mandu-testing

mandu-testing is a skill for Claude Code, Codex from konamgil/mandu. It costs 42 tokens per session (861 once invoked), scanned A, original, MPL-2.0.

A testing guide for Mandu web applications, covering unit tests, integration tests, and browser-based end-to-end tests. It uses Bun test and Playwright.

In plain words
What is it for?
Writing tests for business logic, page components, interactive components, and complete user flows in a browser.
Why use it?
It helps you choose tests that follow the application's routes and component boundaries instead of testing around them.

Skill for Claude CodeCodex

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/konamgil/mandu/mandu-testing
Any agent
npx skills add konamgil/mandu --skill mandu-testing
Clone the repo
git clone --depth 1 https://github.com/konamgil/mandu

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 mandu-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/konamgil/mandu/mandu-testing.svg)](https://agentmods.dev/skills/konamgil/mandu/mandu-testing)
Your own site
<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-testing"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 861 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 $0.00042 $0.00861
Opus 5 $0.00021 $0.00430
Sonnet 5 $0.00008 $0.00172
Haiku 4.5 $0.00004 $0.00086

Measured 5d ago against content hash d45c3e2b80e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mandu-testing 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.

docs/archive/skills/mcp-v0/mandu-testing/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mandu Testing

Mandu 애플리케이션의 테스트 패턴 가이드. Bun test를 활용한 단위 테스트, slot 테스트, Island 컴포넌트 테스트, Playwright E2E 테스트를 다룹니다.

Agent Workflow Contract

This skill is a Domain addendum. It must not replace mandu-agent-workflow. Use it only after mandu.agent.plan selects testing or mandu.agent.verify asks for targeted test coverage.

Canonical workflow step: verify -> repair.

Preferred MCP tools:

Step Tools
plan mandu.agent.plan
verify mandu.agent.verify, mandu.run.tests, mandu.ate.generate, mandu.ate.run
repair mandu.agent.repair, mandu.ate.heal

Allowed file edits:

  • Co-located *.test.ts / *.test.tsx files
  • tests/e2e/**/*.spec.ts
  • Test fixtures and mocks scoped to the planned domain

Verification command:

mandu agent verify --changed --json --write

Common failures:

  • Running broad watch-mode tests as an agent default
  • Adding tests that bypass the route/slot/contract path under change
  • Applying ATE healing before reading the verify report

Repair path:

mandu agent repair --from .mandu/agent-verify.json --json

When to Apply

Reference these guidelines when:

  • Writing unit tests for slots
  • Testing Island components
  • Setting up E2E tests with Playwright
  • Mocking external dependencies
  • Testing authentication flows

Rule Categories by Priority

Priority Category Impact Prefix
1 Slot Testing HIGH test-slot-
2 Component Testing HIGH test-component-
3 E2E Testing MEDIUM test-e2e-
4 Mocking MEDIUM test-mock-

Quick Reference

1. Slot Testing (HIGH)

  • test-slot-unit - Unit test slot handlers
  • test-slot-guard - Test guard authentication
  • test-slot-integration - Integration test with database

2. Component Testing (HIGH)

  • test-component-island - Test Island components
  • test-component-render - Test rendering output
  • test-component-interaction - Test user interactions

Read the full file on GitHub · 133 lines

Files

What ships with it

7 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. 5d ago First seen · 133 lines · 42 tokens per session scan A d45c3e2b80e8

Subscribe to this mod's changes

mandu-testing is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 9d ago), licensed MPL-2.0. It adds 42 tokens to every session and 861 once invoked, about $0.0002 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.