Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/XRenSiu/claude-code-forgenpx agentmods add skills/xrensiu/claude-code-forge/persona-judgeWrote 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/skills/xrensiu/claude-code-forge/persona-judge)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/persona-judge"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/persona-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/skills/xrensiu/claude-code-forge/persona-judge"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/persona-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 | $0.00113 | $0.02951 |
| Opus 5.5 | $0.00045 | $0.01180 |
| Sonnet 5.5 | $0.00023 | $0.00590 |
| Haiku 4.5 | $0.00011 | $0.00295 |
Grade A, and why
persona-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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
persona-judge
把"这个 persona 到底像不像"从直觉变成分数。
Announce at start: "I'm using the persona-judge skill to run the 3-test / 12-dimension / density evaluation pipeline and emit a validation-report.md."
没有量化评估的蒸馏就是玄学，质量无法改进。 (PRD §9.5)
A distillation without quantitative evaluation is mysticism — quality cannot improve.
Overview
persona-judge 是整个 persona-distill 生态的质量闸门。它回答一个问题：
"这个 persona skill 到底有多像本人，以及它的'像'能不能被复现和追踪？"
输出是一份严格符合契约的 validation-report.md——frontmatter 被 distill-meta 机读用于 gating，body 被人类读用于改进。判决分 PASS / CONDITIONAL_PASS / FAIL 三档，全部可追溯到具体维度分数与测试证据。
Two Trigger Modes
| 模式 | 来源 | 入参 | 输出 |
|---|---|---|---|
| Auto | distill-meta Phase 4 自动回调 |
persona skill 根目录 + 本次 distill session id | validation-report.md + frontmatter 供 meta 读取 |
| Manual | 用户说 "evaluate X persona skill" / "评估 X persona skill" | persona skill 根目录（可任何来源，不必是 distill-meta 产出） | 同上 |
两种模式流程完全一致，区别仅在调用方如何消费结果。在 Auto 模式下，distill-meta 只读 frontmatter 字段做门禁判断；Manual 模式下完整展示 body 给用户。
Input Contract
输入只有一个：一个 persona skill 的根目录路径（例如 ~/skills/steve-jobs-mirror/）。
执行前必须：
- 确认目录存在且包含
SKILL.md、manifest.json。 - 用
../../contracts/manifest.schema.json校验manifest.json。校验失败 → 直接verdict: FAIL，dimensions 全 0，critical_failures: 12，并在Recommended Actions中给出 schema 违规列表。 - 从 manifest 读出
schema字段（9 种之一）和components[]，用于后续维度评分的上下文感知（例如internal_tensions仅对public-mirror/mentor强要求）。
Evaluation Pipeline (5 Steps)
┌──────────────────────────────────────────────────────────────────┐
│ Step 1 LOAD 加载 persona skill + 校验 manifest │
│ ↓ │
│ Step 2 3-TEST 运行 Known / Edge / Voice 三项测试 │
│ ↓ 详见 ./references/three-tests.md │
│ Step 3 12-DIM SCORE 按 rubric 打分 12 个维度 │
│ ↓ 详见 ./references/rubric.md │
│ Step 4 DENSITY 反向使用 anti-distill 分类器计算密度 │
│ ↓ 详见 ./references/density-scoring.md │
│ Step 5 EMIT REPORT 生成 validation-report.md + 历史快照 │
│ 遵守 ../../contracts/ │
│ validation-report.schema.md │
└──────────────────────────────────────────────────────────────────┘
What ships with it
6 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.
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 · 180 lines · 113 tokens per session scan A 3fcc3c4a4834
persona-judge is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 113 tokens to every session and 2,951 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…