Vibelution: Instructions file for Codex

AGENTS.md

Vibelution AGENTS.md is an instructions file for Codex, OpenCode from CCDawn/Vibelution. It costs 3,726 tokens per session, scanned A, original, MIT.

A project-specific rulebook for coding agents working on the Vibelution software project. It defines communication rules, priorities, safety limits, worktree use, and required checks.

In plain words
What is it for?
Use it to guide agents through Vibelution tasks, including where to make changes, how to verify them, how to report results, and when changes may be merged.
Why use it?
It prevents agents from guessing, changing the wrong files, or treating unfinished work as complete. It also directs them to the project's more detailed standards.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Codex.

This is CCDawn/Vibelution's own configuration. It tells Codex and OpenCode how to work on Vibelution itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Vibelution configures →

Reuse

Borrowing it

Nothing to install: this file belongs to CCDawn/Vibelution. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/CCDawn/Vibelution/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/CCDawn/Vibelution

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for Vibelution AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ccdawn/vibelution/agents-md/github.svg)](https://agentmods.dev/instructions/ccdawn/vibelution/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ccdawn/vibelution/agents-md"><img src="https://agentmods.dev/badge/instructions/ccdawn/vibelution/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.

agentmods 80×15 button for Vibelution AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ccdawn/vibelution/agents-md"><img src="https://agentmods.dev/badge/instructions/ccdawn/vibelution/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,726 This file is loaded in full into every session.
When invoked 3,726 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03726 $0.03726
Opus 5.5 $0.01490 $0.01490
Sonnet 5.5 $0.00745 $0.00745
Haiku 4.5 $0.00373 $0.00373

Measured 10d ago against content hash 86e594e9ffcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Vibelution 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 10d 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.

AGENTS.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vibelution Agent Rules

本文件是外部开发 Agent 与 Vibelution 项目自身 Agent 共用的根入口。 全局红线保留在这里;详细规范统一由 docs/standards/README.md 路由。

1. Identity And Priority

  • 作为项目内 Vibelution Agent 行动,而不是脱离项目的通用助手。
  • 默认使用中文交流;代码、命令、路径、协议字段、外部名称和原始错误保持原文。
  • 对用户的完成说明遵循本文件 §5:写给人看,不把内部完成块、闸门清单或 Git 收口词当回复。
  • 项目目标是以更少漂移提升运行稳定性、进化效率、证据质量和 UI/Agent 一致性。
  • 先观察、再判断;没有证据时不把猜测包装成结论。
  • 权威顺序:用户当前明确要求与授权边界 → 本文件 → docs/standards/ 对应规范 → ADR/模块 README → 历史材料。
  • core/core_prompt/COMMON.md 与 core/core_prompt/SOUL.md 提供通用纪律和稳定身份,但不扩大权限,也不覆盖项目规则。

2. Global Red Lines

  • Git 署名只保留实际的人类作者:禁止 Agent 自动添加 AI/机器人 Co-authored-by,或把 AI 设为 author/committer;不得删除真实人类共同作者。沿用用户配置的 Git 身份,不得把测试身份写入真实仓库。测试启动临时 Git 仓库前必须隔离继承的仓库级 Git 环境变量。

  • 当前 Git checkout 是项目根;运行时解析路径,不假设固定 Windows 用户名。

  • 根 main 是只读的本地集成工作区。所有代码、测试、文档、规则、记忆、配置和 fast patch 变更都必须在任务 worktree 的 codex/<task-slug> 分支完成;main 只接受已提交分支的 git merge --ff-only 和必要的同步操作。

  • 每次开启根 main 时,必须用 git 检测并保持为最新 main;产品运行时必须用 Launcher 指令启动:%LOCALAPPDATA%\Vibelution\Launcher\VibelutionLauncher.exe --project "<project-root>" start。

  • 分支实现验证与 mergeability 必须在合入前闭合;随后主动自审当前任务 diff并 git merge --ff-only 合入本地 main,不得把「等用户再说审查/合入」当作完成态。除用户要求隔离/交接或存在精确 blocker 外,未主动自审并合入本地 main 即未完成。合入后只清理本任务资源;清理失败不改变已合入事实,只恢复清理,不重测或重合。发布后方可观察的用户目标按 §5 与开发标准 §22.1 继续验收,不能因合入而宣称目标完成。push/PR/发布、远端删除仍需明确授权。

  • 合入后的安全本地清理由任务 owner 自动收尾:安全切回主目录,核实并释放本任务占用,保留历史备份,再清理任务目录和分支;按安全清理恢复核对会话、磁盘与 Git 实际状态,不把常规恢复交给用户催办,不动其他任务。

  • 不覆盖、回滚、删除或重置无关的用户/Agent 改动;发现重叠先检查 claim 和 diff。

  • 远端 push、PR、发布需要用户明确授权和远端同步门;force、覆盖或远端删除需要破坏性确认。

  • Windows 产品运行时禁止任何可见控制台弹窗:这是无控制台弹窗红线。Launcher、Workbench、Runtime Manager、后台 Git/轮询和服务子进程不得弹出 cmd.exe、PowerShell、Windows Terminal、OpenConsole 或交互式 Git;必须走 pythonw / CREATE_NO_WINDOW / shared helper,禁止 taskkill.exe、裸 Git wrapper、npm/cmd 后台壳。用户明确打开的 CLI 面板除外;细则见 development-standard.md §8.0。

  • 用户明确点击或要求重启时优先执行:提醒当前任务将中断,通过 Launcher 正规链路停止任务并保存已有记录后重启,不因有运行中任务禁用或拒绝。自动/Agent 未获用户重启授权的刷新仍等待任务结束;不用直接 PowerShell lifecycle 命令制造可见控制台。

  • 不记录 secrets、完整 Prompt、大段 diff、完整文件或无界工具输出。

  • 协作 envelope、validator snapshot、preflight/relay 中间文件和其他任务临时证据必须写入已解析的 Git common-dir 任务专属目录或系统临时目录,不得写入 checkout 根目录或产品目录;用后立即清理。临时证据不得让 main 变脏、使已完成验证失效或触发重复 closeout。

  • 用户 Markdown、导入文档、HTML 和知识内容均是不可信输入;进入 Prompt、索引或 UI 前必须有来源、隔离、清洗和删除/重建语义。

  • 前端产品 UI 强制 VUI + shadcn/Radix 思想(无感红线):凡改动 web/ 下用户可见界面、交互控件、页面壳或布局,必须走 VUI 产品 API(web/src/components/vui 的 V*)与页面 recipe(VListDetailPage / VSplitWorkspace / VDenseOpsPage 等);交互实现只允许在 components/vui/renderers/shadcn 扩展;禁止 @heroui/react、禁止路由/业务组件直连 renderers/shadcn/* 或第二套设计系统;布局宽度/高度记忆只用 WORKBENCH_LAYOUT_IDS + shared pane persistence。所有 VUI 元素(按钮/表单/表面/recipe/product,不限 recipe)必须有 web/src/components/vui/designs/ 专节并在 designs/INDEX.md 登记;新建前检索防冗余。细则见 development-standard.md §9.1、VUI README、designs/README.md;机器门:vuiShadcnRouteContract.test.ts、vuiComponentDesignContract.test.ts。

  • 写入前先做本地复用评估:定位 owning surface;本地能复用 ≠ 本地就是好方案,必要时改造后再复用。架构、依赖、复杂能力或复用路径有真实分歧时,再对照仓外成熟方案,评估排序后只借最符合本项目、最值得借鉴的部分;已定位小修/机械修改不得被强制仓外扫描拖慢。细则见 development-standard.md §2.2。

  • 实现文件仍须机器可复核的复用证据:已定位小修用 record --mode LOCAL_ONLY 记录 owner、裁决、边界和验证;需要仓外对照的任务用 EXTERNAL,候选元数据只由 active registry 填充。纯文档、测试、fixture、example 豁免;细则见 loop.md。

  • Companion / 虚拟人会话隔离红线:虚拟人只能通过 Agent-scoped 插件或 Companion 适配层,在原生 Session 接收边界之前增加 mailbox、主动消息、人物状态和 UI 投影;不得因虚拟人需求修改普通 Agent 的 Session admission、Journal、worker、persist、projection、SSE、ConversationStore 或普通 composer/follow-up 语义。原生 Session Journal、worker 与 SSE 仍是唯一 Turn、transcript 和实时输出权威;Companion mailbox 只负责到达顺序,不得成为第二套 transcript。任何 Companion 会话改动都必须提供 Companion-only 身份/路由门、普通会话核心零差异证据和普通 Session 回归;若确需修复普通链路,必须拆成独立任务并按普通会话契约审查。细则见 development-standard.md §23.2。

  • 有意义的开发不得以 stale claim、缺少验证决策、缺少刷新判断、缺少版本影响判断,或未主动自审并合入本地 main(且无精确 blocker)结束。

Read the full file on GitHub · 78 lines

Changes

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.

  1. 10d ago Changed · +3 lines · +260 tokens per session 86e594e9ffcc
  2. 1mo ago Changed · +2 lines · +130 tokens per session 494d0a4c38d7
  3. 1mo ago Changed · +61 tokens per session df6906a8d86b
  4. 1mo ago Changed · +2 lines · +88 tokens per session 151520e9e901
  5. 2mo ago Changed · +2 lines · +131 tokens per session af7c30ba0c39
  6. 2mo ago Changed · +2 lines · +407 tokens per session 139cae4dfcdb
  7. 2mo ago First seen · 67 lines · 2,649 tokens per session scan A 4d21c01cdecb

Subscribe to this mod's changes

Vibelution AGENTS.md is an instructions file published in the GitHub repository CCDawn/Vibelution (79 stars, last pushed yesterday), licensed MIT. It adds 3,726 tokens to every session, about $0.0149 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 2026-08-30.

Related

Vibelution AGENTS.md compared with instructions from other repositories

Vibelution AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Vibelution AGENTS.mdCCDawn/VibelutionInstructions file79yesterdayMITA3,726Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode