claude-authenticity SKILL.md skillA

claude-authenticity from agentscope-ai/openjudge is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add agentscope-ai/openjudge/claude-authenticity@git:20260310.56772fa

Pins git:20260310.56772fa in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
agentscope-ai/openjudge
Path
skills/claude-authenticity/SKILL.md
Versions recorded
1
Latest version
git:20260310.56772fa, committed Mar 10, 2026
Size
22,536 bytes
Repository stars
1,020
License
Apache-2.0

Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra packages beyond httpx. Use when the user wants to verify a Claude API key or endpoint, check if a third-party Claude service is authentic, audit API providers for Claude…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Claude Authenticity Skill

Verify whether an API endpoint serves genuine Claude and optionally extract any
injected system prompt.

**No installation required beyond `httpx`.** Copy the code blocks below directly
into a single `.py` file and run — no openjudge, no cookbooks, no other setup.

```bash
pip install httpx
```

## The 9 checks (mirrors [claude-verify](https://github.com/molloryn/claude-verify))

| # | Check | Weight | Signal |
|---|-------|--------|--------|
| 1 | Signature 长度 | 12 | `signature` field in response (official API exclusive) |
| 2 | 身份回答 | 12 | Reply mentions `claude code` / `cli` / `command` |
| 3 | Thinking 输出 | 14 | Extended-thinking block present |
| 4 | Thinking 身份 | 8 | Thinking text references Claude Code / CLI |
| 5 | 响应结构 | 14 | `id` + `cache_creation` fields present |
| 6 | 系统提示词 | 10 | No prompt-injection signals (reverse check) |
| 7 | 工具支持 | 12 | Reply mentions `bash` / `file` / `read` / `write` |
| 8 | 多轮对话 | 10 | Identity keywords appear ≥ 2 times |
| 9 | Output Config | 10 | `cache_creation` or `service_tier` present |

**Score → verdict:** ≥ 85 → `genuine 正版 ✓` / 60–84 → `suspected 疑似 ?` / < 60 → `likely_fake 非正版 ✗`
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add agentscope-ai/openjudge/claude-authenticity@sha256:3f4eddef8e9cf4bb

The line at the top of this page pins the label git:20260310.56772fa, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_chrozcerksus3fn2.svg)](https://markdownregistry.com/a/art_chrozcerksus3fn2)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Mar 10, 2026.

versioncommittedcommitsizeaudit
git:20260310.56772fa latest2026-03-10 56772fa 22,536 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (22536 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

agentscope-ai/openjudge · 1,020 stars · license Apache-2.0 · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_chrozcerksus3fn2
GET https://markdownregistry.com/api/v1/resolve?ref=agentscope-ai/openjudge/claude-authenticity
GET https://markdownregistry.com/api/v1/blob/3f4eddef8e9cf4bbbadee25db5bd373ef401cf39e632d6e65d2ebc6264041d2f

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from agentscope-ai/openjudge

00-academic-router SKILL.md skill
agentscope-ai/openjudge · skills/academic-eval/00-academic-router/SKILL.md · Use when the user wants help with academic papers or citations but it's unclear which specific workflow fits —…
git:20260911.d1e0642 · audit A · 1,020 stars
01-paper-review SKILL.md skill
agentscope-ai/openjudge · skills/academic-eval/01-paper-review/SKILL.md · Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files…
git:20260911.d1e0642 · audit A · 1,020 stars
02-bib-verify SKILL.md skill
agentscope-ai/openjudge · skills/academic-eval/02-bib-verify/SKILL.md · Verify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against CrossRef, arXiv…
git:20260911.d1e0642 · audit A · 1,020 stars
03-ref-hallucination-arena SKILL.md skill
agentscope-ai/openjudge · skills/academic-eval/03-ref-hallucination-arena/SKILL.md · Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and…
git:20260911.d1e0642 · audit A · 1,020 stars
00-arena-router SKILL.md skill
agentscope-ai/openjudge · skills/arena-eval/00-arena-router/SKILL.md · Use when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific…
git:20260911.d1e0642 · audit A · 1,020 stars
01-auto-arena SKILL.md skill
agentscope-ai/openjudge · skills/arena-eval/01-auto-arena/SKILL.md · Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries…
git:20260911.d1e0642 · audit A · 1,020 stars
02-ref-hallucination-arena SKILL.md skill
agentscope-ai/openjudge · skills/arena-eval/02-ref-hallucination-arena/SKILL.md · Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and…
git:20260911.d1e0642 · audit A · 1,020 stars
meta-eval SKILL.md skill
agentscope-ai/openjudge · skills/eval_pipeline/00-meta-eval/SKILL.md · Use when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start —…
git:20260708.2151def · audit A · 1,020 stars
eval-design SKILL.md skill
agentscope-ai/openjudge · skills/eval_pipeline/01-eval-design/SKILL.md · Use when the user needs to design evaluation datasets, create test cases, stratify samples, generate adversarial…
git:20260708.2151def · audit B · 1,020 stars
metric-design SKILL.md skill
agentscope-ai/openjudge · skills/eval_pipeline/02-metric-design/SKILL.md · Use when the user has evaluation principles or a dataset but needs help choosing the right graders, designing…
git:20260708.2151def · audit A · 1,020 stars
align-human SKILL.md skill
agentscope-ai/openjudge · skills/eval_pipeline/03-align-human/SKILL.md · Use when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with…
git:20260708.2151def · audit A · 1,020 stars
eval-report SKILL.md skill
agentscope-ai/openjudge · skills/eval_pipeline/04-eval-report/SKILL.md · Use when the user has run multiple evaluation skills and wants a comprehensive analysis — maturity assessment…
git:20260708.2151def · audit A · 1,020 stars

Every file in agentscope-ai/openjudge

Browse by kind, by grade A, or by owner.