Borrowing it
Nothing to install: this file belongs to MisonL/Ling. 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/MisonL/Ling/main/AGENTS.mdgit clone --depth 1 https://github.com/MisonL/LingWrote 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/misonl/ling/agents-md)<a href="https://agentmods.dev/instructions/misonl/ling/agents-md"><img src="https://agentmods.dev/badge/instructions/misonl/ling/agents-md.svg" alt="Measured on agentmods" 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 | $0.01373 | $0.01373 |
| Opus 5 | $0.00687 | $0.00687 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
Ling 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 3d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
沟通与执行
- 全程使用中文。
- 结论必须基于仓库事实、命令输出、测试结果，不凭印象猜测。
- 优先做最小必要修改；不要顺手扩大范围。
- 不要引入静默降级、假成功路径或仅为过测试而写的硬编码。
仓库结构
bin/：CLI 主链路。bin/ling-cli.js负责命令分发；bin/adapters/处理gemini/antigravity/codex目标差异；bin/core/负责构建与转换；bin/utils/放原子写入、manifest、托管区块等通用能力。.agents/：仓库内唯一 Canonical 模板源。项目安装时：gemini/antigravity-> 项目内.agent/codex-> 项目内.agents/
.spec/：Spec 进阶能力的模板、profiles、references 与 skills 源。tests/：Node 内置测试（*.test.js）。docs/：对外技术文档。reference/：只保留受管参考资料；当前应跟踪reference/official/、reference/docs-archive/，不要重新引入重复镜像目录。web/：Next.js 文档站。仅使用npm，不要重新引入bun工作流。
关键实现约束
gemini与antigravity共用.agent/，但逻辑目标身份必须通过项目内.ling/install-state.json区分；涉及共享.agent/的逻辑时，不要退回“默认全算 gemini”的旧行为。codex受管目录是.agents/；遗留.codex/只作为兼容迁移输入，不再作为主输出。- 全局同步默认目标是
codex + gemini + antigravity；gemini与antigravity不能再互相隐式代管。 - 全局
codexSkills 根目录是~/.agents/skills/；若~/.gemini/skills/与 universal 根目录存在内容完全相同的同名 Skill，需要执行去重清理；若同名但内容不同，必须保留 Gemini 专用版本。 ling spec enable若涉及codex或gemini，必须与全局去重逻辑保持一致，不能在启用 Spec 后重新写回 Gemini CLI 重复 Skill。- 文档、测试、CLI 帮助文本必须与实际命令行为一致；改命令行为时同步更新
README.md、docs/TECH.md、docs/PLAN.md与相关测试。
构建、测试与验证
- 安装依赖：
npm install - 全量测试：
npm test - CI 主链路验证：
npm run ci:verify - 健康检查：
npm run health-check - 清理预检：
npm run clean:dry-run - Web 文档站检查：
cd web && npm run lint - 仅改文档时，至少执行
git diff --check；若改 CLI、安装/更新逻辑、状态判定、Spec 或发布链路，必须跑相关测试，默认优先npm test。
代码风格
- 遵循
.editorconfig：默认 4 空格缩进，JSON/YAML 2 空格，LF，UTF-8。 - 根目录 Node 代码保持 CommonJS 风格（
require/module.exports）。 - 文件命名使用 kebab-case。
- 不要加入 Emoji、花哨 Unicode 装饰符或无意义注释。
测试要求
- 新功能或行为修正必须补回归测试，优先覆盖：
- CLI 参数与默认目标
- 工作区状态判定
- 全局同步与备份语义
- Spec enable/init/doctor
- 文档与实现的一致性
- 当修改
reference/跟踪策略时，同步更新tests/standards-compliance.test.js。
参考资料与忽略规则
- 不要提交
__pycache__/、*.pyc、.DS_Store、.next/、*.log、*.tmp、.eslintcache、.turbo/、coverage/、dist/、web/tsconfig.tsbuildinfo、临时 tarball、测试临时工作区（如.temp-ling-*、.tmp-ling-*）或其他构建噪声。 reference/使用白名单忽略策略：保留需要受管的官方资料与归档文档，其余快照默认忽略。- 不要重新引入
reference/official-docs/这类重复目录；官方资料只保留一份。
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.
- 3d ago First seen · 77 lines · 1,373 tokens per session scan A d125dfc0368e
Ling AGENTS.md is an instructions file published in the GitHub repository MisonL/Ling (8 stars, last pushed 5mo ago), licensed MIT. It adds 1,373 tokens to every session, about $0.0069 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 2026-09-03.
Other instructions, from other repositories
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).
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.
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 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.