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 Go1c/LumioAgent --skill spec-stewardgit clone --depth 1 https://github.com/Go1c/LumioAgentWrote 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/go1c/lumioagent/spec-steward)<a href="https://agentmods.dev/skills/go1c/lumioagent/spec-steward"><img src="https://agentmods.dev/badge/skills/go1c/lumioagent/spec-steward/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/go1c/lumioagent/spec-steward"><img src="https://agentmods.dev/badge/skills/go1c/lumioagent/spec-steward.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 | $0.00072 | $0.02083 |
| Opus 5 | $0.00036 | $0.01042 |
| Sonnet 5 | $0.00014 | $0.00417 |
| Haiku 4.5 | $0.00007 | $0.00208 |
Grade A, and why
spec-steward 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Steward（仓库管家）
保证对 .spec/ 的任何改动都「放对位置、格式合规、索引与名册同步」，并在开发完成后把「改了什么、为什么」沉淀回知识库。
本技能不复述那些规矩（权威在 AGENTS.md 与 knowledge/README.md），只在改动发生时把规矩用起来，并指回对应处。
何时使用
- 新增 / 修改 / 删除一个子 Agent、Skill、知识文档或规则时。
- 完成一处代码 / 设计改动后，要把它沉淀进
knowledge/时。 - 不确定某份内容该放哪（rules / standards / features / agents / skills）时。
前置条件
- 能随时查阅
AGENTS.md（调度核心、宿主差异）与knowledge/README.md（知识导航）——本技能指回它们，不重复。 - 改动目标明确（知道要加 / 改 / 删什么）。
操作步骤
流程 A · 维护结构（新增 / 修改 / 删除能力）
- 判类型——这份内容属于哪一类：
- 禁止碰什么（护栏）→
rules/（系统级硬规则在rules/system.md，无 frontmatter） - 怎么做（流程 / 规范）→
knowledge/standards/（见knowledge/README.md） - 某功能的设计 / 记录 →
knowledge/features/<领域>/…（见knowledge/README.md） - 一个职能角色 →
agents/（先过AGENTS.md的准入门槛「隔离本身即是产出价值」，再照reviewer范例写，正文承载判断；frontmatter 见下面第 3 步，禁令见rules/system.md） - 可复用方法 →
skills/<name>/SKILL.md（目录名即 skill 名；description 只写触发条件、不概括流程——概括流程的 description 会让 agent 照描述走捷径、跳过正文）
- 禁止碰什么（护栏）→
- 放对位置 + 命名（agent 文件
<name>.agent.md、skill 目录skills/<name>/；均 kebab、全局唯一，且目录 / 文件名与 frontmattername一致）。 - 写 frontmatter：
- agents：仅
name+description - skills：仅
name+description（Agent Skills 开放标准允许license等可选字段，但本仓约定只用这两个，spec-lint 强制） - knowledge：
name+description+metadata（type / status） - rules：无 frontmatter
- agents：仅
- 同步登记（漏一处，能力就隐身）：
- 加 / 删子 Agent → 更新
AGENTS.md子 Agent 名册 + 宿主差异表 - 加 / 删 skill → 在用得上的 agent「使用的技能」里登记 / 移除
- 加 / 删知识文档 → 更新
knowledge/README.md文件导航 - 改动影响调度 → 更新
AGENTS.md调度核心
- 加 / 删子 Agent → 更新
流程 B · 沉淀知识（改动完成后）
- 一句话总结：这次改了什么、为什么。
- 判断文档归属：
- 影响开发流程 / 规范（workflow / 测试策略 / 代码风格等）→ 更新
knowledge/standards/对应文件。 - 影响功能设计（新功能、行为变更）→ 找
knowledge/features/对应文档：有就更新，没有就从_TEMPLATE.md新建（放对领域 / 模块）——只写设计现状，不留决策记录。 - 决策（功能内与框架级都算：为什么这样调度 / 选型 / 划边界）→
decisions/新增 ADR（全仓唯一落点，见decisions/README.md）。 - 复发问题 / 踩坑经验（reviewer 退回报告、known gaps 中第二次出现的同类问题）→ 追加进
knowledge/lessons.md（收录准入与条目格式见该文档）。
- 影响开发流程 / 规范（workflow / 测试策略 / 代码风格等）→ 更新
- 更新正文——只保留当前有效内容，交付历史不入库（git 提交即历史）。
- frontmatter
status只能取枚举：设计中/实施中/已交付/历史归档；description保持一句话（是什么 + 何时查，≤120 字符，spec-lint 强制），不得把交付历史写进 description / status。 knowledge/README.md导航行来源于 frontmatterdescription：同一句话口径，允许排版差异，但不得出现 description 没有的事实、不含交付历史（行文一致性靠本步骤自觉，spec-lint 只机械校验长度 / 枚举 / 覆盖 / 链接）——导航是每次 init 的强制税，一行膨胀 = 所有会话永久付费。- 待执行的事走任务卡（拆解用
task-breakdown），别堆进知识库。
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 · 98 lines · 72 tokens per session scan A 1a83538e7cc3
spec-steward is a skill published in the GitHub repository Go1c/LumioAgent (20 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 2,083 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…