Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/sourcelin/sourcelin-cloud-blog/agents-mdgit clone --depth 1 https://github.com/SourceLin/sourcelin-cloud-blogWhat 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 | $0.02895 | $0.02895 |
| Opus 5 | $0.01448 | $0.01448 |
| Sonnet 5 | $0.00579 | $0.00579 |
| Haiku 4.5 | $0.00290 | $0.00290 |
Grade A, and why
sourcelin-cloud-blog 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 2d 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 — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件是 Sourcelin Cloud Blog 仓库级 AI 执行入口。所有 AI 编程工具进入本仓库后必须先读取本文件,再按任务读取对应 rules/ 和 skills/。
默认使用中文进行沟通、注释、提交说明和文档更新。所有文本文件保存为 UTF-8 无 BOM。
1. 项目范围
Sourcelin Blog 是基于 Sourcelin-Cloud v3.6.3 的微服务博客平台。
后端:
sourcelin-api/ # Feign 接口与跨服务 DTO
sourcelin-common/ # 公共能力,不放业务逻辑
sourcelin-gateway/ # 网关
sourcelin-auth/ # 认证中心
sourcelin-modules/ # 业务服务
sourcelin-system/ # 系统管理
sourcelin-blog/ # 博客业务
sourcelin-file/ # 文件服务
sourcelin-job/ # 定时任务
sourcelin-visual/ # 监控等可视化服务
前端:
sourcelin-ui/sourcelin-ui-platform/ # 博客前台,Vue3 + TypeScript + Naive UI 抽象层
sourcelin-ui/sourcelin-ui-uniapp/ # 移动端小程序,Uniapp + Vue3 + TypeScript
sourcelin-ui/sourcelin-ui-admin/ # 管理后台主线,Vue3 + TypeScript + Element Plus
sourcelin-ui/sourcelin-ui-admin-vue2/ # 旧版迁移对照,不承载新功能
2. 开源分支边界
scripts/**不进入开源分支提交。docs/**可以进入开源分支,但docs/internal/**不提交。- 规则、技能和执行入口必须避免引用开源分支未提交的本地维护脚本。
- 数据库初始化文档和 SQL 维护在
docs/sql/**。
3. 仓库发布模型
origin/master:公开发布分支,只承载对外可见内容。develop:日常开发分支,承载功能开发、规则演进和阶段性整理。master:公开发布分支,对外只暴露稳定版本。- 日常开发必须先进入
develop,完成验证后再整理到master。 - 对外发布必须以
master为唯一来源,最终推送到origin/master。 - 发布前必须完成公开边界检查,确保内部脚本、过程文档和仅内部使用的资料不会进入公开分支。
- MUST NOT:跳过
develop直接在master上做日常开发。 - MUST NOT:将
develop、内部脚本或过程性资料直接推送到公开仓库。
4. 默认规则
每次开发、重构、审查或测试必须读取:
-
rules/README.md -
rules/api-contract.md -
rules/coding-conventions.md -
rules/testing-and-validation.md
按任务追加读取:
-
后端:
rules/backend.md -
博客前台:
rules/frontend-platform.md,并联查sourcelin-ui/sourcelin-ui-platform/AGENTS.md -
Uniapp 移动端:
rules/frontend-uniapp.md,并联查sourcelin-ui/sourcelin-ui-uniapp/AGENTS.md -
管理后台:
rules/frontend-admin.md
规则优先级:
-
本文件
-
更近目录的
AGENTS.md/rules/ -
rules/api-contract.md -
领域规则
-
rules/coding-conventions.md -
rules/testing-and-validation.md
5. 可用技能
skills/frontend-platform-dev/SKILL.md:博客前台开发。
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.
- 2d ago First seen · 422 lines · 2,895 tokens per session scan A 137ce7b57da9
sourcelin-cloud-blog AGENTS.md is an instructions file published in the GitHub repository SourceLin/sourcelin-cloud-blog (20 stars, last pushed 2mo ago), licensed MIT. It adds 2,895 tokens to every session, about $0.0145 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 2026-08-30.
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.