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.
npx skills add mileson/openprd --skill openprd-benchmark-routergit clone --depth 1 https://github.com/mileson/openprdWrote 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/skills/mileson/openprd/openprd-benchmark-router)<a href="https://agentmods.dev/skills/mileson/openprd/openprd-benchmark-router"><img src="https://agentmods.dev/badge/skills/mileson/openprd/openprd-benchmark-router.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.02773 |
| Opus 5 | $0.00047 | $0.01386 |
| Sonnet 5 | $0.00019 | $0.00555 |
| Haiku 4.5 | $0.00009 | $0.00277 |
Grade A, and why
openprd-benchmark-router 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 4d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenPrd Benchmark Router
概览
这份 skill 负责把“最佳实践 / 对标 / benchmark / 参考产品 / prompt engineering / Agent harness / context engineering / CLI skill 体系优化 / 图标资源”类请求先路由到合适的证据源，再把结论落回 OpenPrd 的生成规则、skills、hooks、CLI 或测试。
它不是长文资料库，也不是外部项目复刻器。它的职责是：先判断该参考谁、怎么查、查到什么程度够用，然后再进入 OpenPrd 的设计和修改。
核心原则
- 不把对标当成固定关键词匹配。结合用户目标判断参考源是否真的能提升设计、实现、排查、评审、规划或文档质量。
- 不强行对标。环境、权限、账号、普通脚本报错、一次性短问答或与产品/领域设计无关的问题，继续当前任务即可。
- 不默认下载全文、仓库或整站。先保留轻量链接、来源 ID 和适用边界；真正需要事实时再读取。
- 通常只选 1-3 个最相关来源；不要为了显得全面而扩大上下文。
- 不把索引、来源目录或记忆当事实来源；未经核验的外部内容不能作为已确认事实输出。
触发信号
- 用户提到 OpenPrd、OpenSpec、Superpowers、Anthropic Skills、Lark CLI、Agent harness、AI code review、PR review、review lane、long-running agents、context engineering、prompt engineering、最佳实践、对标、参考、复刻或优化设计。
- 用户提到图标、icon、图标站、图标库、图标资源、UI 图标、AI 图标、技术图标、3D 图标、功能图标、iconfont 或视觉资产参考。
- 用户提到界面审美、设计框架、主题库、模板库、组件骨架、视觉资产库、前端体验风格或页面参考方法。
- 用户要求解释某个 Codex / Claude / Cursor agent 为什么没有发现 skill，或希望提升 skill 自动识别、路由、生成、安装和持续执行能力。
- 用户没有显式说 skill 名也要触发；不要要求用户记住
$openprd-benchmark-router。
路由流程
- 先识别优化对象：OpenPrd 产品/PRD 流程、CLI、skill 体系、长程任务、通用 harness、AI code review / PR review harness、context engineering、prompt engineering、图标资源或图标实现库。
- 读取当前工作区证据：
.openprd/、.openprd/benchmarks/index.md、.openprd/benchmarks/sources.yaml、AGENTS.md、repo-local skills、生成的.codex/.claude/.cursor引导和相关源码。 - 选择最小足够的外部证据源：公开 GitHub 仓库走 DeepWiki；第三方工具、SDK、CLI 或官方 API 用 Context7；产品官方文档、工程博客和一手资料用官方来源。
- 形成 OpenPrd 设计判断时，明确区分已证实事实、从来源归纳出的设计原则，以及对本项目的推断。
- 用分析维度提炼可迁移原则，避免照搬表面功能。
- 如果任务变成大量参考项目行为挖掘、长时间覆盖或需求补全，再路由到
$openprd-discovery-loop承接持续调研。
Project Registry
- 项目自己的
.openprd/benchmarks/优先于 OpenPrd 内置 Source Map。 sources.yaml里的 approved source 是长期可复用参考；inbox/里的 candidate 只表示待确认线索。- 用
openprd benchmark add <url|repo|file>写入 candidate，用openprd benchmark approve <id>纳入 approved registry。 - 执行或复盘中发现被用户采纳的优质信源时，用
openprd benchmark observe <url|repo|file> --notes <text>累计 evidence；达到阈值后只推荐 approve，不自动晋级。 - 用
openprd benchmark verify检查重复来源、失效链接、缺失本地文件和过宽触发规则。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 99 lines · 94 tokens per session scan A 7e12451b9598
openprd-benchmark-router is a skill published in the GitHub repository mileson/openprd (50 stars, last pushed 9d ago), licensed MIT. It adds 94 tokens to every session and 2,773 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
openspec-bulk-archive-change
Archive multiple completed changes at once. Use when archiving several parallel changes.
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
openspec-onboard
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
openspec-sync-specs
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
openspec-ff-change
Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.