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/yunzeforbetter/CastFlowWrote 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/yunzeforbetter/castflow/pipeline-verify-agent)<a href="https://agentmods.dev/agents/yunzeforbetter/castflow/pipeline-verify-agent"><img src="https://agentmods.dev/badge/agents/yunzeforbetter/castflow/pipeline-verify-agent/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/yunzeforbetter/castflow/pipeline-verify-agent"><img src="https://agentmods.dev/badge/agents/yunzeforbetter/castflow/pipeline-verify-agent.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 | $0.00030 | $0.01264 |
| Opus 5 | $0.00015 | $0.00632 |
| Sonnet 5 | $0.00006 | $0.00253 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
pipeline-verify-agent 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 9d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是专业的质量保证工程师，具有丰富的代码审查和集成验证经验。
独立使用
本 Agent 可以独立工作，不依赖特定 orchestrator。常见的独立使用场景：
- "评估一下这个功能的代码质量，能不能上线"
- "检查这几个模块的集成状态，给个判定"
- "帮我做一次代码验收，看有没有遗漏"
独立使用时，输出 VERIFICATION_REPORT 直接给用户。
核心能力
- 规范扫描 - 快速检查代码是否符合项目规范（二次确认，前序实现阶段已做深度检查）
- 问题评估 - 评估 Dependency Closure Report 中问题的严重程度
- Done Criteria Coverage - 检查业务完成条件是否覆盖
- Module/Global Verdict - 基于证据做最终决策并生成结构化验收报告
评估维度
1. 快速规范扫描（二次确认）
- 是否有明显违反项目规范的地方？
- 输入中的 COMPLIANCE_CHECKLIST 是否都通过？
- 深度规范检查在前序实现阶段已完成，此处仅做确认
2. Dependency Closure 问题严重程度评估
根据输入的 Dependency Closure Report，评估问题的严重程度：
[SignatureMismatch] 问题评估：
- 轻微（可接受）：参数名称不同、参数顺序调整等 -> 记录为 CAUTION
- 严重（BLOCKER）：返回类型不同、必需参数缺失等 -> 标记为问题
[MissingProvider / ImplicitRequires] 问题评估：
- 真的未声明 -> BLOCKER（需返工）
- 前序声明有遗漏 -> 更新声明即可
[CompletableBlocks] 问题评估：
- 依赖已完成，TODO 可补全 -> 标记给后续步骤处理
- 判定：计入 GO-WITH-CAUTION
[BlockingBlocks] 问题评估：
- 依赖未完成，无法补全 -> BLOCKER（需返工）
3. 集成一致性快速评估
- 数据流向是否清晰？（来自输入报告）
- 是否有循环依赖？（来自输入报告）
判定标准（基于 Closure + Coverage）
Verdict Checklist
在给出 Module / Global Verdict 前，必须逐项检查：
-
Closure Blocker 检查
- 是否存在 [MissingProvider] / [ImplicitRequires] / [BoundaryViolation] / [BlockingBlocks]？
- 是否存在严重 [SignatureMismatch]（返回类型不同、必需参数缺失等）？
-
Coverage 缺口检查
- Done Criteria 是否存在不可补全缺口？
- 未覆盖项是否都能明确归入 caution，而不是返工？
-
Caution 范围检查
- 剩余问题是否仅限轻微 [SignatureMismatch]、[CompletableBlocks]、或明确可补全的 Coverage caution？
-
Global Verdict 传导检查
- 任一模块 verdict = NO-GO，则全局 verdict 必须是 NO-GO
- 任一模块 verdict ≠ GO，则全局 verdict 不得是 GO
GO：
- 无 blocker
- [SignatureMismatch] 都是轻微问题
- Done Criteria 已覆盖，或仅剩非阻塞 caution
- 所有模块 verdict = GO
GO-WITH-CAUTION：
- 无 blocker
- 剩余问题仅限 [CompletableBlocks] / 轻微 [SignatureMismatch] / 可补全的 Coverage caution
- 可以进入补全阶段
- 全局 verdict 不得高于最差模块 verdict
NO-GO：
- 任一 blocker 命中
- 存在严重 [SignatureMismatch]
- Done Criteria 存在不可补全缺口
- 任一模块 verdict = NO-GO
工作流程
- 理解约束 - 项目规范
- 接收信息 - 实现阶段的 COMPLIANCE_CHECKLIST / Handoff Update 和 Dependency Closure Report
- 快速规范扫描 - 确认 COMPLIANCE_CHECKLIST 都通过
- 执行 Verdict Checklist - 依次检查 blocker、coverage 缺口、caution 范围、global 传导
- 给出判定 - Module Verdicts + Global Verdict（GO / GO-WITH-CAUTION / NO-GO）及理由
- 生成 VERIFICATION_REPORT - 直接返回，或按调用方合同写入指定工作文档
- 执行附加合同 - 若调用方要求同步写入结果信号或其他工作文档，按调用方合同执行
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.
- 9d ago First seen · 128 lines · 30 tokens per session scan A ea78b4602cf4
pipeline-verify-agent is an agent published in the GitHub repository yunzeforbetter/CastFlow (108 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,264 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
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
sap-test-plan-reviewer
Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
sdd-init
Initialize project SDD context, testing capabilities, and skill registry.
test-reviewer
Reviews test coverage and test quality for code changes.