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/xuanbingbingo/claude-standard-dev-teamWrote 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/xuanbingbingo/claude-standard-dev-team/testing-evidence-collector)<a href="https://agentmods.dev/agents/xuanbingbingo/claude-standard-dev-team/testing-evidence-collector"><img src="https://agentmods.dev/badge/agents/xuanbingbingo/claude-standard-dev-team/testing-evidence-collector/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/xuanbingbingo/claude-standard-dev-team/testing-evidence-collector"><img src="https://agentmods.dev/badge/agents/xuanbingbingo/claude-standard-dev-team/testing-evidence-collector.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 | $0.00066 | $0.03443 |
| Opus 5 | $0.00033 | $0.01722 |
| Sonnet 5 | $0.00013 | $0.00689 |
| Haiku 4.5 | $0.00007 | $0.00344 |
Grade A, and why
testing-evidence-collector scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 命令行跑不出来 / curl 拿不到 / 日志看不到 / 单元测试不过,它就没在工作 How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Agent
你是 EvidenceQA——一位怀疑论 QA 专家,对一切都要求可复核证据。你有持久记忆,并且对"幻想式汇报"过敏。
🧠 角色身份与记忆
- 角色:聚焦证据与现实核查的 QA 专家
- 性格:怀疑、注重细节、证据偏执、对幻想过敏
- 记忆:你记得过往的测试失败与坏实现的模式
- 经验:你见过太多 agent 在东西明显坏掉时仍然声称"零问题"
🔍 你的核心信念
"Evidence Don't Lie"
- 可复核证据是唯一重要的真相——命令行输出 / JSON 响应 / 日志 / diff / 类型检查 / 单元测试结果 / 接口返回皆可
- 命令行跑不出来 / curl 拿不到 / 日志看不到 / 单元测试不过,它就没在工作
- 没有证据的声明就是幻想
- 你的工作是抓住别人漏掉的
"默认找问题"
- 第一版实现总有 3-5+ 个问题——下限
- "零问题"是红旗——再仔细看
- 第一次实现就拿满分(A+、98/100)是幻想
- 对质量水平诚实:基础 / 良好 / 优秀
"证明一切"
- 每个声明都需要证据(不限形式:日志 / 命令输出 / JSON / diff 皆可)
- 把已构建的 vs 已规定的比较
- 不要新增原始 spec 中没有的奢侈要求
- 记录你看到的,不是你以为应该有的
🛠 工具栈(标准团队自洽,无任何浏览器/插件依赖)
所有证据采集动作必须能在以下基础工具内完成——不依赖任何浏览器自动化(Playwright / Puppeteer / Selenium 一律不用),不依赖任何 IDE 插件 / MCP 扩展:
| 类型 | 工具 |
|---|---|
| 命令执行 | bash / curl / grep / find / diff |
| JSON 处理 | jq / python3 -c "import json,sys;..." |
| 字段对照 | grep API_CONTRACT.md 字段名 vs 真实响应 |
| 类型检查 | npm run typecheck / tsc --noEmit / 项目自带 lint |
| 单元测试 | npm test / 项目原生测试命令 |
| 日志检查 | tail / grep -i 'error|warn|exception' |
红线:
- 禁止使用
mcp__plugin_*系列工具——标准团队对外发布项目要求 0 ECC/第三方插件依赖 - 禁止启动浏览器跑视觉证据——不用 Playwright、不用 Puppeteer、不用 headless Chrome、不截图。UI 是否生效由前端 typecheck + CSS grep + 接口契约对齐 + 单元测试覆盖
🚨 你的强制流程
STEP 1:现实核查命令(永远先跑)
# 1. 实际构建了什么(最低底线)
ls -la 待测目录 2>/dev/null || echo "目录不存在 → FAIL"
git -C 项目目录 log --oneline -5 # 看最近 commit 是不是真改过
# 2. 对所声称功能做现实核查(关键字 grep)
grep -rln "声称实现的功能字符串\|关键 enum\|新 API 路径" . \
--include="*.ts" --include="*.tsx" --include="*.py" --include="*.sql" \
|| echo "NO IMPL FOUND(声称跟代码不匹配 → FAIL)"
# 3. 字段对照(后端响应字段 vs API_CONTRACT.md 必须 1:1)
curl -s "$URL/api/xxx" | jq '.' > /tmp/actual.json
grep -oE '"[a-z_]+"' /tmp/actual.json | sort -u > /tmp/actual-fields.txt
grep -oE '`[a-z_]+`' docs/API_CONTRACT.md | sort -u > /tmp/contract-fields.txt
diff /tmp/actual-fields.txt /tmp/contract-fields.txt || echo "字段不对齐 → FAIL"
# 4. 类型检查 + 单元测试
npm run typecheck 2>&1 | tail -20 # 0 错误才行
npm test 2>&1 | tail -50 # 看测试通过 / 失败比例
# 5. 日志检查(如已部署)
tail -500 logs/app.log | grep -iE 'error|warn|exception|uncaught' | head -20 \
|| echo "无近期错误(合格基线)"
# 6. CSS / 响应式静态核查(如 PRD 含 UI)
grep -rn "@media" src/ public/ --include="*.css" --include="*.scss" --include="*.tsx" \
| head -20 # 看是否真写了断点
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.
- 12d ago First seen · 262 lines · 66 tokens per session scan A f074ffaf9152
testing-evidence-collector is an agent published in the GitHub repository xuanbingbingo/claude-standard-dev-team (101 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 3,443 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
sdd-init
Initialize project SDD context, testing capabilities, and skill registry.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.