testing-master

testing-master is a skill for Codex from wan-aishengtang/testing-master-skill. It costs 138 tokens per session (1,976 once invoked), scanned A, original, MIT.

A testing workflow that treats one person or process as responsible for the project’s overall test coverage and delivery evidence. It covers planning, manual checks, API tests, web-interface automation, performance tests, and acceptance testing.

In plain words
What is it for?
Use it to analyse requirements, design test strategies, plan manual and automated checks, test APIs and web interfaces, assess performance, write defect reports, and prepare acceptance results.
Why use it?
It helps turn vague testing requests into defined scope, test cases, evidence, risks, defects, and next actions. It also avoids claiming bugs that have not been reproduced or supported by evidence.

Skill for Codex

Written for Codex: agents/openai.yaml present.

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

Made for: 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 testing-master

README.md
[![agentmods](https://agentmods.dev/badge/skills/wan-aishengtang/testing-master-skill/testing-master.svg)](https://agentmods.dev/skills/wan-aishengtang/testing-master-skill/testing-master)
Your own site
<a href="https://agentmods.dev/skills/wan-aishengtang/testing-master-skill/testing-master"><img src="https://agentmods.dev/badge/skills/wan-aishengtang/testing-master-skill/testing-master.svg" alt="Measured on agentmods" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,976 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 $0.00138 $0.01976
Opus 5 $0.00069 $0.00988
Sonnet 5 $0.00028 $0.00395
Haiku 4.5 $0.00014 $0.00198

Measured 6d ago against content hash 4ee4e8728a00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

testing-master 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 6d 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.

testing-master/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Testing-Master

Core Posture

Act like a test owner for a software project. Start from scope, evidence, and delivery target.

Default style:

  • Use Chinese unless the user asks otherwise.
  • Keep output concise, structured, and delivery-oriented.
  • Lead with conclusion, risk, and next action.
  • Speak like a testing owner, not like a technical article summarizer.
  • Prefer tables for test points, cases, defects, coverage, and reports.
  • Preserve black-box wording for manual test cases: describe visible behavior and business result, not backend implementation.
  • Do not invent unverifiable defects. Reproduce, cite evidence, or mark them as risks.
  • Do not add default "参考资料/参考文档/技术文章" sections in testing outputs.
  • If basis must be stated, write it as testing evidence or decision basis, and only mention directly relevant project assets, logs, reports, or execution results.

First Checks

Before designing or executing testing work:

  1. Confirm test objective, version boundary, and excluded scope.
  2. Identify available assets: requirements, prototype, API docs, environment URL, accounts, source code, logs, existing cases, defect reports, automation, performance scripts, and reports.
  3. Check whether the task depends on related skills such as prompt-optimizer, docx, xlsx, spreadsheets, webapp-testing, find-skills, or skill-installer.
  4. If a needed related skill is missing, recommend the relevant skill to the user before execution and support the user in downloading and installing it.
  5. If context is incomplete, first ask for or infer the missing test direction, change scope, environment, account permissions, API details, and data prerequisites.
  6. If a local project has custom testing assets or historical testing memory, read references/project-adaptation.md and adapt it into a project-specific local extension before deep execution.

Initial Framework First

When the user says they are preparing to test, asks for a testing plan, asks how to start testing, or wants a testing project from scratch, first provide a complete testing framework before writing detailed documents.

Read the full file on GitHub · 159 lines

Files

What ships with it

4 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. 6d ago First seen · 159 lines · 138 tokens per session scan A 4ee4e8728a00

Subscribe to this mod's changes

testing-master is a skill published in the GitHub repository wan-aishengtang/testing-master-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 138 tokens to every session and 1,976 once invoked, about $0.0007 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

testing

Testing workflow and quality standards for writing and running tests. Use when: (1) Writing new tests, (2) Adding a new feature that needs tests, (3) Modifying logic that has existing tests, (4) Before claiming a task is complete.

iOfficeAI/AionUi · 55 tokens

testing-patterns

Testing patterns and principles. Unit, integration, mocking strategies.

vudovn/ag-kit · 16 tokens

testing

Writing or debugging tests, choosing unit vs integration style, Postgres/ClickHouse tests, regenerating ClickHouse test schema, or exporting test helpers from packages without pulling test code into production bundles.

latitude-dev/latitude-llm · 41 tokens

detect-flaky-tests

Detects flaky Go tests by analyzing GitHub Actions workflow runs across the last 7 days and all PRs — covering both the run-tests job (unit/integration) and the e2e-test job (gVisor and microVM lanes). For each newly-detected flaky test or infra issue, opens a GitHub issue with full evidence and a draft fix PR. Does…

agent-substrate/substrate · 102 tokens

test-pyramid

Analyze the repo's unit and E2E tests and propose rebalancing toward a test pyramid — which E2E tests (or assertions inside them) can be covered by unit tests, which unit-level gaps genuinely need E2E coverage, and where coverage is duplicated. Use when the user asks about test pyramid, test rebalancing, "should this…

kubernetes-sigs/agent-sandbox · 104 tokens

designing-tests

Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.

CloudAI-X/claude-workflow-v2 · 48 tokens