agentmods.dev

wjx-ai-kit: Agent for Claude Code

.claude/agents/wjx-survey.md

wjx-survey is an agent for Claude Code from wjxcom/wjx-ai-kit. It costs 40 tokens per session (805 once invoked), scanned A, original, MIT.

An expert sub-agent for Wenjuanxing, a Chinese online survey platform. It uses the platform’s tools to create surveys, collect and analyze responses, manage contacts, and handle account features.

In plain words
What is it for?
Use it to design, create, publish, edit, monitor, and analyze surveys; manage contacts and departments; and handle subaccounts, single sign-on, and related survey operations.
Why use it?
It provides a structured way to manage the full survey process, including checking results after changes and handling platform-specific formats.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions Claude Code.

This is wjxcom/wjx-ai-kit's own configuration. It tells Claude Code how to work on wjx-ai-kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything wjx-ai-kit configures →

not rated 18repo +2 changed 6d ago A scan 40 tokens original MIT
View source ↗ wjxcom/wjx-ai-kit npmjs.com
Reuse

Borrowing it

Nothing to install: this file belongs to wjxcom/wjx-ai-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/wjxcom/wjx-ai-kit/master/.claude/agents/wjx-survey.md
Clone the repo
git clone --depth 1 https://github.com/wjxcom/wjx-ai-kit

Made for: Claude Code.

Wrote 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.

agentmods badge for wjx-survey

README.md
[![agentmods](https://agentmods.dev/badge/agents/wjxcom/wjx-ai-kit/wjx-survey/github.svg)](https://agentmods.dev/agents/wjxcom/wjx-ai-kit/wjx-survey)
Your own site
<a href="https://agentmods.dev/agents/wjxcom/wjx-ai-kit/wjx-survey"><img src="https://agentmods.dev/badge/agents/wjxcom/wjx-ai-kit/wjx-survey/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.

agentmods 80×15 button for wjx-survey

Your own site · 80×15
<a href="https://agentmods.dev/agents/wjxcom/wjx-ai-kit/wjx-survey"><img src="https://agentmods.dev/badge/agents/wjxcom/wjx-ai-kit/wjx-survey.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 805 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.00805
Opus 5 $0.00020 $0.00402
Sonnet 5 $0.00008 $0.00161
Haiku 4.5 $0.00004 $0.00081

Measured 6d ago against content hash 0f9cfc8f55f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wjx-survey 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 6d 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.

.claude/agents/wjx-survey.md · 59 lines

What it actually says

问卷星 MCP 专家 Agent

这是历史项目中保留的 wjx-survey Agent 名称，行为规则与当前 wjx-mcp-expert 保持一致。你通过 wjx-mcp-server 的核心业务子集完成问卷星业务任务；CLI 的初始化、诊断、profile、补全、reference/schema、更新和 Skill 安装不在 MCP 范围内。

可用技能

配套的 MCP 使用指南位于 skills/wjx-mcp-use/（Claude Code 镜像位于 .claude/skills/wjx-mcp-use/）：

  • SKILL.md：核心子集工具总览、差异边界、工作流、资源和 Prompt 模板
  • references/：按需查阅具体参数和错误处理

先读 SKILL.md 获取全局视图，遇到参数问题时再读对应 reference。

工作原则

创建问卷

  1. 所有新问卷必须使用唯一入口 create_survey_by_json，传入 JSONL 字符串；不要调用已移除的 create_survey_by_text 或 create_survey。
  2. JSONL 创建支持当前 SDK 白名单中的题型；wjx://reference/question-types 只解释读取结果的数字 q_type/q_subtype，不是创建白名单。
  3. 创建后调用 get_survey 验证题目和设置，再提供 build_preview_url 填写链接或 build_survey_url 编辑链接。
  4. 包含纯框架题型时默认创建草稿，完成二次编辑并获得用户明确授权后再发布。

用户体系边界

用户体系工具仅用于维护用户明确提供的既有 usid/sysid；不能通过创建入口新建 atype=8 用户体系问卷。执行批量变更前先确认影响范围。

提交与分析

  • submit_response 先读取题目结构，使用服务端原始 q_index 构造 submitdata；未传 jpmversion 时由服务端工具获取并注入最新版本。
  • 查询数据优先 get_report 和 count_responses，需要明细时再分页 query_responses，大量数据使用 download_responses。
  • 分析流程为获取数据 → decode_responses → NPS/CSAT/异常检测等计算，并给出数据支撑。

安全原则

  • 执行 delete_survey、clear_responses、clear_recycle_bin 前必须获得用户确认。
  • 批量操作先告知影响范围；SSO 链接生成前确认目标账号信息。
  • 不在回复、日志或文件中回显完整 API Key。

常见错误

  • API Key 未配置或失效：停止业务调用，引导用户在 MCP 配置中设置或更新 WJX_API_KEY。
  • 私有化部署：在 MCP 配置中设置对应的 WJX_BASE_URL，不要把私有域名请求发往公网地址。
  • 问卷不存在：先列出问卷确认正确的 vid。
  • 问卷版本过期：重新读取问卷结构并使用最新 jpmversion。
Changes

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.

  1. 6d ago Changed · -20 lines · -1 tokens per session 0f9cfc8f55f3
  2. 9d ago First seen · 79 lines · 41 tokens per session scan A 5157d2ebefc2

Subscribe to this mod's changes

wjx-survey is an agent published in the GitHub repository wjxcom/wjx-ai-kit (18 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 805 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.

Analytics and metricsai-agentclimcpmcp-serveropenapisdk
Related

Other agents, from other repositories

architecture-reviewer

Wave 3 agent: analyzes module boundaries, dependency patterns, and layering decisions across the entire codebase. Produces system-level architectural memories linked with LEADSTO, DEPENDSON, BLOCKS, and CONTRADICTS relationships.

cogniplex/codemem · 51 tokens

security-reviewer

Wave 3 agent: analyzes authentication, authorization, input validation, and trust boundaries. Stores security-related decision memories linked with BLOCKS, LEADSTO, DEPENDSON, and INVALIDATEDBY relationships.

cogniplex/codemem · 45 tokens

symbol-analyst

Wave 2 agent: performs deep analysis of critical and important symbols. Reads source code, explores graph context, stores purpose/decision/pattern memories linked with typed relationships (EXPLAINS, LEADSTO, DEPENDSON, IMPLEMENTS).

cogniplex/codemem · 54 tokens

api-mapper

Wave 2 agent: documents API endpoints in a module or router group. Stores decision memories for each endpoint with route, auth, and shape details. Links endpoints with DEPENDSON, LEADSTO, and PARTOF relationships.

cogniplex/codemem · 50 tokens

dangerous-agent

An agent with security issues for testing.

ryo-ebata/cc-audit · 0 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens