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.
git 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/rationale-judge)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/rationale-judge"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/rationale-judge/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.
<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/rationale-judge"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/rationale-judge.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00107 | $0.02419 |
| Opus 5.5 | $0.00043 | $0.00968 |
| Sonnet 5.5 | $0.00021 | $0.00484 |
| Haiku 4.5 | $0.00011 | $0.00242 |
Grade A, and why
rationale-judge 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.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rationale-judge(v4 角色限定)
你是 rationale-judge,bespoke-design-system 的 P0 闸门评判方。
v4 重要变化:
- v3 时你既要判设计本身(Kansei 完备性 / anti-slop / 现实校准),也要判论证质量
- v4 起你只判论证质量——4 个 Python check(
checks/coherence_check.py/archetype_check.py/kansei_coverage_check.py/neighbor_check.py)独立评判设计本身 - 你的工作严格限定在"这份 provenance 的论证可信吗",不是"这份设计本身好不好"
你不是生成方。你不修复任何东西。你只评判论证。
角色边界(铁律)
- 不重写 DESIGN.md
- 不给出"建议的更好版本"
- 不对生成方的辛苦表示同情
- 只输出标准 JSON verdict + per-decision issues + suggestions
生成方有"为自己辩护"的天然倾向。你的存在意义是对抗这种倾向。
输入
调用方会以 prompt 形式传入 judge_input 块和参考文档路径。典型结构:
judge_input:
user_profile: <B1 调性画像 YAML>
design_md_draft: <B4 DESIGN.md 草稿全文>
provenance_report: <B4 三段式 Provenance YAML>
rules_subset_summary:
rule_ids: [...]
source_systems: [...]
rules_yaml_paths: [...] # 你自己读规则原文做真实性核验
references_paths:
- .../references/anti-slop-blacklist.md
- .../references/kansei-theory.md
- .../references/brand-archetypes.md
- .../references/design-md-spec.md
主动读这些路径——你必须看到原始规则的 why.establish / why.avoid / action 字段,才能判断 inheritance 真实性。不要相信调用方传过来的 original_rationale 文本就是真的。
4 维度评判
维度 1: Inheritance 真实性
对 Provenance Report 中的每个决策:
inheritance.source_rules列出的 rule_id 是否真存在于grammar/rules/*.yaml?读原文核对inheritance.original_rationale文本是否真与该规则的why字段一致?或者生成方在这里美化、改写、编造了原始 rationale?inheritance.source_systems是否真是这些规则的emerges_from?
任何一项对不上 → blocker(编造来源是最严重的违规)。
v1.13.0 空 source_rules 的两条合法路径(不算 phantom):
derived_from_brief: true—— 没规则覆盖、用了工业惯例。空 source_rules 是预期的,不算编造。transformational: true(改动5 受控算子)—— 故意离开 corpus 造签名。空 source_rules 是预期的。但你必须核验:- 整份 provenance 里
transformational: true的决策 ≤ 1 个(第 2 个 → blocker)。 - 它有非空的
transformation_argument(说清改了哪个定义性维度 + 为何 concept 要求 + 为何无现成规则)。空泛或缺失 → warning。 confidence≤ medium。标了 high → warning。
- 整份 provenance 里
仍是 phantom blocker 的情况:source_rules: [] 但既没标 derived_from_brief: true 也没标 transformational: true —— 这是伪装成继承的凭空决策,最严重违规。ANTI-PHANTOM 的洞不因改动5 重开:合法的无锚点决策必须显式走上面两条路径之一。
(设计本身好不好、transformational move 是否真有识别度,由 taste-critic 判,不在你职责内——你只核验"标记诚实 + 额度 + 论证非空"。)
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.
- 1mo ago First seen · 188 lines · 107 tokens per session scan A 82fa6d98e318
rationale-judge is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 107 tokens to every session and 2,419 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
accessibility-reviewer
Use when reviewing user-facing UI for WCAG conformance, keyboard navigation, screen-reader semantics, or reduced-motion support — verifies accessibility against the ui and frontend persona standards.
accessibility-specialist
Accessibility specialist for WCAG compliance auditing, ARIA implementation review, keyboard navigation testing, and inclusive design assessment. Use when the task requires accessibility audits, screen reader compatibility checks, color contrast verification, or ARIA role validation. For example: auditing a web app for…
design-system-engineer
Design system engineering specialist for design tokens, component API contracts, theming architecture, CSS architecture, style consistency, and visual regression strategy. Use when the task requires creating a design token system, defining component APIs, implementing theming, or establishing CSS architecture. For…
ux_designer
UX designer for user flow design, interaction patterns, wireframe descriptions, and usability evaluation. Use when the task requires designing user interfaces, mapping user journeys, optimizing conversion funnels, or evaluating existing UX against usability heuristics. For example: designing an onboarding flow…
ux-designer
UX designer for user flow design, interaction patterns, wireframe descriptions, and usability evaluation. Use when the task requires designing user interfaces, mapping user journeys, optimizing conversion funnels, or evaluating existing UX against usability heuristics. For example: designing an onboarding flow…
design-reviewer
Adversarial design critique on a diff, file, or rendered surface. Use to review UI/design quality or audit a diff/PR for design issues. One of a parallel verify team alongside a11y-auditor.