everything-claude-code-zh is a Chinese translation of a collection of configurations for Claude Code and other AI coding agents. It provides agents, skills, hooks, commands, rules, and MCP configurations intended to support development workflows such as memory persistence, security scanning, evaluation, and research-first work. The catalogue includes commands, skills, agents, instructions, and a plugin from this configuration set.
Borrowing it
Nothing to install: this file belongs to xu-xiang/everything-claude-code-zh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xu-xiang/everything-claude-code-zh/main/.agents/skills/eval-harness/SKILL.mdgit clone --depth 1 https://github.com/xu-xiang/everything-claude-code-zhWrote 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/xu-xiang/everything-claude-code-zh/eval-harness)<a href="https://agentmods.dev/skills/xu-xiang/everything-claude-code-zh/eval-harness"><img src="https://agentmods.dev/badge/skills/xu-xiang/everything-claude-code-zh/eval-harness.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.01775 |
| Opus 5 | $0.00018 | $0.00888 |
| Sonnet 5 | $0.00007 | $0.00355 |
| Haiku 4.5 | $0.00004 | $0.00178 |
Grade A, and why
eval-harness 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 8d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
评测框架（Eval Harness）技能（Skill）
一个用于 Claude Code 会话的正规评测框架（Evaluation Framework），旨在落实评测驱动开发（Eval-Driven Development, EDD）原则。
何时激活
- 为 AI 辅助工作流设置评测驱动开发（EDD）
- 为 Claude Code 任务的完成情况定义通过/失败标准
- 使用 pass@k 指标衡量智能体（Agent）的可靠性
- 为提示词（Prompt）或智能体（Agent）的变更创建回归测试套件
- 跨模型版本对智能体（Agent）性能进行基准测试
核心理念
评测驱动开发（Eval-Driven Development）将评测（Eval）视为“AI 开发中的单元测试”：
- 在实现之前定义预期行为
- 在开发过程中持续运行评测（Evals）
- 跟踪每次变更带来的回归（Regressions）
- 使用 pass@k 指标进行可靠性度量
评测类型
能力评测（Capability Evals）
测试 Claude 是否能够完成其之前无法完成的任务：
[CAPABILITY EVAL: feature-name]
Task: 描述 Claude 应该完成的任务
Success Criteria:
- [ ] 准则 1
- [ ] 准则 2
- [ ] 准则 3
Expected Output: 预期结果的描述
回归评测（Regression Evals）
确保变更不会破坏现有功能：
[REGRESSION EVAL: feature-name]
Baseline: SHA 或检查点（checkpoint）名称
Tests:
- existing-test-1: PASS/FAIL
- existing-test-2: PASS/FAIL
- existing-test-3: PASS/FAIL
Result: X/Y 通过 (之前为 Y/Y)
评分器（Grader）类型
1. 基于代码的评分器（Code-Based Grader）
使用代码进行确定性检查：
# 检查文件是否包含预期模式
grep -q "export function handleAuth" src/auth.ts && echo "PASS" || echo "FAIL"
# 检查测试是否通过
npm test -- --testPathPattern="auth" && echo "PASS" || echo "FAIL"
# 检查构建是否成功
npm run build && echo "PASS" || echo "FAIL"
2. 基于模型的评分器（Model-Based Grader）
使用 Claude 对开放式输出进行评估：
[MODEL GRADER PROMPT]
评估以下代码变更：
1. 它是否解决了所述问题？
2. 结构是否良好？
3. 是否处理了边缘情况？
4. 错误处理是否恰当？
Score: 1-5 (1=差, 5=优秀)
Reasoning: [解释]
3. 人工评分器（Human Grader）
标记以供人工复核：
[HUMAN REVIEW REQUIRED]
Change: 变更内容描述
Reason: 为何需要人工复核
Risk Level: LOW/MEDIUM/HIGH
指标（Metrics）
pass@k
“在 k 次尝试中至少成功一次”
- pass@1: 首次尝试成功率
- pass@3: 3 次尝试内的成功率
- 典型目标：pass@3 > 90%
pass^k
“所有 k 次试验均成功”
- 更高的可靠性门槛
- pass^3: 连续 3 次成功
- 用于关键路径（Critical Paths）
评测工作流（Eval Workflow）
1. 定义（编码前）
## EVAL DEFINITION: feature-xyz
### 能力评测（Capability Evals）
1. 能够创建新用户账号
2. 能够验证邮箱格式
3. 能够安全地哈希密码
### 回归评测（Regression Evals）
1. 现有登录功能仍然正常
2. 会话管理未改变
3. 注销流程完好无损
### 成功指标
- 能力评测的 pass@3 > 90%
- 回归评测的 pass^3 = 100%
What ships with it
1 file 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.
- 8d ago First seen · 236 lines · 37 tokens per session scan A bb224571fd20
eval-harness is a skill published in the GitHub repository xu-xiang/everything-claude-code-zh (1,935 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 1,775 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
build-status-cache
Skip Phase 7 rebuild when no code changed since Phase 5 build passed. Compares git diff hash against stored hash from last successful build validation. Triggers on: entering Phase 7, checking build status, before final build validation. Returns BUILDCACHEHIT to skip or BUILDCACHEMISS to re-run build-validator.
auto-optimize
Autonomously optimize any Claude Code skill by running it repeatedly, scoring against binary evals, mutating the prompt, and keeping improvements. Use when: optimize/improve/benchmark/eval a skill, autoresearch, auto-optimize. Not for creating skills from scratch (use skill-creator-pro).
audit-harness
Use when auditing HARNESS.md, pre-commit hooks, pre-push hooks, architecture gates, or CI workflows for tunacode-cli. This skill treats any mismatch, skipped gate, or failing check as a critical failure and requires manual one-by-one execution rather than make targets, batch wrappers, or summary-only audits.
run-tests
Run tests matching a pattern. Use when user says "test", "run tests", or asks to verify changes.
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
taiyi-test
A project workflow skill for verifying an implementation and producing a TEST.md record. TDD means writing a failing test, implementing the change, and then making the test pass; this skill checks that process and other regression cases.