Borrowing it
Nothing to install: this file belongs to vlln/whale-girl. 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/vlln/whale-girl/main/AGENTS.mdgit clone --depth 1 https://github.com/vlln/whale-girlWrote 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/vlln/whale-girl/agents-md)<a href="https://agentmods.dev/instructions/vlln/whale-girl/agents-md"><img src="https://agentmods.dev/badge/instructions/vlln/whale-girl/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/vlln/whale-girl/agents-md"><img src="https://agentmods.dev/badge/instructions/vlln/whale-girl/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 | $0.02021 | $0.02021 |
| Opus 5 | $0.01010 | $0.01010 |
| Sonnet 5 | $0.00404 | $0.00404 |
| Haiku 4.5 | $0.00202 | $0.00202 |
Grade A, and why
whale-girl AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| lib/client/ 源码或构建配置 | `node scripts/build-client.mjs --check`，改完跑 `node scripts/build-client.mjs`；验证站 web 运行中跑 `node scripts/verify-client-smoke.mjs <web-url>`（浏览器冒烟：apply 成功 + 宠物渲染，curl 覆盖不到的 client 面）；**client 行为改动** How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
whale-girl 以官方 bundle 格式分发（仓库根 package.json 的 dsh.bundle + dsh.client，包根 cordis.patch.yml，见 decisions/implemented/simplification/2026-08-12-migrate-to-bundle-format.md）：在 DSH Web GUI 内悬浮的桌面宠物（QQ 宠物形态，A 模式——GUI 内）。架构决策见 decisions/implemented/architecture/2026-08-08-in-gui-pet-architecture.md；文档规范见 docs/AGENTS.md。
当前阶段取舍
首个版本已分发（官方 bundle 形态，2026-08-12 起）。 不再有「可自由重命名与重组」的过渡条款——公开 ref 被消费后改名/重组破坏安装；deep-standard 档位重评结论见 decisions/implemented/process/2026-08-10-l3-tier-review.md。
目录布局
lib/index.mjs Node half 入口：state/interact/config/assets/events 路由 + 事件记账 + whale-girl.pet 服务（client 经 client-modules 挂载，不再注入页面）
lib/src/ Node half 纯逻辑（账本/活动/assets 守卫/配置/signals，零宿主依赖，可单测）
lib/client/ client bundle 源码（纯 DOM 自渲染 + sprite 帧播放器）
lib/client.js 构建产物（由 scripts/build-client.mjs 生成，勿手改）
lib/assets/ sprite sheet + manifest.json（静态服务；manifest↔文件由 verify-assets 门禁守护）
originals/ 生图参考原图（不参与服务）
docs/preview/ 状态动画预览 gif（由 scripts/make-previews.py 生成）
scripts/ 门禁编排器与生成器（清单权威在 scripts/gates/run.mjs）+ 预览生成
tests/ Node half 单测（node:test）
docs/ 文档；标准见 docs/AGENTS.md
decisions/ 决策记录；契约见 decisions/README.md
命令
node scripts/gates/run.mjs # 本地精选门禁组
node scripts/gates/run.mjs --group ci # CI 全量组（含单测）
node --test 'tests/*.test.mjs' # Node half 单测
node scripts/build-client.mjs # 生成 lib/client.js
node scripts/build-client.mjs --check # 校验 lib/client.js 新鲜度（只读）
按改动面选检查
改动落在哪些表面，就跑覆盖那些表面的最窄证据，跑一次；只汇报真正跑过的命令。不要默认跑全套，不要为了提交或推送重复跑已经通过的检查——CI 独占穷尽覆盖。证据分层：pre-commit hook 跑本地精选组 = 提交底线（快、必过）；开发中按本表跑最窄证据；CI 全量组（含单测/门禁自证）独占穷尽覆盖，本地不重复预演。
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 · 65 lines · 2,021 tokens per session scan A 3d40136b8160
whale-girl AGENTS.md is an instructions file published in the GitHub repository vlln/whale-girl (315 stars, last pushed 9d ago), licensed MIT. It adds 2,021 tokens to every session, about $0.0101 per session on Opus 5. A static security scan graded it A with 1 finding (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
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.