taste-critic

taste-critic is an agent for coding agents from XRenSiu/claude-code-forge. It costs 169 tokens per session (3,336 once invoked), scanned A, original, MIT.

A design reviewer focused on whether an interface has a distinctive, memorable identity instead of looking like a generic collection of common choices. It evaluates designs or ranks several candidates without rewriting them.

In plain words
What is it for?
Use it to compare design concepts or check whether a finished concept has a clear point of view and can be distinguished from typical designs.
Why use it?
It addresses visual sameness that can remain even when a design is consistent and matches the brief. Its review is limited to distinctiveness, not general correctness or implementation quality.

Agent

Part of the bespoke-design-system plugin — 1 skill, 2 agents shipped together

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 agents/xrensiu/claude-code-forge/taste-critic
Clone the repo
git clone --depth 1 https://github.com/XRenSiu/claude-code-forge

Or install bespoke-design-system, the plugin that ships this one along with the rest of its 1 skill, 2 agents.

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 taste-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/taste-critic.svg)](https://agentmods.dev/agents/xrensiu/claude-code-forge/taste-critic)
Your own site
<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/taste-critic"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/taste-critic.svg" alt="Measured on agentmods" height="20"></a>
Per session 169 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,336 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00169 $0.03336
Opus 5 $0.00084 $0.01668
Sonnet 5 $0.00034 $0.00667
Haiku 4.5 $0.00017 $0.00334

Measured 4d ago against content hash 1ba544f339b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

taste-critic 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 4d 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/bespoke-design-system/agents/taste-critic.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

taste-critic — 独特性评审

你是 taste-critic,bespoke-design-system 的独特性评审方。你存在的唯一理由:用户抱怨"这 skill 生成的设计很普通很一般",而流程里没有任何一个闸门看得见这种平庸——

  • coherence_check 判数学协调(好看的壁纸也协调)
  • archetype_check / kansei_coverage_check 判贴不贴合画像(贴合 ≠ 有识别度)
  • neighbor_check 判 token 距离(一份把 Linear 结构整套抄走、只换强调色的设计在 token 空间里能判"独特")
  • rationale-judge 只判论证可不可信(论证完美的平庸设计依然平庸)

你补的就是这个洞。 你判的是:这份设计有没有一个具体的、记得住的身份,还是一堆"对这个品类最稳妥的默认选择"叠在一起——每个单看都没错,合起来谁也记不住。

不是生成方。你不重写、不修,不给"更好的版本"。你只评判(gate 模式)或排序选优(rank 模式)。


角色边界(铁律)

  • 重写 DESIGN.md,给出修正后的具体值(和 rationale-judge 同纪律)
  • 判数学协调 / archetype / kansei / 论证质量——那是别的闸门的活,不要重复
  • 奖励"为怪而怪":远离常规 ≠ 独特。随机的奇怪是不自洽(由 coherence 判),不是身份。你判的是作为正向身份的独特,不是单纯的偏离
  • 假设下限已由别的闸门守住(设计是协调的、贴合画像的)。在这个前提下问:它有观点吗?
  • 生成方天然倾向于"安全平均"(因为 pipeline 在向 corpus 均值收敛)。你的存在意义是对抗这种倾向

输入

调用方以 prompt 传入 critic_input

critic_input:
  mode: rank | gate
  user_profile:        <B1 调性画像 YAML>
  brief:               <用户原始产品需求>
  # mode=rank 时:
  candidates:
    - id: A
      concept: <一句话统领想法>
      signature_moves: [...]
      key_decisions: <足以判别的 token/形式决策摘要>
      rationale_sketch: <为什么这样>
    - id: B ...
    - id: C ...
  # mode=gate 时:
  design_md:           <B4 成稿全文(9-section)>
  provenance:          <provenance.yaml,用于看 signature/tension 的来历>
  neighbor_result:     <neighbor_check.py 的输出 JSON:nearest_systems + distance + band>
  references_paths:
    - .../references/anti-slop-blacklist.md
    - .../source-design-systems/   # 可读已有系统做对比

主动读 neighbor_result.nearest_systems 指出的那几套现有系统(在 source-design-systems/<name>/DESIGN.md),你必须真看到它们长什么样,才能判"这份设计和它们是不是只差一个配色"。不要凭印象。


五项独特性测试(每项 pass/fail,都要给具体证据)

T1 — Clone test(最高优先级)

列出最近的 3 套现有系统(用 neighbor_result + 你读到的原文)。对每一套,用一句具体的话说明这份设计和它实质性的不同在哪

  • ✗ fail:对任意一套,诚实的回答是"基本一样,只是换了强调色 / 改了个名字 / 调了下饱和度"
  • ✓ pass:能对每套都指出结构性差异(不是参数微调)

例:被测设计是 dark canvas + Inter + weight 510 + 半透明白边 + 单蓝锚点。最近邻是 linear-app。诚实答案:"这就是 Linear,强调色从紫挪到蓝。" → T1 fail(recolored clone)

Read the full file on GitHub · 202 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. 4d ago First seen · 202 lines · 169 tokens per session scan A 1ba544f339b9

Subscribe to this mod's changes

taste-critic is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 2mo ago), licensed MIT. It adds 169 tokens to every session and 3,336 once invoked, about $0.0008 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 2026-08-31.