vp-scanner/scanner.py --risk 12 # 稳健档 (推荐默认)
三、确定性判定规则（全 ✓ 才算信号，逐条可复核）
- 放量：触发 K线 量能 ≥ 基线 × 门槛（默认 2x）
- 实体：|涨跌| ≥ 门槛（默认 0.5%）
- 结构破位（关键）：UP→收盘 破前 12 根(1h)高点；DOWN→破前低；且开盘未远离结构位
- 趋势同向：方向与 15m 趋势一致
- 少任何一条 → 丢弃，不做区间噪声
量能分析要点：巨量长阳在顶部 = 常是出货/诱多；安静放量干净破位 = 更可能是真吸筹。别只看放量大小，看"破位是否干净 + 1h 是否过热"。
四、交易参数铁律
止损距离 × 杠杆 ≤ 15% 本金（扫描默认按 12% 输出杠杆）
时间止损：进场 10min 未到 TP 也未止损 → 主动平（数据: 到TP者中位 5min, 前倾严重）
到 TP 耗时参考：0.3%→79% | 0.5%→67% | 0.7%→56% | 1.0%→47%（到TP率）
- 目标自适应：按 ATR5 定，别死等 1% 踏空（活泼币才有 1%，安静币给 0.3-0.5%）
- 1h 过热不追：1h 已涨/跌 >15% 的币谨慎（追顶风险）
- 相关信号只挑 1-2 个：全市场同向齐破 = 一个行情，不是 N 个机会
五、工作流（每单走完整闭环）
① 扫描 → ② 按下方模板出报告(奖牌排序) → ③ 挑 1-2 个(1h同向+不过热+破位干净)
④ 填 REPORT_TEMPLATE.md 存档到 reports/ → ⑤ 30min 回填结果(到TP/止损/平推)
⑥ 攒样本 → 周度统计真实命中率（回测 60-82%，活体验证 ~50%，以活体为准）
六、输出报告模板（统一交易卡格式 · 扫描报告与交易卡同一格式）
扫描报告 = 一排"统一交易卡" + 奖牌排序；选定某一单 = 同一张卡存档进 reports/ 并回填结果。 扫描报告与交易卡共用同一字段集，字段顺序固定如下。
🥇 SYMBOL DIR —— 一句理由（如：1h同向+干净破位, 唯一想动的话做它）
入场 x.xxx | TP x.xxx (+x.x%) | SL x.xxx (-x.x%)
杠杆 Nx → 目标 +x.x% / 止损亏 -x.x% | 现价x.xxx | ATRx.xx% | 量能x.x | 资金费率±x.xx%
趋势: 15m↑x.xx% 1h↑x.xx% 24h+x.x% | 参考命中 xx%
时间: 到TP中位~5min → 10min未到TP也未止损就平(不傻等)
判定链: 放量x.x✓ → 实体x.xx%✓ → 破位(位价)越过x.xx%✓ → 15m同向✓
🥈 SYMBOL DIR —— 次选（一句话）
（同上格式）
⚠️ SYMBOL —— 不建议追
• 理由1（过热/逆势/破位薄）
What ships with it
14 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.
- backtest-findings.md 1.7 KB
- backtest.py 9.9 KB runs code
- breakout_confidence.py 4.7 KB runs code
- config.py 1.4 KB runs code
- pattern_1pct.py 7.1 KB runs code
- README.md 2.3 KB
- REPORT_TEMPLATE.md 3.4 KB
- reports/0GUSDT-2026-09-02-19-28.md 1.6 KB
- reports/2026-09-03-00-01-scan.md 1.3 KB
- reports/2026-09-03-00-19-scan.md 1.5 KB
- scanner.py 11 KB runs code
- time_to_tp.py 3.7 KB runs code
- tp_sizing.py 4.9 KB runs code
- validate_breakout.py 5.1 KB runs code
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.
- today Changed · +6 lines 6fbc39c9fa3f
- 6d ago First seen · 92 lines · 0 tokens per session scan A 5131ca84953b
coin-vp-scanner is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,873 tokens. 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 2026-09-05.
Other skills, from other repositories
modeling-unit-economics
Use when modeling unit economics is required during product work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
generated_skill_1775724185480
Parse XBRL financial documents and extract key taxonomy elements into structured JSON format.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
blocknative-openapi-skill
Operate Blocknative gas intelligence APIs through UXC with a curated OpenAPI schema, API-key auth, and read-first guardrails.
prompt-tuning
Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.
ai-financial-analysis-stock-research
AI financial analysis and stock research powered by CellCog. Stock analysis, valuation models, portfolio optimization, earnings breakdowns, investment research, financial statements, tax planning, and DCF modeling. Wall Street-grade deliverables — interactive dashboards, PDF rep…