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 aAAaqwq/AGI-Super-Team --skill bb-scalpergit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/bb-scalper)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/bb-scalper"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/bb-scalper/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/bb-scalper"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/bb-scalper.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 | $0.00159 | $0.04318 |
| Opus 5 | $0.00079 | $0.02159 |
| Sonnet 5 | $0.00032 | $0.00864 |
| Haiku 4.5 | $0.00016 | $0.00432 |
Grade A, and why
bb-scalper 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎯 BB 双向套利策略 — 完整策略文档
版本: v2.0 三重过滤 | 更新: 2026-08-11 定位: 加密合约 10x 杠杆双向套利 Skill 适配币种: USDT 永续合约（主流优先）
零、一句话说清楚
布林带收窄 = 横盘震荡 → 在下轨买、上轨卖；在上轨卖、下轨买。 不赌方向，只吃区间振荡的统计优势。
一、策略直觉：硬币在碗里滚
想象一个碗——左边是下轨、右边是上轨。硬币在里面滚来滚去：
上轨 ═══════════ 🔴 做空入场 ────
│ │
│ 价格在碗里来回弹 │
│ │
下轨 ═══════════ 🟢 做多入场 ─────
做多逻辑：硬币滚到碗左边（%B < 0.15）→ 大概率弹回去 → 买入，等它滚到右边再卖
做空逻辑：硬币滚到碗右边（%B > 0.85）→ 大概率弹回去 → 卖出，等它滚到左边再买
但市场的碗会变形——有时变窄（没空间赚）、有时倾斜（趋势中不能做）。所以需要三重过滤器确认碗是稳定平的。
二、核心数学：为什么「轨对轨」是唯一解
❌ 错误方案：止盈放中轨（我们踩的第一个坑）
做多: 入场=下轨 → 止盈=中轨 → 收益=1σ
止损=下轨下面 → 风险=1σ + 缓冲
RR = 1σ / (1σ + 0.15%) < 1 ← 永远亏多赚少！
扫了 20 个币，15 个在震荡，RR 没一个超过 1.1。 数学死结，不是参数问题。
✅ 正确方案：轨对轨（解法一）
做多: 入场=下轨 → 止盈=上轨 → 收益=2σ
止损=下轨外 0.15% → 风险 ≈ 1σ + 0.15%
RR = 2σ / (1σ + 0.15%) ≈ 2:1 到 4:1 ✅
一句话：止盈必须放到对侧轨道——吃整个区间，而不是只吃到中轨。
三、三重过滤器（v2.0 核心）
🔴 过滤器一：趋势过滤
检查：1h K 线的布林带中轨斜率
做多: 1h 中轨不能明显下行（斜率 > -0.06%）
做空: 1h 中轨不能明显上行（斜率 < +0.06%）
斜率 < 0.03% = 走平 ✅ 最优
斜率 0.03%-0.06% = 弱趋势，顺方向可以做
斜率 > 0.06% = 明确趋势，禁止逆势
为什么：碗底在下陷 → 硬币碰到底不会弹 → 假突破扫止损。趋势过滤就是确认碗是平放的。
实际效果：刚才扫码，ETH/SOL/BTC/INJ 四个币做空信号全被「1h 中轨上行」拦下——这些恰好是 v1.0 里连续止损 6-8 根的元凶。
🟡 过滤器二：RSI 确认
检查：价格是否已经超买/超卖
做多: RSI < 55 才做（不在高位接盘）
RSI 30-45 加分（超卖反弹概率大）
做空: RSI > 45 才做（不在低位砸盘）
RSI 55-70 加分（超买回落概率大）
直觉：下轨 + RSI 70 = 趋势刚启动、还会继续跌，买就是接飞刀。
🟢 过滤器三：BB 甜区
检查：布林带宽度是否合适
< 0.8%: 太窄 → 10x 利润不够覆盖滑点+手续费 → 跳过
0.8-2.5%: 甜区 → 可以做
> 2.5%: 太宽 → 不是真横盘，是波动行情 → 跳过
各币宽度速查：
| 宽度 | 币种例子 | 判断 |
|---|---|---|
| 0.71% | XRP | ❌ 太窄 |
| 0.87% | BTC | ⚠️ 刚够线 |
| 0.88% | AVAX | ✅ 甜区 |
| 1.13% | NEAR | ✅ 甜区中心 |
| 2.75% | ATOM | ❌ 太宽 |
| 47.5% | TUT | ❌ 崩溃行情 |
四、动态宽度适配（🎯 进阶）
当前固定甜区 0.8-2.5%。但能否根据 BB 宽度动态调整而非一刀切？
分析
BB宽度 1%: 10x 杠杆 → 轨对轨 10% 收益 | 止损 1.5% | RR 6.7:1
BB宽度 2%: 10x 杠杆 → 轨对轨 20% 收益 | 止损 2.3% | RR 8.7:1
BB宽度 3%: 10x 杠杆 → 轨对轨 30% 收益 | 止损 3.2% | RR 9.4:1
What ships with it
24 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.
- cli/__init__.py 0 B runs code
- cli/backtest_daily.py 12 KB runs code
- cli/kline_fetch.py 3.2 KB runs code
- cli/paper_testnet.py 19 KB runs code
- cli/paper.py 22 KB runs code
- cli/simulate.py 10 KB runs code
- cli/test_trade_exec.py 6.5 KB runs code
- cli/testnet_exec.py 16 KB runs code
- cli/trade_exec.py 18 KB runs code
- cli/trade_log.py 6.8 KB runs code
- config.yaml 4.2 KB
- core/__init__.py 0 B runs code
- core/binance_client.py 15 KB runs code
- core/filters.py 5.9 KB runs code
- core/logger.py 1.8 KB runs code
- core/strategy.py 5.6 KB runs code
- core/test_binance_client.py 6.1 KB runs code
- docs/backtest-records.md 11 KB
- docs/paper-reviews.md 3.5 KB
- docs/paper-trading-record.md 3.6 KB
- docs/telegram-push-report.md 1.8 KB
- scripts/bb_report.py 3.8 KB runs code
- scripts/fix_testnet_exit_prices.py 6.2 KB runs code
- scripts/telegram_push.py 1.7 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.
- 5d ago First seen · 309 lines · 159 tokens per session scan A c00861690be4
bb-scalper is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed yesterday), licensed MIT. It adds 159 tokens to every session and 4,318 once invoked, about $0.0008 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 2026-09-05.
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…