Flovart: Instructions file for Codex

AGENTS.md

Flovart AGENTS.md is an instructions file for Codex, OpenCode from avabbbb/Flovart. It costs 3,256 tokens per session, scanned A, original, MIT.

Project instructions for Flovart covering its agent guidance, role definitions, general principles, accumulated reminders, and backend conventions.

In plain words
What is it for?
They help shape agent roles, apply project rules, preserve lessons learned, and follow backend development conventions.
Why use it?
They provide the project context an agent needs to follow Flovart’s expected behavior and implementation style.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions AGENTS.md; mentions Codex.

This is avabbbb/Flovart's own configuration. It tells Codex and OpenCode how to work on Flovart 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 Flovart configures →

Reuse

Borrowing it

Nothing to install: this file belongs to avabbbb/Flovart. 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/avabbbb/Flovart/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/avabbbb/Flovart

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 Flovart AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/avabbbb/flovart/agents-md"><img src="https://agentmods.dev/badge/instructions/avabbbb/flovart/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,256 This file is loaded in full into every session.
When invoked 3,256 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 $0.03256 $0.03256
Opus 5.5 $0.01302 $0.01302
Sonnet 5.5 $0.00651 $0.00651
Haiku 4.5 $0.00326 $0.00326

Measured today against content hash cf3a23a3656b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Flovart 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 today.

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 · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

本文件约束 Flovart的 AI / 自动化开发。优先级:系统/开发者指令 > 用户当前明确要求 > 本文件 > 项目文档。用户已确认的新决定覆盖旧稿;历史文档不得反向改变当前产品方向。

0. 品牌规则

  • 对外产品名称统一为 Flovart:新 UI、标题、按钮、宿主面板、README 和当前文档不再引入 Iris 品牌。
  • CLI、Skill、package、环境变量和命令中已有的 flovart 保持不动。
  • 旧 iris-* 的数据库字段、协议字段、持久化 key、兼容 ID 与已存素材路径保持兼容,不做全局替换;纯展示、CSS 和新导出文件名可以清理。
  • 当前 canonical GitHub repository 经核验为 avabbbb/Flovart。仓库或协议迁移不得混入普通品牌清理。
  • 历史归档和更名前的视频可保留原始名称,引用时说明历史背景。

1. 开始前先确认当前事实

开始任何实质修改前,先读:

  1. docs/index.md
  2. 与任务相关的 current-truth 文档
  3. 真实代码与 SUPPORT_MATRIX.md

产品与系统目标由 docs/design/00-overview.md(总体设计)定义;所有交互遵守 docs/design/01-interaction.md(简单直接、不硬编码、不死锁);模块细节见 docs/design/1x-*.md。不要从 archive、旧 audit、release evidence 或 Git 历史推导当前需求。

会变化的 SDK、宿主 API、许可证、模型/Provider 能力必须按当前日期核验官方文档和真实源码。构建通过、mock 通过、manifest 存在都不等于真实宿主/账号已认证。

2. 当前产品边界

产品目标(三个场景):

  1. 游戏素材替换(暂缓,当前不在 Reverse 中提供):把游戏复刻 demo 里占位的美术与音效,用 Flovart 批量替换为可发布的原创素材;Agent 自动执行,并记住用户的个人美术风格偏好(memory)。
  2. 爆款视频逆向:像 Hypit 一样把爆款视频拆成 Script → 转写证据 → 对齐 → Timeline → 轨道,再用用户自己的 AI 数字人角色批量、高并发、低时延地制作变体,支持快速投流。
  3. 剪辑宿主插件:在达芬奇 / 剪映中作为插件,Agent 直接读取时间轴、图层和素材库作为上下文,不需要用户再手动上传;可对指定片段做人物替换、绿幕背景、AI 特效,或生成剪辑用素材。

顶级产品 surface 固定为 Canvas | Reverse | Agent(原 Table 位改为 Reverse,不再保留 table 视图):

  • Canvas:空间化 Workflow,用户与 Agent 操作同一份可见生产状态。

  • Reverse(逆向):按 Hypit 代码架构与功能复刻的视频逆向工作台(Studio 式:库 / 预览 / 时间线 lane / Inspector)。二次开发:逆向工程可一键转成 Canvas 上的子画布节点,双击子画布回到 Reverse;两边走同一 workflow.apply 边界联动。详见 docs/design/11-reverse.md。

  • Agent:本地/外部 Coding Agent 的发现、准备、状态与切换中心。

  • Assistant / Context / History:只在 Canvas / Reverse 的 contextual drawer 中,不复制到 Agent 页。

    Hypit 复刻边界:以 gitignored 的 _ref/hypit 为参照,对齐包分层、数据模型、术语与数据流,代码在 services/reverse/ 自写;不复制 Hypit 源文件,不把 @hypit/* 打进 bundle(附加条件的 Apache-2.0 要求衍生品同许可、禁止商业再分发与多租户托管,与本仓库 MIT 冲突)。WhisperX / ffmpeg / 渲染等本地能力走本地 Runtime 或用户自装的 hypit CLI,结果作为 durable artifact 导回。

    不要重新引入 Agent full-page chat、Tasks/Artifacts/Context 工作区、Production Crew / Director / Operator 必经层、Production Skill Marketplace 或第二套 Canvas/Workflow。

Read the full file on GitHub · 149 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. today Changed · +8 lines · +473 tokens per session cf3a23a3656b
  2. 22d ago Changed · +3 lines · +249 tokens per session 7f73c317ef9e
  3. 28d ago Changed · +8 lines · +294 tokens per session 5eadbc390297
  4. 1mo ago Changed · +3 lines · +214 tokens per session d2c379cd6eaa
  5. 1mo ago Changed · +36 lines · -891 tokens per session ca8257a5f804
  6. 1mo ago Changed · -18 lines · -77 tokens per session b77260755d00
  7. 1mo ago Changed · +1 lines · +81 tokens per session c0c3f77b11a2
  8. 2mo ago Changed · +1 lines · +101 tokens per session 5e6ebe42fccd
  9. 2mo ago First seen · 107 lines · 2,812 tokens per session scan A d70a2fb337b8

Subscribe to this mod's changes

Flovart AGENTS.md is an instructions file published in the GitHub repository avabbbb/Flovart (145 stars, last pushed today), licensed MIT. It adds 3,256 tokens to every session, about $0.0130 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

Flovart AGENTS.md compared with instructions from other repositories

Flovart AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Flovart AGENTS.mdavabbbb/FlovartInstructions file145todayMITA3,256Codex, 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