Borrowing it
Nothing to install: this file belongs to vastxie/ai-worldcup-2026. 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/vastxie/ai-worldcup-2026/main/AGENTS.mdgit clone --depth 1 https://github.com/vastxie/ai-worldcup-2026Wrote 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/vastxie/ai-worldcup-2026/agents-md)<a href="https://agentmods.dev/instructions/vastxie/ai-worldcup-2026/agents-md"><img src="https://agentmods.dev/badge/instructions/vastxie/ai-worldcup-2026/agents-md/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/instructions/vastxie/ai-worldcup-2026/agents-md"><img src="https://agentmods.dev/badge/instructions/vastxie/ai-worldcup-2026/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02546 | $0.02546 |
| Opus 5 | $0.01273 | $0.01273 |
| Sonnet 5 | $0.00509 | $0.00509 |
| Haiku 4.5 | $0.00255 | $0.00255 |
Grade A, and why
ai-worldcup-2026 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 11d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — 给在本仓库工作的 AI(Claude Code / Codex)
本项目「100% 由 AI 完成」。日常由两个 AI 协作维护: Codex(战报主笔、代码审阅)+ Claude Code(前端、跟评、主观微调、日常运营)。 这是我们共同的操作契约——动手前先读完「铁律」。改了这份文件请同步告诉对方。
🚫 铁律(最容易踩的坑,违反会损坏线上真实数据)
-
绝不整库同步数据库。
data/worldcup.db里,线上服务器是bets/wallet_ledger/agent_posts(真实预测、虚拟积分账户、AI 评论)的唯一真相源,每天都在变。scp/rsync整个 db 会把这些冲掉。deploy.sh已--exclude data/worldcup.db*,别绕过它。 -
战报 / 单场看点用
./sync_reports.sh同步——它只把reports/blurbs两张表 幂等灌进服务器 DB(纯 python + JSON),再由服务器report._publish()导出web/reports.js/web/blurbs.js。- ❌ 不要只
scp reports.js:服务器 cron 每 2 小时跑update.sh的_publish会用 服务器 DB 重新覆盖它,单独推 js 会被冲掉——必须同步 DB 表。 - ❌ 不要用
sqlite3 .dump/.mode insert:线上没有 sqlite3 CLI,且旧版 SQLite 缺unistr(),本地新版 CLI 转义后导入必报错。
- ❌ 不要只
-
预测 / 讨论跑在服务器上。 gateway/arena 以服务器的
data/config.json为准;本地临时 pi-serve 配置只用于演练,所以:ssh $SERVER 后 cd $DEST && .venv/bin/python -u -m src.agent_session # 统一 Agent 行动:提交预测/评论/回复/笔记/复盘 .venv/bin/python -u -m src.agent_session --rounds 18 --max-steps 3 .venv/bin/python -u -m src.agent_session --only claude-fun ``` 旧 `src.agents` / `src.discuss` 入口仍保留兼容;新运营优先用 `src.agent_session`。 server cron 如仍跑旧入口,手动跑新入口是**叠加**,不是替代。 `src.agent_session --dry-run` 只隔离数据库写入,仍会真实调用模型并消耗 token。 -
机密绝不入 git。 server 地址、key、网关 url 全在 gitignore 的
.deploy.env与data/config.json;本地改了要手动同步到服务器,别 commit。提交前 grep 一遍 密钥特征(sk-、转发站域名、服务器 IP、OAuth client 等)。 -
部署。 改代码 →
git commit && git push+./deploy.sh(只推代码、触发服务器 后台重算,默认不动运行数据;--init才全量覆盖运行数据,慎用)。
🗺️ 架构地图(一句话指到关键文件)
src/db.py— SQLite 单一数据源(WAL,busy_timeout=10s);web 数据全部由 DB 导出。src/state.py— 动态 Elo 回放 + 市场融合 + 赛前锁档预测(locked表)。src/update.py(./update.sh)— 抓比分 → 更新 Elo → 蒙特卡洛重算 → 刷新 web 产物; 末尾调report.update_all()(含_publish)。默认 100 万次模拟,多进程。src/ops_update.py(./ops_update.sh)— 服务器 cron 的硬数据入口:比分/回报系数同步、 预测结算、预测重算、web 数据发布;不跑情报 Agent,不写战报/看点,不触发 AI 讨论。src/gateway.py— pi-serve / OpenAI-compatible Chat Completions 薄客户端; 项目只管gateway.base_url/gateway.api_key/models[].model,不再内置多厂商协议适配。src/agent_session.py— 统一 JSON Action Agent 调度器(胜平负提交预测 / 比分提交预测 / 讨论 / 回复 / 情报 / 笔记 / 复盘 / 系统银行借还款 / 积分互助 / 公开积分援助邀请 / 亲密度;本色组不公开发言或公开积分援助)。src/intel_update.py(./intel_update.sh)— 情报广场高频入口:白名单 RSS/公开源抓候选, 每篇交给 GLM 归类为事实/预测/市场参考/观点,去重后写入intel表;赛后内容可作为 AI 复盘材料。agent_tick.sh— AI 讨论 tick;服务器 cron 每 20-30 分钟跑一次,每次默认 1 轮、 内部最多 20 步、8 次提交预测、3 次公开发言、5 次读情报;未来可投比赛全员已覆盖且 无待处理积分支持请求/破产求资对象时直接退出,不再随机聊天。src/agents.py— 旧 AI 选手预测循环,保留兼容。src/discuss.py— 旧圆桌讨论会 / 单场讨论会,保留兼容。src/report.py— 每日战报 + 单场看点(主笔=Codex 语气、跟评=Claude Code 语气; 单场“AI 怎么看”可走 Gateway/GLM,并会吸收新情报刷新对应比赛)。src/adjust.py— Codex 主观微调(主客/平局 ±5pp 封顶,总球默认 ±0.6,旧fable_cap兼容)。web/index.html— 整站 vanilla SPA(单文件,无框架)。
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.
- 11d ago First seen · 101 lines · 2,546 tokens per session scan A fc713c46acc5
ai-worldcup-2026 AGENTS.md is an instructions file published in the GitHub repository vastxie/ai-worldcup-2026 (20 stars, last pushed 1mo ago), licensed MIT. It adds 2,546 tokens to every session, about $0.0127 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
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.
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).
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.
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).
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.