agentmods.dev

live-connector: Skill for Claude Code

.agents/skills/refresh-skills/SKILL.md

refresh-skills is a skill for Claude Code, Codex from philtzjp/live-connector. It costs 191 tokens per session (1,800 once invoked), scanned A, original, MIT.

A maintenance guide for keeping project skills, their symbolic links, and the skill list in AGENTS.md or CLAUDE.md in agreement. A symbolic link is a file-system pointer to another location, while a skill is an instruction set for an agent.

In plain words
What is it for?
Use it after adding, removing, or renaming skills; when links may be broken; when instruction files disagree with the skill directories; or when safely checking and synchronizing skill definitions from upstream.
Why use it?
It helps detect and repair broken links, missing skill entries, inconsistent names, and differences between the local skill files and the upstream philtzjp/skills repository. It also requires user approval before bringing upstream changes into a project.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; installed under .agents/ (shared by several agents).

This is philtzjp/live-connector's own configuration. It tells Claude Code and Codex how to work on live-connector 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 live-connector configures →

not rated 8repo +4 2d ago A scan 191 tokens original MIT
View source ↗ philtzjp/live-connector
Reuse

Borrowing it

Nothing to install: this file belongs to philtzjp/live-connector. 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/philtzjp/live-connector/main/.agents/skills/refresh-skills/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/philtzjp/live-connector

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 refresh-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/philtzjp/live-connector/refresh-skills/github.svg)](https://agentmods.dev/skills/philtzjp/live-connector/refresh-skills)
Your own site
<a href="https://agentmods.dev/skills/philtzjp/live-connector/refresh-skills"><img src="https://agentmods.dev/badge/skills/philtzjp/live-connector/refresh-skills/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 refresh-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/philtzjp/live-connector/refresh-skills"><img src="https://agentmods.dev/badge/skills/philtzjp/live-connector/refresh-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 191 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,800 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.
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 $0.00191 $0.01800
Opus 5 $0.00096 $0.00900
Sonnet 5 $0.00038 $0.00360
Haiku 4.5 $0.00019 $0.00180

Measured 10d ago against content hash 4dcac314157b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

refresh-skills 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 10d 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.

.agents/skills/refresh-skills/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

スキル整合性のリフレッシュ

本スキルでは「エージェント指示ファイル」を AGENTS.md（正本）または CLAUDE.md（AGENTS.md への symlink、または単独の正本）として扱う。プロジェクトの構成に応じて読み替える。

原則

  1. MUST: スキルの正本は .agents/skills/<name>/SKILL.md に置く; NEVER: .claude/skills/<name>/SKILL.md を実ファイルとして編集しない
  2. MUST: .claude/skills/<name> は ../../.agents/skills/<name> への相対シンボリックリンクとして作成する; NEVER: 絶対パスのシンボリックリンクを作成しない
  3. MUST: エージェント指示ファイル（AGENTS.md / CLAUDE.md）のスキル表に列挙されたエントリと、.agents/skills/ 配下のディレクトリ集合と、.claude/skills/ 配下のシンボリックリンク集合の三者を一致させる
  4. MUST: スキル名は kebab-case を使用する
  5. NEVER: スキル本体に機密情報、トークン、認証情報を記載しない

発火タイミング

  1. 新しいスキルを追加する
  2. 既存スキルを削除またはリネームする
  3. .claude/skills/<name> のシンボリックリンクが切れている／不正である疑いがある
  4. エージェント指示ファイルのスキル表とディレクトリ実体が一致していない疑いがある
  5. 上流 (philtzjp/skills) からスキル定義の更新を取り込みたい

上流からの同期

  1. MUST: 同期前に git fetch --prune を実行する
  2. MUST: .agents/skills/ および エージェント指示ファイルの差分を git diff origin/main -- .agents/skills AGENTS.md CLAUDE.md で確認する
  3. IF: 差分がある; THEN MUST: 取り込み方針（マージ / リベース / ピックアップ）をユーザーに確認する
  4. NEVER: ユーザーの確認なしに上流変更を強制取り込みしない
  5. MUST: 同期後に「整合性検査」と「整合性修復」を実行する

整合性検査

  1. MUST: .agents/skills/ 配下のディレクトリ一覧と、それぞれに SKILL.md が存在することを確認する
  2. MUST: .claude/skills/ 配下のエントリがすべて ../../.agents/skills/<name> 形式の相対シンボリックリンクであることを確認する
  3. MUST: .agents/skills/<name> に対応する .claude/skills/<name> が存在することを確認する
  4. MUST: .claude/skills/<name> の解決先が実在する .agents/skills/<name> ディレクトリであることを確認する
  5. MUST: エージェント指示ファイルのスキル表 (| skill | 発火タイミング |) に列挙された skill 名が、.agents/skills/ 配下のディレクトリ集合と完全一致することを確認する
  6. MUST: 各 SKILL.md の frontmatter name フィールドがディレクトリ名と一致することを確認する

整合性修復

  1. IF: .agents/skills/<name>/SKILL.md が存在するのに .claude/skills/<name> が存在しない; THEN MUST: 相対シンボリックリンクを作成する: ln -s ../../.agents/skills/<name> .claude/skills/<name>
  2. IF: .claude/skills/<name> が実ファイル、または不正なリンク先を指している; THEN MUST: 削除して相対シンボリックリンクを作成し直す
  3. IF: .claude/skills/<name> の解決先 .agents/skills/<name> が存在しない（孤立シンボリックリンク）; THEN MUST: 削除する
  4. IF: エージェント指示ファイルのスキル表とディレクトリ集合が乖離している; THEN MUST: 表に行を追加・削除する
  5. IF: SKILL.md の frontmatter name がディレクトリ名と一致しない; THEN MUST: frontmatter を修正する
  6. MUST: 修復後、もう一度「整合性検査」を実行して再発しないことを確認する

Read the full file on GitHub · 74 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. 10d ago First seen · 74 lines · 191 tokens per session scan A 4dcac314157b

Subscribe to this mod's changes

refresh-skills is a skill published in the GitHub repository philtzjp/live-connector (8 stars, last pushed 2d ago), licensed MIT. It adds 191 tokens to every session and 1,800 once invoked, about $0.0010 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 2026-08-31.

Building agents
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