Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ZTE-AICloud/Co-OmniSpec/plugin install omni-dsddWrote 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)<a href="https://agentmods.dev/skills/zte-aicloud/co-omnispec/eval-code"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/eval-code/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/zte-aicloud/co-omnispec/eval-code"><img src="https://agentmods.dev/badge/skills/zte-aicloud/co-omnispec/eval-code.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 | $0.00061 | $0.01430 |
| Opus 5.5 | $0.00024 | $0.00572 |
| Sonnet 5.5 | $0.00012 | $0.00286 |
| Haiku 4.5 | $0.00006 | $0.00143 |
Grade A, and why
eval-code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OmniEval 综合代码评测技能
本技能整合了代码变更采集和第三方模型评测功能，提供完整的 SDD 流程代码质量评估。
环境初始化
| 变量 | 含义 |
|---|---|
CLAUDE_PLUGIN_ROOT |
插件根目录 |
CLAUDE_WORKING_DIR |
Git 工作区根 |
FEATURE_DIR |
当前特性目录 |
test -n "${CLAUDE_PLUGIN_ROOT:-}" && test -d "${CLAUDE_PLUGIN_ROOT}"
test -n "${CLAUDE_WORKING_DIR:-}" && test -d "${CLAUDE_WORKING_DIR}"
缺失时：export CLAUDE_WORKING_DIR="$(pwd)"（不用 git rev-parse --show-toplevel）。
推荐：source "${FEATURE_DIR}/.runs/env.sh"。
路径约定
| 产物 | 路径 |
|---|---|
| 采集 JSON | ${FEATURE_DIR}/.runs/evaluations/code.diff.json |
| 评测报告 | ${FEATURE_DIR}/.runs/evaluations/eval-code-report.txt |
功能说明
- 代码变更采集：从当前 SDD 分支采集代码变更信息，生成评测所需的 JSON 文件
- 自动评测：使用第三方评测模型对生成的代码进行质量评估
- 结果输出：将评测结果同时输出到控制台和文件
技能依赖
本技能会调用以下技能:
- /eval-code-collector: 采集 SDD 流程的代码变更信息
- /eval-code-evaluator: 使用第三方评测模型对代码质量进行评估
执行流程
阶段 1：代码变更采集
加载 skill eval-code-collector，或执行：
python3 "${CLAUDE_PLUGIN_ROOT}/skills/eval-code-collector/scripts/collect.py" \
--working-dir "${CLAUDE_WORKING_DIR}" \
${FEATURE_DIR:+--feature-dir "${FEATURE_DIR}"} \
--target-dir "<目标代码目录>"
阶段 2：代码质量评测
加载 skill eval-code-evaluator，或执行：
python3 "${CLAUDE_PLUGIN_ROOT}/skills/eval-code-evaluator/scripts/evaluate_code.py" \
--config "${FEATURE_DIR}/.runs/evaluations/code.diff.json" \
--output "${FEATURE_DIR}/.runs/evaluations/eval-code-report.txt"
输入参数
自动检测当前项目的主要代码目录：
- 优先级顺序： 当前目录
- 用户可以通过参数指定特定目录来覆盖自动检测
- 评测模型：使用配置文件中指定的模型（默认 glm4.6）
输出
- 控制台输出：显示评测进度和最终结果
- 文件输出：
${FEATURE_DIR}/.runs/evaluations/eval-code-report.txt- 包含详细的评测报告
评测指标
ICE Score 组件
- 功能正确性 (0-1)：代码是否正确实现了需求
- 实用性 (0-1)：代码是否实用且结构良好
Code Judge 组件
- 评分 (0-1)：代码一致性和整体质量
- 不一致问题：发现的问题列表
- 严重级别：Small, Major, Fatal
- 问题数量：发现的问题总数
综合指标
- 平均 LLM 评测指标：所有指标的综合得分
使用示例
基础用法
/eval-code
执行步骤：
- 自动检测并采集当前项目的主要代码目录变更
- 自动进行代码质量评测
- 输出评测结果到控制台和文件
指定目录
What ships with it
2 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 · 192 lines · 61 tokens per session scan A 83866a6cda0d
eval-code is a skill published in the GitHub repository ZTE-AICloud/Co-OmniSpec (57 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 1,430 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…