live-connector: Skill for Claude Code

.agents/skills/skill-escalation/SKILL.md

skill-escalation is a skill for Claude Code, Codex from philtzjp/live-connector. It costs 162 tokens per session (1,703 once invoked), scanned A, original, MIT.

A set of instructions for improving an existing agent skill when it gives poor results, conflicts with newer information, or blocks a better solution.

In plain words
What is it for?
Use it to edit a skill's source instructions, check related rules, run consistency checks, and create a GitHub issue for broadly useful changes.
Why use it?
It explains when to adjust a skill locally and when a useful change should be proposed to the shared skills repository.

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 →

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/skill-escalation/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 skill-escalation

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/philtzjp/live-connector/skill-escalation"><img src="https://agentmods.dev/badge/skills/philtzjp/live-connector/skill-escalation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,703 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 $0.00162 $0.01703
Opus 5 $0.00081 $0.00851
Sonnet 5 $0.00032 $0.00341
Haiku 4.5 $0.00016 $0.00170

Measured 10d ago against content hash 8bb9407e3af8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

skill-escalation 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/skill-escalation/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

スキル改良とエスカレーション

発火タイミング

  1. 既存スキルに従って作業したが期待通り進まなかった
  2. Web 検索など外部情報源で、スキル記述と異なる/より新しい情報が得られた
  3. スキルの条件分岐を厳守するとスタックや実装の自由度が制限され、最良の結果が得られないと判断した

ローカル改変

  1. MUST: スキル正本 .agents/skills/<name>/SKILL.md を直接編集する
  2. MUST: 編集内容が commit-and-git / issue-branch-pr-flow など他スキルと矛盾しないか確認する
  3. MUST: 編集後は refresh-skills の整合性検査を実行し、description の意味(発火条件)が変わる場合は AGENTS.md / CLAUDE.md のスキル表も更新する
  4. NEVER: .claude/skills/<name>/SKILL.md の symlink 先以外を編集する(実体は .agents/skills/<name>/SKILL.md

エスカレーション判断

  1. MUST: ローカル改変が他ユーザー/他エージェントにも有用と判断した場合、philtzjp/skills リポジトリに変更提案 Issue を起票する
  2. SHOULD: 単発のワークアラウンドや、特定タスク固有の例外は Issue 化しない
  3. SHOULD: 既存 Issue / PR があれば、新規起票せずそこへコメント追記する

Issue 起票

  1. MUST: gh issue create --title "<title>" --body-file <file> で起票する
  2. MUST: タイトルは type(scope): 短い日本語 形式を使用する
    • typefeat / fix / perf / refactor のいずれか
    • scope は変更対象スキル名(例: commit-and-git / refresh-skills / skill-selection
  3. MUST: タイトルの説明は動作で終える(OK: 〜する / 〜修正 / 〜追加 / 〜削除 / 〜実装 / 〜廃止 など); NEVER: 体言止めにしない; NEVER: emoji を含めない; MUST: 1 行で完結させる
  4. MUST: Issue 本文の先頭は AGENTS.md / CLAUDE.md 運用ルールの署名規約に従い、✳︎ <会社名> <モデル名> <バージョン> 形式の署名行を入れ、1 行空けて本文を続ける
  5. MUST: 本文には「背景」「作業範囲」「完了条件」「備考」セクションを設ける(後述のテンプレートを使用)

タイトル例

  • feat(commit-and-git): scope のドット込みディレクトリ表記ルールを明文化する
  • fix(refresh-skills): symlink 検査スクリプトの誤検知を修正する
  • refactor(issue-branch-pr-flow): マージ前チェック手順を再編する
  • perf(api-design): OpenAPI 検証コマンドの実行時間を短縮する

本文テンプレート

gh issue create --body-file <file> に渡すファイル(または --body の文字列)の中身は以下を使用する。<...> を具体内容に置き換える。

✳︎ <会社名> <モデル名> <バージョン>

## 背景

なぜこの作業が必要か、動機・関連 Issue/PR を 1〜3 文で書く。

## 作業範囲

- やること 1
- やること 2

## 完了条件

- 受け入れ条件 1
- 受け入れ条件 2

## 備考

補足・参考リンク・注意点(任意)。

GitHub Issue Template ファイル(参考)

GitHub Web UI 経由で人間が起票する場合は、リポジトリルートに .github/ISSUE_TEMPLATE/skill-escalation.md を配置する。frontmatter 付き全文は以下:

---
name: skill-escalation
about: より良いスキルにするための変更提案をスキルの正本リポジトリに対して起票する
title: "type(scope): 短い日本語"
labels: ""
assignees: ""
---

<!--
タイトル形式: type(scope): 短い日本語

  type は次のいずれか:
    feat / fix / perf / refactor

  scope は変更範囲(スキル名):

  短い日本語の説明:
    - 体言止めは使用しない(〜する / 〜修正 / 〜追加 / 〜削除 / 〜実装 / 〜廃止 等、動作の意味を持たせる)
    - emoji は使用不可
    - 1 行で完結させる
    - 例: chore(ci): Github Workflow の不整合を修正
    - 例: feat(numsec): plugin と gui を monorepo に移行
    - 例: refactor(xtask): Standalone Target を物理削除
-->

✳︎ ${会社名} ${モデル名} ${バージョン名}

## 背景

なぜこの作業が必要か、動機・関連 Issue/PR を 1〜3 文で書く。

## 作業範囲

- やること 1
- やること 2

## 完了条件

- 受け入れ条件 1
- 受け入れ条件 2

## 備考

補足・参考リンク・注意点(任意)。

Read the full file on GitHub · 127 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 · 127 lines · 162 tokens per session scan A 8bb9407e3af8

Subscribe to this mod's changes

skill-escalation is a skill published in the GitHub repository philtzjp/live-connector (8 stars, last pushed 2d ago), licensed MIT. It adds 162 tokens to every session and 1,703 once invoked, about $0.0008 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.

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