claude-plugins-manager: Skill for Claude Code

.claude/skills/update-settings-options/SKILL.md

update-settings-options is a skill for Claude Code from vivalalova/claude-plugins-manager. It costs 22 tokens per session (2,819 once invoked), scanned A, original, MIT.

A workflow for keeping a Claude Code extension's settings schema, types, interface, translations, tests, documentation, and environment-variable list aligned with Claude Code's official settings documentation.

In plain words
What is it for?
Use it when Claude Code settings or environment variables change, to detect missing options and update the related code, user interface, translations, tests, and documentation.
Why use it?
Settings can change in the official documentation while an extension still shows older options. This workflow finds those differences and supports reviewing, applying, and verifying the necessary updates.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

This is vivalalova/claude-plugins-manager's own configuration. It tells Claude Code how to work on claude-plugins-manager itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-plugins-manager configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vivalalova/claude-plugins-manager. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vivalalova/claude-plugins-manager/main/.claude/skills/update-settings-options/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vivalalova/claude-plugins-manager

Made for: Claude Code.

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 update-settings-options

README.md
[![agentmods](https://agentmods.dev/badge/skills/vivalalova/claude-plugins-manager/update-settings-options/github.svg)](https://agentmods.dev/skills/vivalalova/claude-plugins-manager/update-settings-options)
Your own site
<a href="https://agentmods.dev/skills/vivalalova/claude-plugins-manager/update-settings-options"><img src="https://agentmods.dev/badge/skills/vivalalova/claude-plugins-manager/update-settings-options/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 update-settings-options

Your own site · 80×15
<a href="https://agentmods.dev/skills/vivalalova/claude-plugins-manager/update-settings-options"><img src="https://agentmods.dev/badge/skills/vivalalova/claude-plugins-manager/update-settings-options.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,819 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00022 $0.02819
Opus 5 $0.00011 $0.01409
Sonnet 5 $0.00004 $0.00564
Haiku 4.5 $0.00002 $0.00282

Measured 8d ago against content hash e5ff5d97e5dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

update-settings-options scanned grade A with 1 finding 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (references/scripts/sync-settings.workflow.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **primary**:官方 docs `code.claude.com/docs/en/settings.md`(直接 curl 取 Markdown,確定性 parse)
.claude/skills/update-settings-options/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

update-settings-options

讓 extension 的 settings surface(schema + 衍生 types + UI + i18n + tests + docs + env registry)跟上 Claude Code 目前有哪些設定選項——以官方 docs code.claude.com/docs/en/settings.md 為準,由確定性 CLI 偵測 gap。

Trigger

  • sync settings from docs
  • update settings options
  • Claude settings docs changed

形狀:workflow 探查 → 主迴圈套用

這個 skill 用一個 workflow 跑「探查」,再由主迴圈做「決策 + 套用 + 驗證」。分工不是半套,是兩個硬限制逼出來的:

  1. 背景 workflow 不能 AskUserQuestion — section 歸屬的確認必須回主迴圈做。
  2. 本 repo 禁止 test/build 併發(見 CLAUDE.md)— workflow 會 fan-out 平行 agent,若在裡面跑 typecheck/test/build 會違反「整台機器同時僅一個」。

所以:workflow 擁有唯讀、可平行、無副作用的部分(跑 CLI 取 gap → 逐 gap 分類),回傳結構化 gap report;主迴圈擁有互動 + 寫檔 + 序列驗證的部分

Source of truth

  • primary:官方 docs code.claude.com/docs/en/settings.md(直接 curl 取 Markdown,確定性 parse)
  • env vars:官方 docs code.claude.com/docs/en/env-vars.md(同上)
  • 偵測 CLIscripts/settings-sync-diff.ts(curl live docs → parse → diff against repo schema → 輸出 JSON)。exit 1 = health failure 或 fetch error,workflow 即報錯。
  • fail-fast:CLI exit 1 → workflow throw,不 fallback

細節見 references/sources.md

Key categories

Schema 含多種 key,只有 user-facing 需要進 settings UI。判定準則與完整 excluded 清單以 references/surface-map.md 為準;機器強制排除清單(SSOT)在 src/shared/settings-sync/settings-diff.tsKNOWN_EXCLUDED

Category 處理
user-facing 同步(按 surface-map 分 section)
anti-direction 同步到現有 AdvancedSection(啟用後違反低成本/高效率/高精度方向)
managed-only skip → 加入 KNOWN_EXCLUDED
plugin-internal skip → 加入 KNOWN_EXCLUDED
deprecated skip → 加入 KNOWN_EXCLUDED
meta skip → 加入 KNOWN_EXCLUDED

Step 1 — 跑探查 workflow

Workflow({ scriptPath: ".claude/skills/update-settings-options/references/scripts/sync-settings.workflow.js" })

腳本(references/scripts/sync-settings.workflow.js)兩個 phase,全唯讀:

  • Detect:一個 agent 跑 Bash npx tsx scripts/settings-sync-diff.ts(cwd repo root),拿回 JSON { settingsGaps, removedKeys, envGaps, envRemoved, counts, health }。四個 diff 方向皆該 CLI 的確定性結果:settingsGaps/removedKeys 已扣掉 KNOWN_EXCLUDED/KNOWN_REPO_ONLYenvRemoved 已扣掉 KNOWN_ENV_REPO_ONLY(docs 記在別頁或僅 prose 提及的 var);settingsGapsenvGaps 每筆帶 docs 原文 description。CLI exit 1 → 報錯。
  • Categorize(平行):對每個 settingsGap{key, description})把 description inline 餵給分類 agent,指派 section(用 surfaceMapHint)、判斷是否 isObjectEditor(需手寫 object editor)、標記 non-user-facing key 需加入 KNOWN_EXCLUDEDremovedKeysenvGapsenvRemoved 原樣傳回,不走 LLM 分類——刪除/registry 變更判斷交回主迴圈確認。

Read the full file on GitHub · 142 lines

Files

What ships with it

6 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.

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. 8d ago First seen · 142 lines · 22 tokens per session scan A e5ff5d97e5dc

Subscribe to this mod's changes

update-settings-options is a skill published in the GitHub repository vivalalova/claude-plugins-manager (2 stars, last pushed 18d ago), licensed MIT. It adds 22 tokens to every session and 2,819 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

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

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…

microsoft/vscode · 72 tokens