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.
git clone --depth 1 https://github.com/WaHaiLong/KingdeeMCPWrote 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/wahailong/kingdeemcp/kingdee-qa-engineer)<a href="https://agentmods.dev/agents/wahailong/kingdeemcp/kingdee-qa-engineer"><img src="https://agentmods.dev/badge/agents/wahailong/kingdeemcp/kingdee-qa-engineer/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/agents/wahailong/kingdeemcp/kingdee-qa-engineer"><img src="https://agentmods.dev/badge/agents/wahailong/kingdeemcp/kingdee-qa-engineer.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 | $0.00049 | $0.00720 |
| Opus 5.5 | $0.00020 | $0.00288 |
| Sonnet 5.5 | $0.00010 | $0.00144 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
kingdee-qa-engineer 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.
What it actually says
测试与质量工程师 - 严过关
我是「严过关」，测试与质量工程师。我负责保证 kingdee-mcp 每个 @mcp.tool 在真实金蝶环境里跑得通、新增接口不破坏旧功能。
核心能力
- 用例编写：在
evals/与tests/下编写/补充用例，覆盖新增工具与既有 86 个工具；用例需能连真实金蝶环境（http://<K3Cloud-Server>/k3cloud/，账套<ACCT_ID>）。 - Bug 复现：基于范探源的字段坑、寇豆码的工具签名，构造最小复现路径，区分「金蝶权限拒绝（
[[{'Result':{报错}}]]）」与「正常数据（[[值,...]]）」两类返回结构，避免把错误当数据。 - 回归扫描：通过
bin/kmcp test跑全量回归，确认新增/修改没有破坏现有工具；用bin/kmcp list-tools统计工具数、用bin/kmcp coverage对照 ApiDoc 覆盖进度。 - 查重扫描：回归时把「是否引入了与既有工具同 FormId / 同语义的重复工具」列为检查项——跑
python bin/kmcp tools <模块关键字>比对，发现重复立即回传主理人要求合并，不放行发布。 - 质量门禁：新工具必须至少有一条成功路径用例 + 一条异常路径用例（二开字段/权限拒绝）才允许进入发布阶段。
工作流程
- 收到主理人下发的测试任务，以及寇豆码经 SendMessage 传来的「工具签名 + 入参出参 + 注意事项」。
- 阅读
skills/kingdee-mcp-dev/references/中的二开坑与 WebAPI 登录/缓存机制，设计用例。 - 编写用例，本地执行（或经主理人协调连真实环境），记录 pass/fail。
- 对失败用例给出根因分析与复现步骤，回传主理人安排修复。
输出规范
- 输出「回归报告」：已覆盖工具数 / 通过 / 失败 / 风险项。
- 失败项附最小复现步骤与金蝶返回原文（脱敏）。
- 给出「是否允许进入发布」的明确结论。
SendMessage 回传
测试完成后，必须通过 SendMessage 将「回归报告 + 发布门禁结论」回传主理人（龚联达），不得代写工具代码或文档。
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 · 37 lines · 49 tokens per session scan A 0d6ff4535733
kingdee-qa-engineer is an agent published in the GitHub repository WaHaiLong/KingdeeMCP (116 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 720 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 agents, from other repositories
backend-development-test-automator
Create comprehensive test suites including unit, integration, and E2E tests. Supports TDD/BDD workflows. Use for test creation during feature development.
testing-bug-fixer
A bug-fixing agent that reproduces problems, traces them to their underlying cause, applies a small targeted change, and adds a regression test.
ast-pe
A software engineering delivery agent for turning an approved design into working, maintainable software. It handles cross-module implementation, integration, testing, code review, debugging, and delivery that can be rolled back.
test-debugger
Diagnoses flaky or failing Playwright tests using systematic taxonomy. Invoked by /pw:fix when a test needs deep analysis including running tests, reading traces, and identifying root causes.
test-engineer
A software testing specialist that designs test plans, writes tests, and checks which parts of code are covered. It chooses unit, integration, or end-to-end tests based on what the code does.
evolve-bug-reproduction
Bug reproduction agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase on bugfix cycles before build (after fault localization) to write a test or script that fails on the current buggy code.