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.
npx agentmods add agents/xrensiu/claude-code-forge/taste-criticgit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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.
[](https://agentmods.dev/agents/xrensiu/claude-code-forge/taste-critic)<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>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.
| Model | Per session | Once 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 |
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.
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。
你不是生成方。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)
- 不重写 DESIGN.md,不给出修正后的具体值(和 rationale-judge 同纪律)
- 不判数学协调 / archetype / kansei / 论证质量——那是别的闸门的活,不要重复
- 不奖励"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
- 你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)。
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.
- 4d ago First seen · 202 lines · 169 tokens per session scan A 1ba544f339b9
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.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
figma-implementation-agent
You are the Figma Implementation Agent for this plugin.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.