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 agentmods add instructions/ethanalgox/llm-tradebot/agents-mdgit clone --depth 1 https://github.com/EthanAlgoX/LLM-TradeBotWrote 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/ethanalgox/llm-tradebot/agents-md)<a href="https://agentmods.dev/instructions/ethanalgox/llm-tradebot/agents-md"><img src="https://agentmods.dev/badge/instructions/ethanalgox/llm-tradebot/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 | $0.04912 | $0.04912 |
| Opus 5 | $0.02456 | $0.02456 |
| Sonnet 5 | $0.00982 | $0.00982 |
| Haiku 4.5 | $0.00491 | $0.00491 |
Grade A, and why
LLM-TradeBot AGENTS.md 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 4d 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件用于约束本仓库的默认开发流程，目标是减少重复沟通、减少返工，并让改动和当前项目结构保持一致。
如果本文件与仓库中的脚本、工作流、代码现状不一致，以实际可执行内容为准，并在相关改动中顺手修正文档，避免规则继续漂移。
1. 硬规则
- 遵循现有目录边界：
- 后端逻辑优先放在
src/、data_provider/、api/、bot/ - Web 前端改动在
apps/dsa-web/ - 桌面端改动在
apps/dsa-desktop/ - 部署与流水线改动在
scripts/、.github/workflows/、docker/
- 后端逻辑优先放在
- 未经明确确认，不执行
git commit、git tag、git push。 - commit message 使用英文，不添加
Co-Authored-By。 - 不写死密钥、账号、路径、模型名、端口或环境差异逻辑。
- 优先复用现有模块、配置入口、脚本和测试，不新增平行实现。
- 默认稳定性优先于“顺手优化”；非当前任务直接需要的重构、抽象和基础设施迁移一律克制。
- 新增配置项时，必须同步更新
.env.example和相关文档。 - 涉及用户可见能力、CLI/API 行为、部署方式、通知方式、报告结构变化时，必须同步更新相关文档与
docs/CHANGELOG.md。 - 修改报告格式、报告渲染效果或 Web UI 界面时，PR 描述必须附受影响报告 / 页面截图；涉及前后差异时优先附前后对比，无法截图时说明原因与替代可视证据。
- Issue / PR 过程截图、审查截图、一次性验收截图和临时可视证据不得作为仓库文件合入；应放在 PR 描述、PR 评论、GitHub 附件、Actions artifact 或外部可访问证据链接中。产品长期文档确需保留的示意图除外，但文件名和文档语义必须脱离具体 issue / PR 编号。
docs/CHANGELOG.md的[Unreleased]段使用扁平格式：每条独立一行，格式为- [类型] 描述，类型取值：新功能/改进/修复/文档/测试/chore；禁止在[Unreleased]内新增### 类目标题，以减少并发 PR 的 merge 冲突。发版时由 maintainer 汇总整理成带标题的正式格式。README.md只用于项目定位、核心能力总览、快速开始、主要入口、赞助/合作等首页级信息；非必要不更新 README，避免持续膨胀。- 更细的模块行为、页面交互、专题配置、排障说明、字段契约、实现语义和边界条件，优先更新对应
docs/*.md或专题文档，不写入 README。 - 变更中英双语文档之一时，需评估另一份是否需要同步；若未同步，交付说明里要写明原因。
- 注释、docstring、日志文案以清晰准确为准，不强制要求英文，但应与文件语境保持一致。
1.1 PR 标题规范（非阻断建议）
- 推荐使用
<类型>: <修改内容>作为 PR 标题，例如fix: 修复大盘分析历史记录丢失，优先类型为fix/feat/refactor/docs/chore/test/ci。 - 标题应描述实际变更内容，建议不添加
[codex]、codex、autocode、copilot或其他工具/agent 来源前缀。 - 该规范仅用于协作可读性与一致性提示，不应单独作为 review process blocker。
1.2 贡献质量底线
- 本仓库不接受以堆叠代码量、扩大 diff 面、补丁式响应 review 来替代真实设计收敛的 PR。
- 贡献质量以是否解决明确问题、是否最小化影响面、是否保持现有契约一致、是否覆盖真实风险路径为准；不以新增行数、文件数量、功能宣传或“看起来完整”为准。
- 请不要把本仓库当作低成本试验场、简历展示场或 contribution farming 场所。任何 PR 都必须证明作者理解当前系统契约，并完成基本自审、集成和验证。
- 使用 AI 辅助开发本身不是问题；问题是提交 AI 生成后未经人工语义审查、未验证、未收敛的代码。此类 PR 会按低质量提交处理。
- review 反馈后，不接受只在被指出的位置追加局部 patch。作者必须重新检查同一业务语义涉及的所有入口、配置、测试、文档、workflow 和用户可见路径。
- 如果一个 PR 在多轮 review 后仍持续出现同类契约漂移、重复 fallback、测试绕过真实风险层、PR body 与实际 diff 不一致等问题，维护者可以要求关闭重做，而不是继续逐点 review。
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.
- 4d ago First seen · 292 lines · 4,912 tokens per session scan A 4b4e299422c1
LLM-TradeBot AGENTS.md is an instructions file published in the GitHub repository EthanAlgoX/LLM-TradeBot (316 stars, last pushed today), licensed MIT. It adds 4,912 tokens to every session, about $0.0246 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.
Other instructions, from other repositories
binance-net
Use Binance.Net when generating C#/.NET code that interacts with the Binance cryptocurrency exchange — including Spot, Margin, USD-M Futures, COIN-M Futures, Options, sub-accounts, brokerage, REST endpoints, WebSocket subscriptions, account management, market data, or order placement. Triggers on any request…
Binance.Net copilot-instructions.md
Copilot instructions for JKorf/Binance.Net, covering copilot instructions for binance.net, use binance.net, not raw http, client setup, result handling and api structure.
nautilus_AItrader AGENTS.md
AGENTS.md instructions for Patrick-code-Bot/nautilus_AItrader, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
ai-fund CLAUDE.md
Claude Code instructions for cubexch/ai-fund, covering ai fund, project structure, architecture, development workflow and ci/cd.
my-binance AGENTS.md
AGENTS.md instructions for cokepoppy/my-binance, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
jesse AGENTS.md
AGENTS.md instructions for jesse-ai/jesse, covering jesse repository guide for ai agents, skills, key characteristics, central framework and technology stack.