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.
npx agentmods add skills/zte-aicloud/co-omnispec/eval-code-evaluatornpx skills add ZTE-AICloud/Co-OmniSpec --skill eval-code-evaluatorgit clone --depth 1 https://github.com/ZTE-AICloud/Co-OmniSpecWrote 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/zte-aicloud/co-omnispec/eval-code-evaluator)<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/eval-code-evaluator"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/eval-code-evaluator.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.01332 |
| Opus 5 | $0.00033 | $0.00666 |
| Sonnet 5 | $0.00013 | $0.00266 |
| Haiku 4.5 | $0.00007 | $0.00133 |
Grade A, and why
eval-code-evaluator 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 5d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Judge Model Evaluator Skill
This skill evaluates code generation quality using standardized metrics including ICE Score (Functional Correctness + Usefulness) and Code Judge assessments.
环境初始化
| 变量 | 含义 |
|---|---|
CLAUDE_PLUGIN_ROOT |
插件根目录（脚本与 prompts/ 位于此技能目录下） |
FEATURE_DIR |
可选；读取 ${FEATURE_DIR}/.runs/evaluations/code.diff.json |
评测入口（配置 JSON 通常由 eval-code-collector 生成）：
python3 "${CLAUDE_PLUGIN_ROOT}/skills/eval-code-evaluator/scripts/evaluate_code.py" \
--config "${FEATURE_DIR}/.runs/evaluations/code.diff.json"
模板目录为 ${CLAUDE_PLUGIN_ROOT}/skills/eval-code-evaluator/scripts/prompts/（脚本内相对 __file__ 解析，无需工作区路径）。
When to Use
- Evaluating AI-generated code against requirements
- Assessing code quality in automated workflows
- Comparing multiple code implementations
- Getting structured feedback on code changes
- Validating that code meets specification requirements
Quick Start
- Ensure you have API access configured
- Provide the requirement description and generated code
- Optionally provide reference code for comparison
- Get comprehensive evaluation scores
What You Need to Provide
Required Inputs
-
Requirements/Feature Description - What the code is supposed to do
- Format: List of change descriptions or natural language requirements
-
Generated Code - The code to be evaluated
- Format: String or structured code blocks with file paths
Optional Inputs
- Reference Code - Correct/expected implementation (if available)
- Improves evaluation accuracy
- Format: List of code answers with file paths and snippets
Evaluation Metrics
ICE Score Components
- Functional Correctness (0-1): Does the code correctly implement the requirements?
- Usefulness (0-1): Is the code practical and well-structured?
Code Judge Components
- Score (0-1): Overall code consistency and quality
- Inconsistencies: Detailed list of issues found
- Severity levels: Small, Major, Fatal
- Inconsistencies Count: Number of issues found
What ships with it
21 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.
- evals/evals.json 2.2 KB
- prompts/code_judge_no_answer_v1.jinja2 1.2 KB
- prompts/code_judge_no_answer_v2.jinja2 1.5 KB
- prompts/code_judge_with_answer_v1.jinja2 1.5 KB
- prompts/code_judge_with_answer_v2.jinja2 1.8 KB
- prompts/ice_score_functional_correctness_no_answer.jinja2 1.4 KB
- prompts/ice_score_functional_correctness_with_answer.jinja2 2.9 KB
- prompts/ice_score_usefulness_no_answer.jinja2 1.4 KB
- prompts/ice_score_usefulness_with_answer.jinja2 3.2 KB
- README.md 4.4 KB
- references/config-example.json 837 B
- scripts/evaluate_code.py 6.7 KB runs code
- scripts/judge_model_metrics_standalone.py 21 KB runs code
- scripts/prompts/code_judge_no_answer_v1.jinja2 1.2 KB
- scripts/prompts/code_judge_no_answer_v2.jinja2 1.5 KB
- scripts/prompts/code_judge_with_answer_v1.jinja2 1.5 KB
- scripts/prompts/code_judge_with_answer_v2.jinja2 1.8 KB
- scripts/prompts/ice_score_functional_correctness_no_answer.jinja2 1.4 KB
- scripts/prompts/ice_score_functional_correctness_with_answer.jinja2 2.9 KB
- scripts/prompts/ice_score_usefulness_no_answer.jinja2 1.4 KB
- scripts/prompts/ice_score_usefulness_with_answer.jinja2 3.2 KB
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.
- 5d ago First seen · 220 lines · 66 tokens per session scan A 1588df990bd3
eval-code-evaluator is a skill published in the GitHub repository ZTE-AICloud/Co-OmniSpec (54 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,332 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…