agentmods.dev

visual-multimedia AGENTS.md

visual-multimedia AGENTS.md is an instructions file for Codex, OpenCode from CheshireMew/visual-multimedia. It costs 1,890 tokens per session, scanned A, original, MPL-2.0.

Project instructions for the visual-multimedia repository, which produces reusable media packages and shared data formats. They define which files are authoritative and when changes must also be checked in MediaFlow Pro.

In plain words
What is it for?
Use them when changing media schemas, sample assets, deterministic playback controls, synchronization scripts, or integrations with MediaFlow Pro.
Why use it?
They prevent different tools or repositories from developing conflicting versions of the same media formats, assets, and timing rules.

Instructions file for CodexOpenCode

not rated 24 4d ago A scan 1,890 tokens original MPL-2.0
View the source file CheshireMew/visual-multimedia
Install

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.

agentmods
npx agentmods add instructions/cheshiremew/visual-multimedia/agents-md
Clone the repo
git clone --depth 1 https://github.com/CheshireMew/visual-multimedia

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 visual-multimedia AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cheshiremew/visual-multimedia/agents-md.svg)](https://agentmods.dev/instructions/cheshiremew/visual-multimedia/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cheshiremew/visual-multimedia/agents-md"><img src="https://agentmods.dev/badge/instructions/cheshiremew/visual-multimedia/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,890 This file is loaded in full into every session.
When invoked 1,890 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01890 $0.01890
Opus 5 $0.00945 $0.00945
Sonnet 5 $0.00378 $0.00378
Haiku 4.5 $0.00189 $0.00189

Measured 5d ago against content hash 97a444665b1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual-multimedia 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 5d 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

visual-multimedia 项目协作规则

项目定位

本仓库是媒体制作流程和通用媒体合同的生产者。MediaFlow Pro 是正式消费者之一，但不是本 Skill 的唯一实现工具。网页包、素材声明和确定性时间边界必须保持产品无关，不能在通用合同中写入 MediaFlow 专用字段、项目数据库结构或内部路径。

维护本仓库本身不等于启用 visual-multimedia Skill。除非用户明确要求使用 Skill，否则按普通仓库维护任务处理。

共享边界与唯一真源

  • schemas/editable-media.v6.schema.json 是 editable-media v6 清单结构的唯一真源。
  • assets/web-media-starter/ 和 assets/web-card-cases/ 是生产者真实输出及跨仓库合同案例的唯一来源。assets/web-layout-templates/catalog.json 是可实例化布局模板的唯一目录；模板只能引用生产者包，不能反向把案例变成默认模板或视觉源。消费端不得手写等价假数据代替这些输出。
  • window.editableMedia 是结构化编辑状态入口，window.__hf.duration/seek(seconds) 是确定性逐帧时间入口。运行时、校验器和消费者必须读取同一边界，不能增加第二套时钟或恢复逻辑。
  • references/structured-media-editor-cli.md 只记录 Skill 如何使用公开编辑器能力。MediaFlow Pro 的操作名称、参数和功能可用性以实际 mediaflow-cli describe 输出为真源，本仓库不得复制维护另一份 CLI 定义。
  • MediaFlow Pro 内嵌的 schema 和测试案例是本仓库真源的同步快照，只能通过 scripts/sync_visual_multimedia_fixture.py 从本仓库单向更新。

何时必须联动 MediaFlow Pro

修改以下任一边界前，必须同时检查 E:\Work\BaiduSyncdisk\Code\MediaFlow Pro：

  • editable-media schema、协议版本、字段语义、默认继承、场景、变体、图层、质量规则或 production 元数据；
  • assets/web-media-starter/、作为合同案例使用的 assets/web-card-cases/，以及它们的入口、运行时或素材账本；
  • window.editableMedia、window.__hf、随机定位、画布尺寸、透明合成或逐帧稳定性；
  • editable-media 所使用的 media-sources 字段、browser、native-underlay、native-audio 管线及原片与代理解析；
  • validate-editable-media.mjs、editable-media-contract.mjs、素材导入或表示解析中会改变消费端输入的行为；
  • structured-media-editor-cli.md 中依赖的公开能力，或任何直接创建、修改、渲染、导出 MediaFlow Pro 项目的正式生产链路；
  • 采访原声讲解型等 profile 对 MediaFlow Pro 工程、片段状态、帧范围、字幕或导出结果的约束。

纯媒体文案、视觉配方、声音配方、角色制作或其它没有改变上述输入输出合同的修改，不要求为了形式同时修改 MediaFlow Pro。先判断是否穿过共享边界，不得把两个仓库无条件绑成每次都一起改。

联动修改规则

共享边界发生变化时，这次任务必须同时完成生产者、同步边界、消费者和最终可见结果的迁移，不能只在一边留下待办。

  1. 先在本仓库确定新的唯一合同，更新 schema、生产运行时、starter、真实案例、校验器和全部调用点。
  2. 在 MediaFlow Pro 中运行同步脚本，更新内嵌 schema、真实生产者案例及来源哈希；不得直接手改同步副本。
  3. 根据新合同一次性更新 MediaFlow Pro 的解析、项目状态、编辑操作、浏览器渲染、原生媒体管线、缓存、时间线和导出消费者。
  4. 回到本仓库核对公开 CLI 能力和正式生产流程，确保 Skill 只使用 describe 实际声明的操作。
  5. 删除旧字段、旧类型、旧 helper、旧分支、旧恢复逻辑和旧导出。需要破坏性变更时明确升级协议并一次性迁移两边，不在同一活动架构中长期并存新旧合同。

Read the full file on GitHub · 75 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. 5d ago First seen · 75 lines · 1,890 tokens per session scan A 97a444665b1a

Subscribe to this mod's changes

visual-multimedia AGENTS.md is an instructions file published in the GitHub repository CheshireMew/visual-multimedia (24 stars, last pushed 4d ago), licensed MPL-2.0. It adds 1,890 tokens to every session, about $0.0095 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.

agent-skillaudio-editingcodexdata-visualizationmultimediavideo-editing
Related

Other instructions, from other repositories

semiotic CLAUDE.md

Claude Code instructions for nteract/semiotic, covering semiotic claude code instructions and claude code notes.

nteract/semiotic · 129 tokens

mcp-steroid CLAUDE.md

Claude Code instructions for jonnyzzz/mcp-steroid, covering claude.md, agents.md, design philosophy, recursive context lookup (do this before sub-folder work), sub-folder guides and must do.

jonnyzzz/mcp-steroid · 6,916 tokens

nopua AGENTS.md

Instructions for wuji-labs/nopua, covering nopua · codex 入仓规则, 一 · 项目定位, 二 · 起手必读, 三 · 工程与研究纪律 and 四 · 对外署名.

wuji-labs/nopua · 546 tokens

streamlit e2e_playwright.instructions.md

Instructions for streamlit/streamlit, covering streamlit e2e tests, test structure, key fixtures and utilities, external test mode and url handling (no localhost hardcoding).

streamlit/streamlit · 2,431 tokens

leclap CLAUDE.md

Instructions for heristop/leclap: This repository's agent guidance lives in AGENTS.md — read it first; it is the single source of truth for structure, commands, and conventions.

heristop/leclap · 83 tokens

skills CLAUDE.md

Instructions for mixedbread-ai/skills, covering mixedbread skills, repository structure, conventions, adding a new skill and testing a skill.

mixedbread-ai/skills · 1,225 tokens