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/beihaili/get-started-with-web3/agents-mdgit clone --depth 1 https://github.com/beihaili/Get-Started-with-Web3Wrote 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/beihaili/get-started-with-web3/agents-md)<a href="https://agentmods.dev/instructions/beihaili/get-started-with-web3/agents-md"><img src="https://agentmods.dev/badge/instructions/beihaili/get-started-with-web3/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 | $0.04297 | $0.04297 |
| Opus 5 | $0.02148 | $0.02148 |
| Sonnet 5 | $0.00859 | $0.00859 |
| Haiku 4.5 | $0.00430 | $0.00430 |
Grade A, and why
Get-Started-with-Web3 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Get Started with Web3 Agent Notes
默认用中文交流。错误信息可保留英文,分析和说明尽量用中文。
项目定位
这是一个 Web3 学习平台,包含 Markdown 教程内容、React SPA、AI Tutor、徽章系统、SEO 构建脚本、捐赠/赞助配置,以及面向 AI Agent 的只读内容接口。当前主课程由 src/config/courseData.js 驱动,覆盖 Web3 快速入门、比特币技术、以太坊与智能账户、Web3 Builder、DeFi、Layer 2/跨链、DAO 等模块。
CEO 运营目标
项目当前运营目标是把 Get Started with Web3 做成具备持续增长、持续运营和收入能力的开源 Web3 学习平台。核心里程碑是达到 1000 GitHub stars,并让项目同时提升 beihai 的个人影响力。
运营文档:
docs/strategy/2026-05-14-ceo-operating-system.md: CEO 操作系统,包含使命、北极星指标、增长闭环、变现模型、30/60/90 天路线图和外部动作审批边界。docs/strategy/2026-05-14-execution-board.md: 执行看板,包含 KPI、工作流、前 10 个任务、内容发布队列和赞助线索。docs/strategy/2026-05-14-sponsor-kit.md: 赞助包草案,包含受众、价格、曝光权益、接受政策和月度汇报指标。docs/strategy/2026-05-14-sponsor-outreach-drafts.md: 赞助外联话术草案;常规外联可自主执行,高风险赞助对象仍需单独确认。docs/strategy/2026-05-15-sponsor-leads-tracker.md: 具名赞助/资助线索 tracker,记录公开来源、fit score、建议外联角度、渠道、状态和风险边界;发送外联后必须同步每日运营汇报。docs/strategy/2026-05-18-donation-affiliate-disclosure-review.md: 捐赠、赞助、联盟链接和加密货币打赏的披露审查记录;新增或扩大 affiliate、payment、wallet、x402 相关入口前必须保持公开披露并确认风险边界。docs/strategy/2026-05-18-safe-reown-impact-memo.md: 面向 Safe Ecosystem Foundation 和 Reown / WalletConnect 的资助/赞助 impact memo 草案,包含当前指标、官方来源、建议 ask、外联话术和发送前检查清单;尚未发送外联。docs/strategy/2026-05-18-paid-ai-tools-landing-copy.md: 未来 hosted AI 工具 landing copy 草案,覆盖generate_personalized_web3_plan和audit_learning_answer的定位、CTA、边界文案、FAQ 和 launch checklist;不得描述为已上线付费能力。docs/strategy/2026-05-14-awesome-list-submissions.md: awesome-list 和社区分发追踪,包含定位文案、目标列表、PR 模板和中文社区帖草案。docs/community/contributor-ladder.md: 贡献者成长路径,定义 first-time contributor、repeat contributor、reviewer、module steward 和 community/sponsor ally。docs/community/contributor-spotlight-template.md: 月度贡献者 spotlight 模板,用于把公开 PR、issue、社区分发和增长指标转化为 GitHub/社交更新;不能承诺代币奖励、付费曝光或金融背书。docs/community/spotlights/: 已发布贡献者 spotlight 目录;只引用公开 GitHub username、PR、issue、公开指标和贡献影响,不写未经同意的个人信息。docs/community/good-first-issues.md: 可复制到 GitHub Issues 的 starter issue 清单,包含标签、背景、验收标准和验证方式。docs/operations/: 每日运营汇报目录;README.md定义 cadence、数据源和风险边界,templates/daily-report-template.md是每日汇报模板,按YYYY-MM-DD-daily-report.md记录实际进展、指标、部署、外部分发、赞助线索和下一步。
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 · 162 lines · 4,297 tokens per session scan A fb6c099f470a
Get-Started-with-Web3 AGENTS.md is an instructions file published in the GitHub repository beihaili/Get-Started-with-Web3 (614 stars, last pushed 3d ago), licensed MIT. It adds 4,297 tokens to every session, about $0.0215 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
bitcoin-api copilot-instructions.md
Instructions for Bortlesboat/bitcoin-api, covering satoshi api copilot instructions, project shape, x402 buyer path, agent/mcp integration and required maintenance.
maestro-mcp-server CLAUDE.md
Claude Code instructions for maestro-org/maestro-mcp-server, covering maestro mcp server - developer guide, architecture, key components, code generation and performance optimizations (2026-02).
ethereum-wallet-toolkit AGENTS.md
AGENTS.md instructions for nirholas/ethereum-wallet-toolkit, covering ethereum-wallet-toolkit development guidelines, project overview, terminal management and contributing.
ethereum-wallet-toolkit copilot-instructions.md
Copilot instructions for nirholas/ethereum-wallet-toolkit, covering ethereum-wallet-toolkit and terminal management.
ethereum-wallet-toolkit GEMINI.md
Gemini CLI instructions for nirholas/ethereum-wallet-toolkit, covering ethereum-wallet-toolkit and terminal management.
platform CLAUDE.md
Claude Code instructions for dashpay/platform, a project described as: Structured data storage blockchain with secondary indices and identities.