fake-summoner-client

fake-summoner-client is a skill for Claude Code from recca0120/code-quest. It costs 62 tokens per session (2,829 once invoked), scanned A, original, MIT.

A test harness for React components, contexts, and hooks that need a simulated socket connection and message-processing pipeline. It provides helpers for testing one channel or a complete workspace with multiple tabs.

In plain words
What is it for?
Use it to render React tests with a channel or workspace, inject state, simulate user messages and assistant turns, and test multi-tab behavior.
Why use it?
It supplies the surrounding application state and connections that these client-side tests would otherwise need to build themselves.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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.

agentmods
npx agentmods add skills/recca0120/code-quest/fake-summoner-client
Any agent
npx skills add recca0120/code-quest --skill fake-summoner-client
Clone the repo
git clone --depth 1 https://github.com/recca0120/code-quest

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 fake-summoner-client

README.md
[![agentmods](https://agentmods.dev/badge/skills/recca0120/code-quest/fake-summoner-client.svg)](https://agentmods.dev/skills/recca0120/code-quest/fake-summoner-client)
Your own site
<a href="https://agentmods.dev/skills/recca0120/code-quest/fake-summoner-client"><img src="https://agentmods.dev/badge/skills/recca0120/code-quest/fake-summoner-client.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,829 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00062 $0.02829
Opus 5 $0.00031 $0.01414
Sonnet 5 $0.00012 $0.00566
Haiku 4.5 $0.00006 $0.00283

Measured 5d ago against content hash d4c06394fe5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

fake-summoner-client 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 5d 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.

.claude/skills/fake-summoner-client/SKILL.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FakeSummoner — Client Tests

核心概念

Client 端 FakeSummoner 繼承 server 基礎版 + 加上 TypedSocket 型別。搭配兩個 render helper:

  • renderWithWorkspace — 完整 workspace,適合 多 tab / workspace-level 測試
  • renderWithChannel — 單一 channel 包好,適合 component / context / hook 測試

React 互動必須在 act() 裡 flush。

Import 來源

東西 從哪 import
renderWithChannel / renderWithWorkspace @/test/render-with-channel / @/test/render-with-workspace
createFakeSummoner / FakeSummoner @/test/fake-summoner(含 TypedSocket 強型別)
createFakeServer @code-quest/server/test
segments as s / controlRequest* @code-quest/summoner/test
sendUserMessage / emitAssistantTurn @/test/helpers

renderWithChannel — 最常用

自動包 SocketProviderSessionProvider → ... → TabProviderChannelProvider,並跑 claude.initialize()

import { renderWithChannel } from '@/test/render-with-channel';
import { segments as s } from '@code-quest/summoner/test';

const { claude, channelId, user } = await renderWithChannel(<ChatPanel />);

await user.type(screen.getByPlaceholderText(/Esc to focus/i), 'hello{Enter}');
await act(async () => {
  await claude.emitSegment(s.assistant('Hi back'));
  await claude.emitSegment(s.result());
});

expect(screen.getByText('Hi back')).toBeInTheDocument();

選項

await renderWithChannel(<MyComponent />, {
  channelId: 'ch-test',
  skipInit: false,                    // false = 自動 initialize
  extraSegments: [                    // 額外 init-time segments
    s.controlResponse('init', { models: [{ value: 'opus-4-6' }] }),
  ],
  initialState: {                     // ChannelProvider 的 initial state 注入
    pendingControls: [{ requestId: 'r1', subtype: 'can_use_tool', toolName: 'Bash' }],
  },
  launchOnMount: false,               // true = React 驅動 session:launch
  cwd: '/test/cwd',
});

skipInit: true 用於外部控制啟動流程(搭配 cwd prop)。

renderWithWorkspace — 多 session 測試

整個 WorkspaceLayout 入口(含 project list / tab bar)。

Read the full file on GitHub · 279 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. 5d ago First seen · 279 lines · 62 tokens per session scan A d4c06394fe5a

Subscribe to this mod's changes

fake-summoner-client is a skill published in the GitHub repository recca0120/code-quest (11 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 2,829 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

react-native-testing

Write tests using React Native Testing Library (RNTL) v13 and v14 (@testing-library/react-native). Use when writing, reviewing, or fixing React Native component tests. Covers: render, screen, queries (getBy/getAllBy/queryBy/findBy), Jest matchers, userEvent, fireEvent, waitFor, and async patterns. Supports v13 (React…

callstack/react-native-testing-library · 134 tokens

hook-test

Write and run jest tests for a hook in @reactuses/core, following the repo's conventions (co-located index.spec.ts, renderHook/act, fake timers, the .test/ helpers, and the SSR jest-environment pragma). Triggers on "write a test", "add test coverage", "fix the failing test", or "test this hook".

childrentime/reactuse · 77 tokens

react-testing

Write and review React/TypeScript tests for Sentry's frontend using Jest and React Testing Library. Use when adding or editing tests in static/ (.spec.tsx), writing component/hook tests, mocking API responses with MockApiClient, testing routing or network requests, or when asked to "write a frontend test", "add a…

getsentry/sentry · 86 tokens

authoring-data-quality-checks

Adds and runs data quality checks (dbt-test style assertions) on a project's warehouse tables and saved-query views: not-null, uniqueness, accepted values, referential integrity, row-count bounds, freshness, and custom HogQL. Use when asked to test a model, validate a view, check for nulls or duplicates, add data…

PostHog/posthog · 161 tokens

frontend-testing

Generate Vitest + React Testing Library tests for frontend components, hooks, and utilities. Triggers on testing, spec files, coverage, Vitest, RTL, unit tests, integration tests, or write/review test requests.

PageAI-Pro/ralph-loop · 48 tokens

writing-unit-tests

Guidelines for writing unit tests in the Hex1b TUI library. Use when creating new tests for widgets, nodes, or terminal functionality.

mitchdenny/hex1b · 33 tokens