EngramGraph: Skill for Claude Code

.agents/skills/journey-test-assistant/SKILL.md

journey-test-assistant is a skill for Claude Code from AsiaOstrich/EngramGraph. It costs 123 tokens per session (2,341 once invoked), scanned A, original, MIT.

A tool that creates a user-journey test plan and matching end-to-end test skeletons from a project description. End-to-end tests check a complete flow across the system, while a user journey is a connected sequence of actions.

In plain words
What is it for?
Use it to define user roles and journeys, create TESTPLAN files and test skeletons, or find missing coverage in existing journey tests.
Why use it?
It helps test whether state and actions remain correct across several features, rather than checking each feature in isolation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is AsiaOstrich/EngramGraph's own configuration. It tells Claude Code how to work on EngramGraph 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 EngramGraph configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AsiaOstrich/EngramGraph. 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/AsiaOstrich/EngramGraph/main/.agents/skills/journey-test-assistant/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AsiaOstrich/EngramGraph

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 journey-test-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/asiaostrich/engramgraph/journey-test-assistant/github.svg)](https://agentmods.dev/skills/asiaostrich/engramgraph/journey-test-assistant)
Your own site
<a href="https://agentmods.dev/skills/asiaostrich/engramgraph/journey-test-assistant"><img src="https://agentmods.dev/badge/skills/asiaostrich/engramgraph/journey-test-assistant/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 journey-test-assistant

Your own site · 80×15
<a href="https://agentmods.dev/skills/asiaostrich/engramgraph/journey-test-assistant"><img src="https://agentmods.dev/badge/skills/asiaostrich/engramgraph/journey-test-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,341 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 $0.00123 $0.02341
Opus 5.5 $0.00049 $0.00936
Sonnet 5.5 $0.00025 $0.00468
Haiku 4.5 $0.00012 $0.00234

Measured 14d ago against content hash 2e6a0a97a328, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

journey-test-assistant 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 14d 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.

Makes network callslowCapability

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

- 驗證指令:`curl $BASE_URL/health`
.agents/skills/journey-test-assistant/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Journey Test Assistant | 旅程測試助手

從專案描述生成連貫的使用者旅程測試計畫(TESTPLAN-NNN.md)與對應的 E2E 骨架,讓每個新專案從第一天起就擁有完整測試旅程。

與 /e2e 的差異

維度 /e2e /journey-test
組織單位 單一 XSPEC/AC 跨 Story 的使用者旅程
測試結構 隔離、獨立 連貫、狀態共享
產物 *.spec.ts 骨架 TESTPLAN.md + *.journey.spec.ts
觸發時機 功能完成後 專案建立時(Journey-First)
偵測目標 單一 AC 是否正確 跨步驟狀態傳遞是否連貫

工作流程

輸入:專案描述 / 現有 TESTPLAN / --analyze
    ↓
Phase 1:定義 Persona
    分析專案描述 → 識別所有使用者角色 → 定義 Actor/Role/Key Permissions
    ↓
Phase 2:設計旅程地圖
    列出主要業務目標 → 拆解為 T-NNN 群組 → 宣告依賴鏈
    ↓
Phase 3:生成 TESTPLAN
    按格式輸出 test-plans/TESTPLAN-001.md(含 Personas、步驟、依賴圖)
    ↓
Phase 4:生成 E2E 骨架
    從 TESTPLAN T-NNN 生成 *.journey.spec.ts(含 skipIf + 共享 state)

模式

1. 生成模式(預設)

從專案描述生成完整的 TESTPLAN + E2E 骨架。

/journey-test "電商平台,需要 buyer/seller/admin 三個角色"

產物:

  • test-plans/TESTPLAN-001.md:含 Personas、T-000 環境重置、T-001~T-NNN 步驟群組、執行順序依賴圖
  • src/e2e/journey/main-flow.journey.spec.ts:含 describe.skipIf + 共享 state + T-NNN 對應的完整骨架

2. 分析模式(--analyze)

掃描現有測試,找出旅程覆蓋缺口。

/journey-test --analyze

執行步驟:

  1. 讀取 test-plans/TESTPLAN-NNN.md(若存在)
  2. 掃描 src/e2e/ 下所有 *.journey.spec.ts 和 *.journey.e2e.test.ts
  3. 比對 TESTPLAN T-NNN 與自動化測試中的 T-NNN 引用
  4. 輸出 Coverage gap 報告:列出 TESTPLAN 中缺乏自動化對應的 T-NNN 步驟

3. Archetype 模式(--archetype)

使用預設旅程模板,適合已知類型的專案快速啟動。

/journey-test --archetype A1    # Spec-driven 旅程
/journey-test --archetype A2    # UI-driven 旅程
/journey-test --archetype A3    # Brownfield 旅程
Archetype 模板 適用場景
A1 Spec-driven 需求 → Spec → Code → Test,適合 API/Backend 專案
A2 UI-driven 設計稿 → UI → 視覺回歸,適合前端/全端專案
A3 Brownfield 現有程式碼 → 分析 → 重構驗證,適合既有專案補測試

TESTPLAN 格式(T-NNN)

以下為完整的 TESTPLAN 範本,展示所有必要區段:

# TESTPLAN-001 <ProjectName> 主線旅程

## Personas

| Actor         | Role          | Key Permissions              |
|---------------|---------------|------------------------------|
| platform_admin | Platform Admin | 建立 Org、管理使用者、查看所有資源 |
| org_member    | Org Member    | 讀取專案、執行 Pipeline         |

## Environment

- BASE_URL:`http://localhost:3000`(本機)/ `$JOURNEY_BASE_URL`(CI)
- 驗證指令:`curl $BASE_URL/health`
- 必要帳號:`ADMIN_EMAIL`、`ADMIN_PASSWORD` 環境變數

## T-000 環境重置(optional)

前置條件:無
depends_on:無

| 步驟    | 操作                              | 預期結果        |
|---------|-----------------------------------|-----------------|
| T-000-1 | [API] GET /health                | 回傳 200 OK     |
| T-000-2 | [CHECK] 資料庫連線正常            | 無錯誤日誌      |

## T-001 Platform Admin 登入

前置條件:環境正常運行(T-000 通過)
depends_on:T-000

| 步驟    | 操作                                        | 預期結果                 |
|---------|---------------------------------------------|--------------------------|
| T-001-1 | [API] POST /api/auth/login(admin 帳號)    | 回傳 200 + authToken     |
| T-001-2 | [CHECK] authToken 存入共享 state            | let authToken 有值       |

## T-010 主要功能操作

前置條件:authToken 已取得(T-001 通過)
depends_on:T-001

| 步驟    | 操作                                        | 預期結果                 |
|---------|---------------------------------------------|--------------------------|
| T-010-1 | [API] POST /api/resources(帶 authToken)   | 回傳 201 + resourceId ★  |
| T-010-2 | [CHECK] resourceId 存入共享 state           | let resourceId 有值      |

## 執行順序依賴圖

T-000 → T-001 → T-010

Read the full file on GitHub · 208 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. 14d ago First seen · 208 lines · 123 tokens per session scan A 2e6a0a97a328

Subscribe to this mod's changes

journey-test-assistant is a skill published in the GitHub repository AsiaOstrich/EngramGraph (3 stars, last pushed today), licensed MIT. It adds 123 tokens to every session and 2,341 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-16.

Related

Other skills, from other repositories

nguyen-ly-test-file-tach-biet

(Use when) Dùng khi cần tạo, review, hoặc tổ chức cấu trúc test file (unit, component) theo mô hình tách biệt 100% khỏi mã nguồn sản phẩm (Electron/Desktop/Frontend), hoặc theo Go convention (test.go cùng package). Bao gồm fixtures, path aliases, build isolation, phân định rõ giữa electron/test/ (nội bộ) với…

tamnguyendinh/Anvien · 105 tokens

kivgraph

Use Kivgraph's local MCP server to search symbols, read their source, and follow references, dependencies, cross-repository consumers and graph status in the indexed code graph.

Luqueee/kivgraph · 39 tokens

testing-strategy

Choose the right test type for every change — unit, integration, contract, end-to-end, property-based, mutation, fuzz. Use when adding tests to a new feature, deciding what to test for a bug fix, designing a test pyramid for a service, evaluating coverage targets, or untangling a slow test suite. Stack-agnostic…

kouroshez/coding-os · 118 tokens

end-to-end-testing

Write reliable end-to-end tests that exercise real user journeys — Playwright for web, Maestro for mobile — without the flakiness that makes teams ignore them. Use when adding an end-to-end test, debugging a flaky test, choosing what to cover end-to-end vs unit/integration, setting up CI for browser/device tests, or…

kouroshez/coding-os · 177 tokens

qa

Use when the user asks to run QA without fixing code, including mounted runtime behavior, visible user flows, browser-visible app execution, source-of-truth checks, action/state coverage, route/control inventories, Playwright control sweeps, or QA report generation in repositories.

tamnguyendinh/Anvien · 55 tokens

source-command-swarm-testing

Migrated source command swarm-testing.

ayushcodes10/echo-mem · 15 tokens