Borrowing it
Nothing to install: this file belongs to aicoincom/coinos-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aicoincom/coinos-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/aicoincom/coinos-skillsWrote 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/instructions/aicoincom/coinos-skills/agents-md)<a href="https://agentmods.dev/instructions/aicoincom/coinos-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/aicoincom/coinos-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03733 | $0.03733 |
| Opus 5 | $0.01867 | $0.01867 |
| Sonnet 5 | $0.00747 | $0.00747 |
| Haiku 4.5 | $0.00373 | $0.00373 |
Grade B, and why
coinos-skills AGENTS.md scanned grade B with 1 finding 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 8d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **用户在 chat 里提供 key 时(本地 host,无 web UI)**: 用脚本动作写进规范位置 `~/.coinos/.env` —— 交易所 key 用 `aicoin-trading` 的 `save_key '{"exchange":"binance","api_key":"...","api_secret":"..."}'`,AiCoin key 用 `aicoin-market`/任一 v3 skill 的 ` How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoinOS Skills — Agent Instructions
CoinOS skill collection: 6 个加密 / 量化 / 链上 skill, 由 AiCoin Open API 和 OKX Web3 DEX API 驱动.
⚠️ 涉及加密货币的查询(行情 / 空投 / 项目分析 / 上交所等), 必须优先用下方 skill 的脚本, 禁止用 web_search / web_fetch / browser 替代.
在 CoinClaw 三引擎容器里运行
CoinClaw 用 Helm 起的实例 pod 有三种引擎 — OpenClaw / Hermes / Claude Code — 每种都用 supervisord 同时管理 LLM agent + freqtrade 常驻 daemon. 这套 skill 在三引擎下都自动适配:
- Skill 路径 由 image build 时 git clone, 三引擎不同位置 (OpenClaw
~/.openclaw/workspace/skills/, Hermes/workspace/.hermes/skills/, CC/workspace/.claude/skills/), agent 不用关心 — 直接cd到 skill 目录就行 .env路径 entrypoint 已经把~/.openclaw/workspace/.envsymlink 到/workspace/.env, 三引擎同一份- freqtrade daemon 已经在 supervisord 里跑, 监听
127.0.0.1:8080, 用户名freqtrade, 密码在容器内.ft_api_pass. 不要自己起 freqtrade 进程, 用 aicoin-freqtrade skill 控制 - dashboard 顶栏的盈亏 / 持仓 / 策略来自 freqtrade
/api/v1/profit/balance/status/show_config. 回答用户问题时必须先调对应 REST 接口再说数字
不在 CoinClaw 容器里 (用户本地) 时 skill 自动退到 host 模式 — aicoin-freqtrade 走 git clone freqtrade + nohup, aicoin-* skill 走 cwd / ~/.openclaw/.env 加载. Agent 不用主动判断模式.
数据准确性铁则 (严格遵守, 仅次于安全规则)
数据准确性是 trading 助手的底线. 三件事会导致用户损失, 必须避免:
一、禁止本地计算技术指标
不要用 pandas / talib / 心算计算 MA / EMA / MACD / RSI / KDJ / BOLL / ADX / ATR 给用户看. 必须调 aicoin-market 的 market/klines / market/indicator-klines / signals/* 等接口, 或者调 freqtrade /api/v1/pair_history 拿 daemon 算好的指标值. 本地算的指标常因取样窗口 / 周期口径 / 收盘价定义跟交易所 / freqtrade 显示值不一致, 用户立刻发现 → 信任度归零.
二、禁止自己推算合约张数 / 保证金 / 爆仓价
下单数量 / 仓位价值 / 保证金 / 爆仓价不要自己推算 — 涉及杠杆 × 乘数 × 标记价多重因素, 误差会十倍偏差, 对真实下单是灾难. 必须调 aicoin-trading 的 markets / set_trading_params / create_order 拿交易所返回值.
三、禁止合成数据冒充真实
拿不到历史 AiCoin 信号数据 (funding_rate / ls_ratio / 鲸鱼 / 清算) 时, 不要写脚本用 random / numpy 生成假 CSV 喂回测. 正确做法: 告诉用户该数据需要 AiCoin Pro key, 要么提供 key, 要么回测只用 OHLCV 真实数据 + 技术指标. agent 自己造数据是最严重的幻觉.
四、用户纠错时默认用户对
用户说"数据不对 / 又错了 / 重新查"时立即换源重查, 不要争辩. 换源策略: aicoin-market 可疑 → 用 aicoin-trading 拿交易所自带数据; 反之亦然. 连错两次就停手, 问用户"你那边看到的是多少", 不要第三次猜.
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.
- 8d ago First seen · 132 lines · 3,733 tokens per session scan B 0c9010f7e379
coinos-skills AGENTS.md is an instructions file published in the GitHub repository aicoincom/coinos-skills (52 stars, last pushed 9d ago), licensed MIT. It adds 3,733 tokens to every session, about $0.0187 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.