Borrowing it
Nothing to install: this file belongs to xiaojiou176-open/campus-copilot. 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/xiaojiou176-open/campus-copilot/main/AGENTS.mdgit clone --depth 1 https://github.com/xiaojiou176-open/campus-copilotWrote 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/xiaojiou176-open/campus-copilot/agents-md)<a href="https://agentmods.dev/instructions/xiaojiou176-open/campus-copilot/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaojiou176-open/campus-copilot/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/xiaojiou176-open/campus-copilot/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaojiou176-open/campus-copilot/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 | $0.05761 | $0.05761 |
| Opus 5 | $0.02880 | $0.02880 |
| Sonnet 5 | $0.01152 | $0.01152 |
| Haiku 4.5 | $0.00576 | $0.00576 |
Grade A, and why
campus-copilot 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 9d 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 — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CampusCopilot Repo Agent Notes
这份文件是 repo-local 工作边界,用来补充全局 agent 规范。
它不重写根规则,只回答这个仓库里最容易写偏的地方。
先接受的事实
- 这不是“先做聊天框”的项目。
- 这是一个 本地优先的学习信息整理工作台。
- 正确顺序始终是:
- 先
schema - 先
adapter - 先真实数据链路
- 先工作台与导出
- 最后才是 AI
- 先
当前正式主线
- 支持站点:
Canvas / Gradescope / EdStem / MyUW - extension 主链已接通四站最小同步
- AI 已进入最小问答闭环,但仍然只走:
OpenAI api_keyGemini api_key
Gemini OAuth / Anthropic / web_session / 多 provider 自动路由仍然不是正式主路径
绝对不要写偏的地方
- 不要让 AI 直接读取网页、DOM、cookie 或 raw adapter payload
- 不要把 exporter 直接绑到站点原始响应
- 不要把 private/internal request 路径包装成“已经官方稳定”
- 不要引入自动提交、自动发帖、自动写操作
- 不要扩大权限到
cookies
当前事实层和展示层
Dexie是 canonical local entitiesstorage read-model是工作台真相源TanStack Query不是本仓库主真相源- sidepanel/popup/options 都应该消费统一 schema + read model
当前推荐门禁
任何声称“本地默认 gate 已完成”的改动,至少要附带这些新鲜结果:
pnpm verify
如果改动触及 extension 的用户可见交互,或你要对齐 GitHub-hosted required lane,再补:
pnpm verify:hosted
如果碰到 BFF 或 API 入口,再补 targeted 证据:
pnpm --filter @campus-copilot/api test
bash scripts/api-healthcheck.sh
当前 live / profile / auth 纪律
- 做真实 campus-site live/browser/session 推进时,当前 repo 的 canonical Chrome 根目录不再是默认系统根,而是:
~/.cache/campus-copilot/browser/chrome-user-data/
- 当前 repo 的 canonical profile directory 是:
Profile 1
- 当前 repo 的 canonical 显示名是:
campus-copilot
- 旧世界里默认 Chrome 根目录下的
Profile 13只再承担一件事:- 一次性迁移源
- 默认系统 Chrome 根目录:
$HOME/Library/Application Support/Google/Chrome不再是当前 repo 的运行真相面。
- live/browser 脚本不允许再偷偷回退到默认系统根目录;缺少 repo-owned browser root 或 repo-owned instance 时,应直接报:
browser_root_not_bootstrappedbrowser_attach_missing_repo_instance
probe:live/diagnose:live/support:bundle只允许读取 repo-owned Chrome lane 的 CDP / DevTools target 控制面。- 严禁再用
AppleScript/JXA/System Events/ GUI 坐标点击去读取或推动任意桌面 Chrome 窗口、标签页或系统前台会话。 - 如果当前缺少 repo-owned 控制面,必须直接 fail fast;不要再回退到“扫桌面上现有 Chrome 标签”的 global fallback。
- 当前 live runtime 的正式登录态口径必须是确定性的:
authenticated: true | falseauthBoundary: authenticated | session_resumable | mfa_required | logged_out | not_open | profile_mismatch | attach_failed
- 不要再把
likely_authenticated/public_or_unknown当成当前 operator-facing 真相面。 browser:launch现在还要维护当前 canonical lane 的人眼身份锚点:.runtime-cache/browser-identity/index.html- title / favicon / accent 应明显可识别
- 可以提示用户手工 pin 一次
- 但不要去写 Chrome 私有 avatar/theme/pinned-tab 偏好
- 对
Canvas / Gradescope / EdStem / MyUW的默认工作假设必须是:- 如果用了正确的 repo-owned
Profile 1(显示名campus-copilot),要么已有登录态; - 要么密码管理器已经能自动填充;
- 如果用了正确的 repo-owned
- agent 应先继续推动登录 / SSO / 会话续接,而不是一看到
session_resumable或mfa_required就停。 - 只有在正确 profile 下确认:
- 没有现成登录态;
- 没有密码自动填充;
- 且继续操作后仍无法前进; 才允许把它归类成真实 external / human-only 边界。
- 如果四站确实需要账号密码,最后兜底只允许使用本地
.env中的ACCOUNT_ID/PASSWORD这两个变量;只允许读取变量名和使用它们完成登录,严禁在日志、回复、截图标注或文档里扩散具体值。 Gradescope的默认登录推进假设要写死:- 先点
Log In - 或直接走
https://www.gradescope.com/auth/saml/uw - 优先复用
Canvas/MyUW已存在的 UW SSO 会话 - 若
MyUW/Canvas已在同一 profile 中完成认证,则应优先沿学校 SSO 链继续,不要把它过早报成 blocker。
- 先点
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.
- 9d ago First seen · 396 lines · 5,761 tokens per session scan A 11e42c8d6869
campus-copilot AGENTS.md is an instructions file published in the GitHub repository xiaojiou176-open/campus-copilot (2 stars, last pushed 7d ago), licensed MIT. It adds 5,761 tokens to every session, about $0.0288 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 2026-08-31.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.