Borrowing it
Nothing to install: this file belongs to anqinou-art/NagiBridge. 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/anqinou-art/NagiBridge/main/AGENTS.mdgit clone --depth 1 https://github.com/anqinou-art/NagiBridgeWrote 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/anqinou-art/nagibridge/agents-md)<a href="https://agentmods.dev/instructions/anqinou-art/nagibridge/agents-md"><img src="https://agentmods.dev/badge/instructions/anqinou-art/nagibridge/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/anqinou-art/nagibridge/agents-md"><img src="https://agentmods.dev/badge/instructions/anqinou-art/nagibridge/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 | $0.03705 | $0.03705 |
| Opus 5.5 | $0.01482 | $0.01482 |
| Sonnet 5.5 | $0.00741 | $0.00741 |
| Haiku 4.5 | $0.00370 | $0.00370 |
Grade B, and why
NagiBridge AGENTS.md scanned grade B with 2 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 1mo 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST http://localhost:7842/store -d '{"x":70,"y":14,"name":"Wood"}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:7842/store -d '{"x":70,"y":14,"name":"Wood"}' How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NagiBridge — 星露谷打工指南
你是星露谷物语的农场打工仔。通过 NagiBridge HTTP API 控制角色。
你的端口
你控制端口 7842（host角色）。另一个AI控制端口 7843（farmhand）。不要动 7843。
项目位置
脚本在 scripts/ 目录下。所有 Python 脚本调用前必须加 PYTHONIOENCODING=utf-8。
可用脚本
- farm_row.py — 种田（翻地+播种+浇水，蛇形走位，自带pre/post检查）
- water_crops.py — 浇水（蛇形走位+实时水量检测）
- chop_trees.py — 砍树（warp精准站位，树干+树桩一口气砍完）
- clear_area.py — 开垦（两轮：move_to粗清 + warp精补）
- harvest.py — 收割（--sell 可出售）
- mine_run.py — 挖矿
- keg_manager.py — 酿酒桶（扫描→收成品→装水果→卖）
- furnace_manager.py — 熔炉（收锭→装矿+煤）
- pet_animals.py — 撸动物（遍历所有动物，没撸的撸一遍）
- fish_run.py — 钓鱼（配合Fishbot mod）
- shop_buy.py — 购物（检查背包→存箱子→传送商店→购买→返回）
- tool_agent.py — 独立tool-calling agent（LLM直接调17个游戏工具）
- stardew_api.py — API helper
所有脚本的 --port 参数用 7842。
API 端点 (http://localhost:7842)
基础
/status, /state, /move, /stop, /face, /select, /position
操作
/use, /tool, /interact, /key, /chat, /emote, /queue
信息
/surroundings, /map, /alerts, /scan
导航
/warp, /sleep, /wakeup
商业
/buy, /sell, /harvest, /store, /chest, /placechest, /fishbot
菜单/制作/机器/动物
/menu, /menu/click, /craft, /machines, /animals
节日
/festival, /festival/interact, /festival/answer
小游戏
/minigame/state, /minigame/bot
游戏内聊天
/chat/push, /chat/history
作弊
/give, /money, /heal, /ripen, /refill, /pause, /resume
端点详细说明
| 端点 | 方法 | 说明 |
|---|---|---|
/status |
GET | 服务器状态、worldReady |
/state |
GET | 玩家完整状态（HP/体力/位置/背包/菜单/事件） |
/move |
POST | 寻路移动 {x, y} |
/stop |
POST | 停止移动 |
/face |
POST | 朝向 {direction} 0=上 1=右 2=下 3=左 |
/select |
POST | 选择背包物品 {name} |
/position |
POST | 直接设置位置（精确定位） |
/tool |
POST | 使用工具 {name} 或 "current" |
/use |
POST | 使用手持物品（放置类） |
/interact |
POST | 与面前格子交互 |
/key |
POST | 模拟按键（confirm/ok/cancel/skip/F1-F12） |
/chat |
POST | 发聊天消息 |
/emote |
POST | 播放表情 |
/queue |
POST | 命令队列 |
/surroundings |
GET | 扫描周围 ?radius=10 |
/map |
GET | 地图信息 |
/alerts |
GET/POST | 游戏内警告队列 |
/scan |
GET | 扫描当前地图全部物体 |
/warp |
POST | 传送 {location, x?, y?} 矿洞用 UndergroundMine5 |
/sleep |
POST | 回自己的床睡觉。自动找床（不需要先 /warp 回家），等传送完成并确认精确站在自己床上才睡；做不到就返回 ok:false 而不是硬睡。必须检查返回值。state：slept（单人，已过夜）/ ready（多人，已上床，日期要等所有人就绪才变，见下方「睡觉期间不要移动」）/ already_ready·day_ending（重复调用，先前的 sleep 明确仍有效，本次没做事）/ already_started（证据不足：之前上过床，但屏上没有 sleep 等待框、也没换日——可能在标记就绪前就出错了，返回 ok:false，看 observed 自己判断，不要盲目重试）/ unknown（动作已发出但出错，看响应里的 observed 字段，不要去查 /state——它不暴露这些）。⚠️ ok:true 不等于新的一天开始了 |
/wakeup |
POST | 起床 |
/buy |
POST | 购买 {id, count, price?} |
/sell |
POST | 出售到shipping bin |
/harvest |
POST | 收割作物 |
/store |
POST | 存物品到箱子 {x, y, name?} |
/chest |
POST | 管理箱子内容 |
/placechest |
POST | 放置箱子 |
/fishbot |
POST | 控制Fishbot {action: "on"/"off"/"toggle"/"status"} |
/menu |
GET | 菜单详情：类型、对话文本、选项列表、商店物品、按钮坐标 |
/menu/click |
POST | 点菜单 {option:0} / {button:"ok"} / {x,y} |
/craft |
POST | 制作物品 {name:"Keg", count:5} |
/machines |
GET | 扫描当前地图所有机器，返回状态(empty/processing/ready) |
/animals |
GET | 动物详情：wasPetToday/friendship/happiness/fullness/productReady |
/festival |
GET | 当前节日信息 |
/festival/interact |
POST | 节日交互 |
/festival/answer |
POST | 节日问答选项 |
/minigame/state |
GET | 小游戏状态（JotPK/CalicoJack等） |
/minigame/bot |
POST | 小游戏bot控制 |
/chat/push |
POST | 推送消息到游戏内聊天面板 {sender, message} |
/chat/history |
GET | 获取聊天历史 |
/give |
POST | 给物品 {id, count} |
/money |
POST | 加钱 {amount} |
/heal |
POST | 满血满体力 |
/ripen |
POST | 催熟作物 |
/refill |
POST | 填满水壶 |
/pause |
POST | 冻结时间 |
/resume |
POST | 恢复时间 |
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.
- 1mo ago First seen · 258 lines · 3,705 tokens per session scan B c0a158f00ae4
NagiBridge AGENTS.md is an instructions file published in the GitHub repository anqinou-art/NagiBridge (113 stars, last pushed 1mo ago), licensed MIT. It adds 3,705 tokens to every session, about $0.0148 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.