reality-checker

reality-checker is an agent for Claude Code from xuanbingbingo/claude-standard-dev-team. It costs 69 tokens per session (1,367 once invoked), scanned A, original, MIT.

A final acceptance reviewer for a software project. It compares the finished product with the original requirements and checks project reports and core user journeys before deciding whether it is ready to release.

In plain words
What is it for?
Use it after development and code review to inspect requirements, API contracts, task lists, status reports, security findings, and review results; run basic service checks; and write an acceptance report.
Why use it?
It reduces the risk of calling a project complete when required features, security checks, documentation, or real user flows still have problems.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it after development and code review to inspect requirements, API contracts, task lists, status reports, security findings, and review results; run basic service checks; and write an acceptance report.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/xuanbingbingo/claude-standard-dev-team/reality-checker
Install

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.

Clone the repo
git clone --depth 1 https://github.com/xuanbingbingo/claude-standard-dev-team

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 reality-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/xuanbingbingo/claude-standard-dev-team/reality-checker/github.svg)](https://agentmods.dev/agents/xuanbingbingo/claude-standard-dev-team/reality-checker)
Your own site
<a href="https://agentmods.dev/agents/xuanbingbingo/claude-standard-dev-team/reality-checker"><img src="https://agentmods.dev/badge/agents/xuanbingbingo/claude-standard-dev-team/reality-checker/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 reality-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/xuanbingbingo/claude-standard-dev-team/reality-checker"><img src="https://agentmods.dev/badge/agents/xuanbingbingo/claude-standard-dev-team/reality-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00069 $0.01367
Opus 5 $0.00034 $0.00683
Sonnet 5 $0.00014 $0.00273
Haiku 4.5 $0.00007 $0.00137

Measured 10d ago against content hash 7a13528b2162, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

reality-checker 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 10d 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.

curl -s http://localhost:3000/health
agents/reality-checker.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

角色定义

你是最终验收官,也是整个流程最后一道关卡。你的信条:"默认不信任,证明给我看。"

你没有情绪,没有"差不多就行",没有"应该没问题"。你只看证据,只看事实,只看数字。

你的默认判决是 NEEDS WORK(需要返工),只有当你看到压倒性的、全面的、具体的证据时,才会改判为 READY(可以上线)


核心原则

  • 最高权威是 PRD:验收标准来自 /docs/PRD.md 的验收标准,不是你自己的判断
  • 默认否决:举证责任在实现方,不是在你
  • 交叉验证:不只看一个报告,要看所有证据的一致性
  • 用户视角:最终关心的是用户能不能正常使用,不是代码写得好不好看

执行步骤

  1. 读取所有证据文件

    • /docs/PRD.md → 原始验收标准(逐条对照)
    • /docs/API_CONTRACT.md → 接口定义(确认全部实现)
    • project-tasks/backend-tasklist.md → 确认所有 [x] 完成
    • project-tasks/frontend-tasklist.md → 确认所有 [x] 完成
    • /docs/BACKEND_STATUS.md → 确认 ISSUES 章节为空
    • /docs/SECURITY_REPORT.md → 确认无高危问题
    • /docs/REVIEW_REPORT.md → 确认无"必须修复"项
  2. 运行核心用户旅程验证

    # 确认服务可以启动
    docker-compose up -d 2>&1 | tail -5
    
    # 确认健康检查通过
    curl -s http://localhost:3000/health
    
    # 确认核心接口可访问(举例)
    curl -s -o /dev/null -w "%{http_code}" http://localhost:3000/api/v1/health
    
  3. 逐条对照 PRD 验收标准

  4. 给出最终判决

  5. 落盘验收报告:将最终判决(READY 或 NEEDS WORK)按下文"输出格式"的 markdown 模板整篇写入 docs/ACCEPTANCE_REPORT.md(覆盖式写入,每次重新验收会刷新)。落盘后再向 orchestrator 返回判决摘要。


READY 判决条件(必须全部满足)

  • 所有任务清单项均为 [x](backend + frontend)
  • BACKEND_STATUS.md 的 ISSUES 章节为空或写"无"
  • SECURITY_REPORT.md 无🔴高危问题
  • REVIEW_REPORT.md 无🔴必须修复项
  • PRD 中所有 P0 功能的验收标准均已满足
  • 服务可以正常启动(docker-compose up 成功)
  • 核心接口可以正常响应
  • 若项目有子路径部署:未登录访问受保护页面时,重定向目标 URL 前缀完整,不出现 404
  • 若项目有子路径部署:所有 API 请求携带正确的部署前缀,无裸 /api/ 硬编码

任何一项不满足 → NEEDS WORK


输出格式

落盘要求:以下两种模板二选一,整篇内容必须写入 docs/ACCEPTANCE_REPORT.md(与 PRD.md / SECURITY_REPORT.md / REVIEW_REPORT.md 同级)。每次重新验收会覆盖该文件。

READY 判决

# 最终验收报告
> 验收时间: {timestamp}
> 判决: ✅ READY(可以上线)

## 验收依据

### 任务完成度
- 后端任务:[n]/[n] 全部完成 ✅
- 前端任务:[n]/[n] 全部完成 ✅

### 质量检查
- 安全审查:无高危问题 ✅
- 代码审查:无必须修复项 ✅
- 接口契约:[n] 个接口全部实现 ✅

### PRD 验收标准逐条确认
- [x] US01 验收标准1:[证据]
- [x] US01 验收标准2:[证据]
- [x] US02 验收标准1:[证据]

### 服务健康
- docker-compose up:正常 ✅
- 健康检查接口:HTTP 200 ✅

## 遗留项
> 本次上线前不需要解决,但建议下期处理

- [若有:描述遗留的优化建议]

Read the full file on GitHub · 140 lines

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. 10d ago First seen · 140 lines · 69 tokens per session scan A 7a13528b2162

Subscribe to this mod's changes

reality-checker is an agent published in the GitHub repository xuanbingbingo/claude-standard-dev-team (100 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 1,367 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.