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 JerryLookupU/klein-harness --skill blueprint-architectgit clone --depth 1 https://github.com/JerryLookupU/klein-harnessWrote 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/jerrylookupu/klein-harness/blueprint-architect)<a href="https://agentmods.dev/skills/jerrylookupu/klein-harness/blueprint-architect"><img src="https://agentmods.dev/badge/skills/jerrylookupu/klein-harness/blueprint-architect/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/skills/jerrylookupu/klein-harness/blueprint-architect"><img src="https://agentmods.dev/badge/skills/jerrylookupu/klein-harness/blueprint-architect.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 | $0.00077 | $0.02649 |
| Opus 5 | $0.00039 | $0.01324 |
| Sonnet 5 | $0.00015 | $0.00530 |
| Haiku 4.5 | $0.00008 | $0.00265 |
Grade A, and why
blueprint-architect 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 11d 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 — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This Skill Is For
这个 skill 负责把“我要做什么”收敛成“接下来该怎么做”的蓝图面。
它适合这些场景：
- 新能力设计
- 现有系统扩展
- 大改造前的设计收敛
- 需求模糊、边界不清、需要先定位约束
- 多方案对比和冲突分析
- recommendation / compare / choose / best-way 类问题
- 需要先出 draft blueprint，再 review，再定稿
- 需要先决定是否要做 targeted / deep research，再进入 blueprint
一句话：
先把蓝图做对，再让实现层接手。
它不是纯文档美化 skill。 它要产出的是可执行、可检查、可交接的 blueprint。
这个 Skill 负责什么
- 拆解目标、边界、成功标准
- 在仓库内定位相关代码、接口、配置、测试、扩展点
- 需要时查外部资料、官方文档、上游实现
- 提炼约束、风险、依赖、兼容性要求
- 对 recommendation / compare 请求先给 2 到 3 个方案与 trade-offs，再收敛成推荐方案
- 在需要时先形成 research memo，再把 memo 消化进 blueprint
- 生成草稿蓝图
- 做蓝图检查
- 做蓝图冲突分析
- 收敛为定稿蓝图
这个 Skill 不负责什么
- 直接跳过设计进入大规模实现
- 用一句“以后再说”掩盖关键冲突
- 只写口号式架构说明，不给接口、边界、迁移和验证面
- 把 blueprint 和 task plan 混成一份模糊清单
先决定当前模式
只选一个主模式，不要混着做。
greenfield
适合：
- 新功能、新系统、新子模块
- 仓库里还没有明确实现
重点：
- 先定义边界、接口、数据流、状态流、验证面
extension
适合：
- 现有系统上继续加能力
- 需要明确挂载点、兼容性、迁移成本
重点：
- 先定位扩展点、冲突点、复用面、不可破坏面
refactor
适合：
- 想重构、重分层、换抽象
- 需要避免“看起来更整洁但打坏现有行为”
重点：
- 先列行为约束、迁移顺序、验证门槛、回退路径
audit
适合：
- 已有蓝图，但怀疑它和代码/需求/测试漂移
重点：
- 先找缺口、冲突、假设失效点，再决定是修订还是重写
Progressive Disclosure
不要一次性把所有仓库文件和外部资料都塞进上下文。
默认先读
- 用户目标
- 项目根
README.md - 相关 package / build / test 配置
- 与目标最相关的源码目录
- 与目标最相关的测试目录
需要蓝图结构时再读
看 references/blueprint-schema.md。
这里只放：
- blueprint 应该最少包含哪些段
- draft 和 final 的差别
- blueprint 与 task plan 的边界
需要做冲突分析时再读
看 references/conflict-checklist.md。
这里只放：
- 常见冲突维度
- 如何判断是假冲突还是硬冲突
- 冲突写法模板
需要示例时再读
工作顺序
按这个顺序做。不要上来就写“最终方案”。
recommendation / compare 请求的前置规则
如果用户是在问“推荐哪个”“怎么选”“best way”“trade-off”：
- 先做 repo-local 定位，确认真实约束
- 先给 2 到 3 个可行方案
- 每个方案都要写明 trade-offs
- 明确给出推荐方案和理由
- 只有在推荐方案已经成立后，才进入 blueprint / plan
不要直接跳成单一路线计划，更不要直接进入实现。
1. 先把目标改写成设计问题
至少明确：
- 要解决什么问题
- 哪些不是这次要解决的问题
- 成功标准是什么
- 哪些约束不能碰
What ships with it
5 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.
- 11d ago First seen · 403 lines · 77 tokens per session scan A 1e968836776f
blueprint-architect is a skill published in the GitHub repository JerryLookupU/klein-harness (11 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 2,649 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…