Borrowing it
Nothing to install: this file belongs to glide-the/im-dream. 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/glide-the/im-dream/develop/AGENTS.mdgit clone --depth 1 https://github.com/glide-the/im-dreamWrote 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/glide-the/im-dream/agents-md)<a href="https://agentmods.dev/instructions/glide-the/im-dream/agents-md"><img src="https://agentmods.dev/badge/instructions/glide-the/im-dream/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/glide-the/im-dream/agents-md"><img src="https://agentmods.dev/badge/instructions/glide-the/im-dream/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 | $0.03052 | $0.03052 |
| Opus 5.5 | $0.01221 | $0.01221 |
| Sonnet 5.5 | $0.00610 | $0.00610 |
| Haiku 4.5 | $0.00305 | $0.00305 |
Grade A, and why
im-dream 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS Instructions
本仓库是 Ink & Memory
Vibe Contract
- Any functional, architectural, or coding-style change must update affected folder docs and file headers before session end.
- Prefer reuse-first refactor: search existing modules/components before adding new implementations.
- Avoid hard-coded business IDs, thresholds, hosts, paths, or policy values; resolve to env/config/policy first.
Source Of Truth
- Root repository maintenance and Agent contract:
AGENTS.md - Folder contracts:
**/.folder.md - Rules index:
docs/rules/README.md - Cursor rules:
.cursor/rules/*.mdc
Validation
- Run requested validation commands after meaningful changes.
- When touching docs, verify Markdown inventory and referenced paths remain valid.
- Report concrete evidence (
command, exit code, key output) in the final summary.
浏览器 E2E 前置检查
- 浏览器 E2E 优先复用本机已安装的 Chrome；只做一次能否启动的轻量检查，不要求重复下载 Playwright Chromium revision。
- 仅当本机没有兼容浏览器时才安装浏览器依赖。浏览器或 runner 无法启动属于 harness 前置失败，不能据此判断页面或 API 有缺陷。
- E2E 结束后只清理本轮明确命名的隔离数据库、端口、进程和生成物，不得停止或修改用户已有服务。
数据库 Schema 协议
- 共享 PostgreSQL Schema 由
https://github.com/glide-the/ink-admin-memory项目的/drizzle唯一管理。 - 禁止新增 Alembic revision、Alembic version table、runtime DDL、自动建表或 SQLite fallback。
- Dream 需要新增表、字段、索引、约束、函数或触发器时，必须先在 Admin Drizzle 中提交前向 migration 和 capability。
- Dream 代码只能依赖已经发布的 capability，不得依赖 Drizzle 全局最新 head。
- 缺少 capability 时必须 fail closed，不得在 Dream 仓库临时补建 schema。
- SQLite 代码只允许存在于明确命名的数据导入或测试 fixture 中，且不得成为运行时依赖。
- 跨版本发布必须遵循 expand → Dream 双版本兼容 → backfill/validate → contract。
评审方案约束
如果评审阶段发现代码已经符合目标，则以文档重构、状态语义统一和缺口测试为主，不制造无意义代码变更。
通用产品设计原则
- 产品方案进入正文前必须完成 Double Diamond：发现阶段读取用户目标、历史工作、现行设计和当前实现；定义阶段收敛核心问题、任务目的与边界；发展阶段比较可行方案并排除概念偏移与过度设计；交付阶段才编写选定方案、业务图和验收。正式设计稿或评审记录保留简洁的判断依据，不把方法过程扩写成用户文章。
- 产品设计稿必须以“背景与问题、目标与边界、概念与规则”为基础结构。
- 产品规则必须对应真实业务约束，不得把任意技术常量包装成产品限制。
- 页面不得展示对用户决策没有帮助的技术说明、重复确认或实现细节。
- 除非操作不可逆或具有明显风险，否则不得增加确认弹窗。
- 配置型业务必须明确 default、desired、effective、revision 和状态转换。
- 实现和测试必须聚焦当前业务目标，不得增加 Chromium revision、重复环境初始化、远程环境、部署状态或其他与验收无关的检查。
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 Changed · +3 lines · +170 tokens per session 2e199e203696
- 7d ago Changed · +14 lines · +548 tokens per session dc3c4fc54e14
- 12d ago First seen · 88 lines · 2,334 tokens per session scan A adfaf74529c0
im-dream AGENTS.md is an instructions file published in the GitHub repository glide-the/im-dream (0 stars, last pushed yesterday), licensed MIT. It adds 3,052 tokens to every session, about $0.0122 per session on Opus 5.5. 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 2026-10-02.
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.