spec-steward

spec-steward is a skill for Claude Code, Codex from zhuanggenhua/BoardGame. It costs 50 tokens per session (2,402 once invoked), scanned A, original, MIT.

A repository-maintenance skill for a BoardGame project’s .spec directory, which stores agents, reusable skills, rules, decisions, and supporting knowledge. It keeps these documents in the right places and keeps their indexes and lists up to date.

In plain words
What is it for?
Use it when adding, changing, or removing an agent, skill, rule, knowledge document, or decision, or when documenting completed code or design work.
Why use it?
It prevents project instructions from becoming misplaced, inconsistent, or difficult for agents to find. It also records important implementation changes in the project knowledge base.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it when adding, changing, or removing an agent, skill, rule, knowledge document, or decision, or when documenting completed code or design work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zhuanggenhua/boardgame/spec-steward
Install

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.

Any agent
npx skills add zhuanggenhua/BoardGame --skill spec-steward
Clone the repo
git clone --depth 1 https://github.com/zhuanggenhua/BoardGame

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for spec-steward

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/spec-steward/github.svg)](https://agentmods.dev/skills/zhuanggenhua/boardgame/spec-steward)
Your own site
<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/spec-steward"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/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.

agentmods 80×15 button for spec-steward

Your own site · 80×15
<a href="https://agentmods.dev/skills/zhuanggenhua/boardgame/spec-steward"><img src="https://agentmods.dev/badge/skills/zhuanggenhua/boardgame/spec-steward.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,402 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.02402
Opus 5 $0.00025 $0.01201
Sonnet 5 $0.00010 $0.00480
Haiku 4.5 $0.00005 $0.00240

Measured 3d ago against content hash 099df3902977, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 3d 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.

.spec/skills/spec-steward/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 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。 本技能不复述业务规范;权威在 .spec/AGENTS.mdknowledge/README.mdrules/system.md 和对应 skill 正文。

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 / decisions)时。
  • 需要清理 AI 文档冗余、降低误读、压缩长规则或做全量自查时。
  • 用户问“规范有没有问题 / 规范的规范有没有问题 / 要不要更新规范”时,先定位对应规范责任,而不是默认进入全量整理。

前置条件

  • 能随时查阅 .spec/AGENTS.md(调度核心、宿主差异)与 knowledge/README.md(知识导航)。
  • 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)

  1. 判类型——这份内容属于哪一类:
    • 禁止碰什么(护栏)→ rules/(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 .spec/AGENTS.md 的准入口径,再照 reviewer 范例写)
    • 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)
    • 决策原因 → decisions/(ADR,只记录为什么)
  2. 放对位置 + 命名
    • agent 文件:<name>.agent.md
    • skill 目录:skills/<name>/SKILL.md
    • knowledge 文档:kebab-case,放在 standards/features/
  3. 写 frontmatter
    • agents:仅 name + description
    • skills:仅 name + description
    • knowledge:name + description + metadatatype / status
    • rules / decisions:无 frontmatter
  4. 同步登记
    • 加 / 删子 Agent → 更新 .spec/AGENTS.md 子 Agent 名册与宿主差异表
    • 加 / 删知识文档 → 更新 knowledge/README.md
    • 加 / 删 ADR → 更新 decisions/README.md
    • 改动影响调度 → 更新 .spec/AGENTS.md 调度核心

流程 B · 沉淀知识(改动完成后)

  1. 一句话总结:这次改了什么、为什么。
  2. 判断文档归属:
    • 影响开发流程 / 规范 → 更新 knowledge/standards/ 对应文件。
    • 影响功能设计 → 找 knowledge/features/ 对应文档;有就更新,没有就从 _TEMPLATE.md 新建。
    • 决策 → decisions/ 新增 ADR。
    • 复发问题 / 踩坑经验 → 追加进 knowledge/lessons.md
  3. 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)。
  4. 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。
  5. knowledge/README.md 导航行来源于 frontmatter description,同一句话口径。
  6. 待执行事项走任务卡,不堆进知识库。

Read the full file on GitHub · 132 lines

Changes

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.

  1. 3d ago Changed · +1 lines 099df3902977
  2. 6d ago Changed · +25 lines 9ebea6b8357e
  3. 11d ago First seen · 106 lines · 50 tokens per session scan A 0216134a9b59

Subscribe to this mod's changes

spec-steward is a skill published in the GitHub repository zhuanggenhua/BoardGame (23 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 2,402 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens