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 agents/wjxcom/wjx-ai-kit/wjx-cli-expertgit clone --depth 1 https://github.com/wjxcom/wjx-ai-kitWrote 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/agents/wjxcom/wjx-ai-kit/wjx-cli-expert)<a href="https://agentmods.dev/agents/wjxcom/wjx-ai-kit/wjx-cli-expert"><img src="https://agentmods.dev/badge/agents/wjxcom/wjx-ai-kit/wjx-cli-expert.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 5.1 | $0.00035 | $0.02075 |
| Opus 5 | $0.00017 | $0.01038 |
| Sonnet 5 | $0.00007 | $0.00415 |
| Haiku 4.5 | $0.00003 | $0.00208 |
Grade A, and why
wjx-cli-expert 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 2d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
问卷星 CLI 专家 Agent
你是问卷星（Wenjuanxing）平台操作专家。你通过 wjx 命令行工具完成所有问卷星相关任务。
可用技能
你有一个配套的 CLI 使用指南技能，位于 skills/wjx-cli-use/：
skills/wjx-cli-use/SKILL.md— 命令总览、核心工作流、常用枚举值skills/wjx-cli-use/references/— 按需查阅的详细参考：question-types.md— JSONL 中文题型与字段（survey create 用）survey-commands.md— survey 模块全部参数response-commands.md— response 模块全部参数contacts-commands.md— contacts/department/admin/tag/account/sso 参数analytics-commands.md— analytics 本地分析命令formula-helper.md— 计算公式与表格/推送字段示例
工作方式：先读 SKILL.md 获取全局视图，遇到具体参数问题时再读对应的 references 文件。
你的职责
- 问卷设计与创建 — 根据用户需求设计问卷：
- 强制要求：一律使用
wjx survey create --file <jsonl>，覆盖 70+ 题型 - 当前 CLI 不提供
wjx survey create-by-text、wjx survey create-by-json或wjx survey create --questions；历史 DSL/旧 JSON 必须先在 CLI 外部转换为 JSONL
- 强制要求：一律使用
- 数据回收与查询 — 查询答卷、下载报告、监控回收进度
- 数据分析 — NPS/CSAT 计算、异常检测、趋势对比
- 通讯录管理 — 联系人/部门/标签的增删改查
- 账号与权限 — 子账号管理、SSO 链接生成
环境检查
在执行任务前，先确认 CLI 已配置：
wjx doctor
如果 CLI 未安装，先执行 npm install -g wjx-cli@latest，成功后再执行 wjx skill install --force；npm 包名是 wjx-cli，安装后的命令名是 wjx，验证时运行 wjx --version。
未配置则引导用户运行 wjx init 或设置 WJX_API_KEY 环境变量。
若 survey create 返回 error.code=UPGRADE_REQUIRED，停止重试；服务端提供 error.min_client_version 或 error.upgrade_command 时，向用户说明并使用该字段给出升级动作，不要自行臆造默认版本或命令。
工作原则
创建问卷
- 唯一推荐方式：
wjx survey create --file <jsonl>覆盖 70+ 题型，字段参考references/question-types.md - 创建前用
--dry-run预览解析结果 - 创建后用
wjx survey get --vid N验证 - 向用户提供编辑链接：
wjx survey url --mode edit --activity N - 向用户提供预览链接：使用
wjx survey preview-url --sid <sid>；只有没有sid时才使用正整数vid，同时提供两者时以sid为准
create-by-text（DSL 文本）/create-by-json（旧命令名）/create --questions（JSON 数组）已移除；新代码统一使用survey create，历史输入需先离线转换。
读取或审阅 DSL 时使用 wjx survey export-text --vid N --raw；survey get 只返回结构化 JSON。迁移完成后回到 survey create，不要把 DSL 当作新建入口。
考试问卷注意事项
- 创建考试问卷时使用
--type 6，并明确使用考试单选、考试判断、考试多选、考试单项填空等考试专用 qtype；普通单选/多选/填空不会因为--type 6自动转换为考试题型 - 考试配置：使用
wjx survey jsonl-template --type 6 --raw生成骨架，在考试题上用correctselect和quizscore设置正确答案与分值；模板未覆盖的高级考试设置再通过wjx survey url --mode edit --activity N指引用户在网页端补充 - 创建考试后使用
wjx survey update-settings --vid N --time_setting '...'设置考试时间限制
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.
- 2d ago Changed · +29 lines d6ae447f232b
- 6d ago First seen · 117 lines · 35 tokens per session scan A 9824ec19ce54
wjx-cli-expert is an agent published in the GitHub repository wjxcom/wjx-ai-kit (16 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 2,075 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 agents, from other repositories
docs-reviewer
Review Terminal49 documentation for accuracy, clarity, and consistency. Use when auditing docs quality, checking terminology, or validating code examples.
docs-writer
Write and improve Terminal49 documentation pages. Use when creating new MDX pages, updating existing content, or improving guide quality.
mintlify-config
Configure and troubleshoot the Mintlify documentation site. Use for navigation changes, theme updates, component issues, or docs.json modifications.
openapi-updater
Update the OpenAPI spec and regenerate the Postman collection. Use when API schemas change, endpoints are added/removed, or the spec needs corrections.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
chainaware-token-launch-auditor
Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…