rationale-judge

rationale-judge is an agent for coding agents from XRenSiu/claude-code-forge. It costs 107 tokens per session (2,419 once invoked), scanned A, original, MIT.

A review agent for checking whether the reasoning behind a design document is trustworthy. It examines the evidence and explanations supporting design decisions, rather than judging how attractive the design is.

In plain words
What is it for?
Use it to audit a design document’s decision record, verify that cited rules were applied accurately, and return a structured verdict with issues and suggestions.
Why use it?
It helps catch unsupported claims, misleading explanations, and decisions that do not follow from the referenced rules or evidence. It does not rewrite the design.

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/rationale-judge
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 rationale-judge

README.md
[![agentmods](https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/rationale-judge.svg)](https://agentmods.dev/agents/xrensiu/claude-code-forge/rationale-judge)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 107 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,419 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 $0.00107 $0.02419
Opus 5 $0.00053 $0.01210
Sonnet 5 $0.00021 $0.00484
Haiku 4.5 $0.00011 $0.00242

Measured 4d ago against content hash 82fa6d98e318, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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/rationale-judge.md · 188 lines

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"

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)

  • 重写 DESIGN.md
  • 给出"建议的更好版本"
  • 对生成方的辛苦表示同情
  • 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:

  1. inheritance.source_rules 列出的 rule_id 是否真存在于 grammar/rules/*.yaml?读原文核对
  2. 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?
  3. 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)

  1. derived_from_brief: true —— 没规则覆盖、用了工业惯例。空 source_rules 是预期的,算编造。
  2. 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。

仍是 phantom blocker 的情况source_rules: []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"。)

Read the full file on GitHub · 188 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 · 188 lines · 107 tokens per session scan A 82fa6d98e318

Subscribe to this mod's changes

rationale-judge is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 2,419 once invoked, about $0.0005 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.