Borrowing it
Nothing to install: this file belongs to ACCSCI/AgentDock. 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/ACCSCI/AgentDock/master/AGENTS.mdgit clone --depth 1 https://github.com/ACCSCI/AgentDockWrote 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/accsci/agentdock/agents-md)<a href="https://agentmods.dev/instructions/accsci/agentdock/agents-md"><img src="https://agentmods.dev/badge/instructions/accsci/agentdock/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/accsci/agentdock/agents-md"><img src="https://agentmods.dev/badge/instructions/accsci/agentdock/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 | $0.01485 | $0.01485 |
| Opus 5.5 | $0.00594 | $0.00594 |
| Sonnet 5.5 | $0.00297 | $0.00297 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
AgentDock 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 2mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
本文件是给所有 contributor（包括 AI agent）阅读的项目级指引。架构、测试、用户测试的当前规则都在这里。
架构现状
单实例架构（0.1.x 当前状态）
- AgentDock 0.1.x 运行在 单个 Electron 进程里，所有 session/port/state 都由这个进程拥有（
SessionManager、PortPool）。没有独立的 daemon 进程——DaemonStatusBar已在 PR #108 中移除，因为单实例下这个栏位只是静态 "Running" 文字，没有信息价值。 - 状态分两份 SQLite 存储：
- 全局项目 DB：dev 模式在
<userDataDir>/global/projects.db，生产在~/.agentdock/projects.db——存已打开的项目（id, name, path, createdAt） - 项目 DB：在
<userDataDir>/data/db.sqlite——存当前激活项目的sessions和todos
- 全局项目 DB：dev 模式在
SessionManager是纯内存的，session 的生命周期状态（creating | active | deleting）和步骤进度持久化到项目 DB 的sessions.status/sessions.steps列，渲染端通过db:projects:list直接读，不需要 SSE/streaming。
Dev 模式 userData 隔离
AGENTDOCK_DEV_INSTANCE=<N>环境变量（由scripts/dev-instance.ts设置）标记 dev 模式。- 设了之后，
projects.db跟随<userData>/global/projects.db，不再用生产路径~/.agentdock/projects.db。这样多个 dev AgentDock 实例可以并行跑而不撞共享 SQLite 文件。 - 不设时行为等同于生产（单实例、单全局
~/.agentdock/projects.db）。 - 默认保持生产行为；dev/测试需要并行时显式设
AGENTDOCK_DEV_INSTANCE=1。 - Worktree 目录（
<project>/.agentdock/worktrees/）是项目级的，不跟随 userData——dev 和生产用的是同一份。 app.requestSingleInstanceLock()以userData为 key，所以 dev 实例只要--user-data-dir不同就能共存；生产单实例不变量保持不变。
测试隔离流水线
测试按"在哪跑"分成三层，不要跨层迁移：
| 层 | 跑在哪 | 跑什么 | 触发方式 |
|---|---|---|---|
| CI | GitHub Actions runner | typecheck + lint + unit + build | push/PR 自动 |
| 本地 dev | 开发者机器 | unit + integration + acceptance + e2e（59 个 spec） | bun run test / bun run test:e2e |
| 用户测试 | 开发者机器 | 探索性 UI 流程测试（见下文） | npx flue run user-agent |
为什么 CI 不跑 e2e
GitHub runner 是共享临时虚拟机，Electron 在上面启动不稳定（字体/端口/显示系统都不可控）。CI 守住"代码能 build + 单测过"这条线就够了。
并行实例隔离规则
每个并行运行的实例（e2e test、user-agent、多 dev 窗口）启动 Electron 时必须带：
--user-data-dir=<独立目录>—— 隔离项目 DB（data/db.sqlite）AGENTDOCK_DEV_INSTANCE=1—— 隔离全局 DB（<userData>/global/projects.db）
这两个 flag 一起用能产生完全自洽的 AgentDock 实例，不与其它实例在 SQLite、端口、session 状态上冲突。
<userData>/global/projects.db 这个路径是 v9/v10 schema 迁移加的——之前共享的 ~/.agentdock/projects.db 是并行测试的撞车点。
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.
- 2mo ago First seen · 79 lines · 1,485 tokens per session scan A 50b7a0fd88c3
AgentDock AGENTS.md is an instructions file published in the GitHub repository ACCSCI/AgentDock (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,485 tokens to every session, about $0.0059 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 2026-08-31.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.