design-brand-identities

design-brand-identities is a skill for Codex from EverMind-AI/Raven. It costs 178 tokens per session (8,995 once invoked), scanned A, original, Apache-2.0.

A brand-identity design workflow for creating or updating how an organisation, product, service, place, project, or person looks and communicates. It delivers realistic examples such as a website, package, shop, business card, or social post, along with a toolkit of logo directions, colors, fonts, imagery, and guidelines.

In plain words
What is it for?
Use it to develop names and wordmarks, logo systems, color and type choices, image direction, messaging elements, brand architecture, or a brand refresh and migration.
Why use it?
It helps a new or changing identity look consistent across real-world uses instead of being just an isolated logo or one promotional image. The examples show how the identity works, while the toolkit lets others continue using it.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: $skill-name invocation.

Good fit Use it to develop names and wordmarks, logo systems, color and type choices, image direction, messaging elements, brand architecture, or a brand refresh and migration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/evermind-ai/raven/design-brand-identities
About the project

Raven is an open-source agent harness for running long-term AI work with terminal execution, tracing, memory, skills, evaluation, and reusable workflows. People use the current release to operate and improve persistent AI workflows, while its described future direction is a multi-agent system that combines specialized harnesses.

EverMind-AI/Raven · 5,463 stars · on GitHub · raven.evermind.ai

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.

Any agent
npx skills add EverMind-AI/Raven --skill design-brand-identities
Clone the repo
git clone --depth 1 https://github.com/EverMind-AI/Raven

Made for: Codex.

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 design-brand-identities

README.md
[![agentmods](https://agentmods.dev/badge/skills/evermind-ai/raven/design-brand-identities/github.svg)](https://agentmods.dev/skills/evermind-ai/raven/design-brand-identities)
Your own site
<a href="https://agentmods.dev/skills/evermind-ai/raven/design-brand-identities"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/design-brand-identities/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 design-brand-identities

Your own site · 80×15
<a href="https://agentmods.dev/skills/evermind-ai/raven/design-brand-identities"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/design-brand-identities.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 178 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,995 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00178 $0.08995
Opus 5.5 $0.00071 $0.03598
Sonnet 5.5 $0.00036 $0.01799
Haiku 4.5 $0.00018 $0.00899

Measured 1mo ago against content hash 745434f52f89, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

design-brand-identities 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 1mo 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.

plugins-dist/design-engine/raven_design/skills/design-brand-identities/SKILL.md · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.

设计品牌识别

核心目标

让用户在看到产物的三秒内相信:这个品牌已经存在,做出来就是这样。交付两样东西:一组品牌示例 (官网首屏、门店、包装、名片、社媒帖等最终效果,看不出是效果图)和一个品牌工具包(文件夹, 里面是这套品牌的方向与工具:标志方向、色表、字体建议、图像调子、信息要素、参考设计、指南)。 示例给人看效果做决定,工具包让人能接着把它做成正式生产文件。我们做的是示例与方向,不是印刷厂 文件;但示例必须像真的一样,不打水印、不标"示意"、不用占位。

遵循四个原则:

  1. 最小系统。 从一个主要标志载体、少量颜色、有限字体、一种图像调子和一种语气开始。这里的数量是 默认探索上限,不覆盖用户已有的品牌规范、既有生产系统或明确的交付要求;超出默认上限时,记录每个新增 颜色或字体的职责与消费者。
  2. 同一个世界。 全部示例与工具包文件必须像同一家公司在同一天拍的:同一主色、同一字体口吻、 同一光线与材质、同一标志。一帧飘了整组判不合格。
  3. 触点由用户决定,基础工具由本 Skill 决定。 用户列出的触点逐个做成示例;用户没列的标志、色、 字、语气照样交付。
  4. 像真的一样。 场景是真实的场所与光线,材质可信,文字拼写正确,标志清楚;效果图里出现的一切 都应该能在现实中被这样做出来。

本 Skill 只拥有品牌领域判断。品牌触点保持介质中立,必须在各自的目标媒介和最终消费者中验证,并记录最终像素或等价终态。 流程与证据服从共享 $visual-artifact-design。只有最终消费者是 Web,或合同明确要求 Web 交付时,才组合 $build-polished-visual-frontends;该 Skill 负责 Web 实现,品牌 Skill 继续负责身份系统。每个使用的字体、图像、 商标或生成资产都要记录来源、许可与替换边界。完整字体家族转交 字体领域;单个功能含义转交图标领域;一次性传播转交营销领域;产品工作流转交产品界面领域。

什么算好,七条判据(后文以代号引用):

  • B1 一个颜色世界:示例帧被一个主色统治,其余色只做点缀或功能;不是"色板有五个色"。
  • B2 一种字体口吻:标题与正文的字面、字重关系在所有帧里相同,能用一个词说出它的性格。
  • B3 一种图像调子:光线、背景、道具、裁切、有无人物一致,能用一句话描述。
  • B4 标志与文案在场景里:标志出现在真实载体上(网页、包装、招牌、名片),语气随之出现;孤立的 标志放大页不算示例。
  • B5 可溯源一致:示例里每个可见元素能指向工具包里的一项;工具包里每项工具至少在一帧示例中被使用。
  • B6 近邻可分:示例帧与两个真实近邻并排缩略时,一眼能分出是谁;靠的是结构关系,不是更亮的颜色。
  • B7 像真的:没读过任务的人把示例帧当成真实品牌的照片或网页;场景、材质、光线可信,文字无 乱码,标志无变形。

1. 先读懂任务,再决定做什么

新建或大改前,先在 BRAND-BRIEF.md 写一张品牌决策卡:

主体: 正式名称、简称、语言读序、所有权或背书关系
身份任务: 谁在什么重复场景认出它,与哪些真实近邻区分,认错的代价是什么
任务触点与范围: 记录用户或主代理提出的触点,区分示例清单与明确范围限制;有子任务分工时,记录当前任务负责和不负责的内容
交付档位: logo_kit | basic | full | social_kit | packaging_kit
示例帧清单: 每个触点一帧 + 一帧定调帧(官网首屏 | 产品图 | 平铺 | 空间实景)
表达强度: quiet | editorial | expressive
硬约束: 用户禁忌、既有资产、语言、接收方
未知与阻断: 名称未定阻断什么、关系未定阻断什么

硬约束只来自用户要求、既有资产、语言和接收方;模型偏好的气质、色相、"想做得更完整"都不是硬约束。 mode 分 create / edit / govern / diagnose:create 与改变核心的 edit 走完整流程;主体已有标识(按 $visual-artifact-design 的既有身份盘点)时,create 默认为延展:既有标识按 $visual-artifact-design 的三档阶梯取用后作为 logo/ 母版,新工作落在色、字、应用层,reference_route 即 accepted_system;只有用户明说"重新设计 / 换标"才重做标识。窄 edit 只从最早失效的一步进入;govern 先核验已批准资产与消费者;diagnose 只读复现与定位。品牌架构、 焕新迁移、动态识别的专项模式按需读取品牌模式与检查。

Read the full file on GitHub · 369 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago First seen · 369 lines · 178 tokens per session scan A 745434f52f89

Subscribe to this mod's changes

design-brand-identities is a skill published in the GitHub repository EverMind-AI/Raven (5,463 stars, last pushed today), licensed Apache-2.0. It adds 178 tokens to every session and 8,995 once invoked, about $0.0007 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 2026-09-12.