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 agentmods add skills/yibie/spec-agents.md/checknpx skills add yibie/SPEC-AGENTS.md --skill checkgit clone --depth 1 https://github.com/yibie/SPEC-AGENTS.mdWrote 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/yibie/spec-agents.md/check)<a href="https://agentmods.dev/skills/yibie/spec-agents.md/check"><img src="https://agentmods.dev/badge/skills/yibie/spec-agents.md/check.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.02320 |
| Opus 5 | $0.00034 | $0.01160 |
| Sonnet 5 | $0.00013 | $0.00464 |
| Haiku 4.5 | $0.00007 | $0.00232 |
Grade A, and why
check 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 today.
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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check
用证据判断“实现是否满足已经确认的契约”。默认只读，不在检查过程中改代码或重写计划。
独立性声明
开头写明：本次 check 是否由执行 do 的同一上下文完成。
同一上下文时，下面的「权威落点」一项需要正面举证 —— 点名落点、点名地图条目、 说明两者相符 —— 而不是「没看出问题」。选择落点的上下文去审自己选的落点，是在 复核自己的决定；真实事故中的 15 条违例是独立 reviewer 发现的，不是自审发现的。
不强制独立执行：强制会让每个小改动都变贵。这里只是把盲区变成显式的。
固定比较基点
确定一个比较基点。读取变更相关的 .spec-agents/doctrine/docs/WORKFLOW.md、
CONTEXT.md、项目 .spec-agents/state/KERNEL.md、Protocol、Runbook、Lesson 和 AGENTS.md。
只读取与当前意图相关的知识记录，不要加载整个 docs/，也不要只凭 diff
猜意图。
比较基点按路径取：
- SPEC 路径：另读相关
SPEC.md和目标 Slice，契约轴对着它们比。 - 短路径（
plan直接approve）：没有 SPEC 也没有 Slice，契约轴对着plan交出的那句验收比，加上.spec-agents/state/KERNEL.md、Protocol 和AGENTS.md。 不要因为找不到 SPEC 就跳过契约轴，也不要为此创建 Slice。
三条轴在两条路径上都要跑。
三条检查轴
契约
- 目标、边界和 out-of-scope 是否符合 SPEC；
- 项目概念、身份、关系、生命周期和不变量是否符合
.spec-agents/state/KERNEL.md；框架工作流 语义是否符合.spec-agents/doctrine/docs/WORKFLOW.md与CONTEXT.md； - Action Contract 和稳定接口是否符合 Protocol；
- 相关代码实践、Runbook 前置条件和 Lesson 的
applies_when是否满足； - 旧行为是否仍被验证，新行为是否有明确证据。
权威落点。 符合 .spec-agents/state/KERNEL.md 不等于落在对的位置：第二份实现完全符合每一条
概念、身份、关系、生命周期和不变量，它只是多了一个。本体影响必答对它也会答
「否」——它没新增任何概念，那条规则 Kernel 里早就有。所以要单独核：
- 这条规则已经有权威落点了，本次改动是不是在第二个位置又实现了一遍？
- 前端／客户端是不是复制了一份服务端已经强制的规则？
- 派生状态是不是被持久化了两次？
- 切片写了
n/a的话，对着 diff 看它是否属实 —— 这次改动真的没有碰到任何 已有归属的规则吗？arrange只读意图，核不了这一条；check读得到 diff， 这里是唯一能核的地方。
命中任何一条，产出 semantic 发现交回 plan：要么改回权威落点，要么经
plan 修 Kernel 的地图，不允许沉默分叉。允许存在的第二落点必须有同输入等价
测试，见 .spec-agents/doctrine/docs/single-authority.md。
注意单测全绿不构成反证：与实现同层的测试无法证明实现在正确的层，测试和 错误落点是同一个决定的两个结果。
工程
- 测试、类型、错误处理、安全、可访问性和仓库规范；
- 是否存在数据丢失、状态泄漏或未覆盖的调用方；
- 项目自己的
docs/protocols/与编码约定。
在项目自身约定之上，叠加这份 smell 基线。它来自 Fowler 的 Refactoring， 是跨语言跨项目通用的判据，不是本框架发明的规则：
| Smell | 判据与处置 |
|---|---|
| Mysterious Name | 名字讲不清它是什么；改名，改不动就说明设计需要重想 |
| Duplicated Code | 同一段逻辑出现多处；抽出可复用形式 |
| Feature Envy | 一个方法主要在动别的对象的数据；把方法搬过去 |
| Data Clumps | 几个字段总是一起出现；打包成一个类型 |
| Primitive Obsession | 用基本类型冒充领域概念；建立类型 |
| Repeated Switches | 同一组条件分支反复出现；换成多态或映射表 |
| Shotgun Surgery | 一次改动散落到很多文件；把它们合并到一处 |
| Divergent Change | 一个文件为互不相关的原因被反复修改；按职责拆开 |
| Speculative Generality | 为想象中的需求做的抽象；SPEC 没要求就删掉 |
| Message Chains | a.b().c().d() 式的长导航；用一个方法封装 |
| Middle Man | 一个类大部分方法只是转发；直接调真正的目标 |
| Refused Bequest | 子类用不上继承来的大部分东西；改用组合 |
What ships with it
1 file 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.
- today Changed 576b8f51a110
- 5d ago First seen · 163 lines · 67 tokens per session scan A 1ae51f1dc7ce
check is a skill published in the GitHub repository yibie/SPEC-AGENTS.md (126 stars, last pushed 4d ago), licensed MIT. It adds 67 tokens to every session and 2,320 once invoked, about $0.0003 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…