What is write-test-plan?

A guide for writing QA and user-acceptance test plans from product requirements and task definitions. QA checks whether software works as intended, while user acceptance checks whether it meets agreed needs.

Use it to map acceptance criteria to test scenarios and cover complete feature workflows. It requires product specifications and task definitions.

It prevents important requirements and user flows from being missed during integration, acceptance, and exploratory testing.

write-test-plan — Skill for Claude Code and Codex by andresharpe

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.

Any agent

npx skills add andresharpe/dotbot --skill write-test-plan

Clone the repo

git clone --depth 1 https://github.com/andresharpe/dotbot

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andresharpe/dotbot/write-test-plan/github.svg)](https://agentmods.dev/skills/andresharpe/dotbot/write-test-plan)

Your own site

<a href="https://agentmods.dev/skills/andresharpe/dotbot/write-test-plan"><img src="https://agentmods.dev/badge/skills/andresharpe/dotbot/write-test-plan/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andresharpe/dotbot/write-test-plan"><img src="https://agentmods.dev/badge/skills/andresharpe/dotbot/write-test-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,562 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00043	$0.01562
Opus 5.5	$0.00017	$0.00625
Sonnet 5.5	$0.00009	$0.00312
Haiku 4.5	$0.00004	$0.00156

Measured 1mo ago against content hash 77037497f423, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-test-plan 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 1mo 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.

content/skills/write-test-plan/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Test Plan

Guide for producing a QA/UAT test plan that maps every acceptance criterion and feature scope item to verifiable test scenarios at the integration, acceptance, and exploratory levels.

Prerequisites

Both of these must exist before writing a test plan:

Product specifications — at least one of: mission.md, entity-model.md, PRD, change request, or interview summary
Task definitions — task list with acceptance criteria (via task_list + task_get MCP calls, or task-groups.json)

If either is missing, stop and surface the gap to the operator. A test plan written without full scope is incomplete by definition.

Inputs to Collect

.bot/workspace/product/mission.md              # core goals and principles
.bot/workspace/product/entity-model.md         # data model and relationships
.bot/workspace/product/tech-stack.md           # runtime, frameworks, E2E tooling
.bot/workspace/product/task-groups.json        # group-level scope and acceptance criteria
.bot/workspace/product/prd.md                  # if present
.bot/workspace/product/change-request-*.md     # if present (for change-scoped plans)
task_list (MCP)                                # all tasks with names, categories, criteria

Read every relevant file first, then call task_list to pull the live task queue. Do not write the plan until all inputs are loaded.

Test Plan Structure

Output file: .bot/workspace/product/test-plan.md

Required Sections

1. Overview

What this plan covers (product / feature / change request)
Date and version
Target audience: QA engineers, product owners, UAT participants
Test approach summary

2. Scope

In scope: features, workflows, integrations, and user-facing behaviours covered
Out of scope: unit/component-level testing (covered by write-unit-tests), explicitly excluded areas
Derive both lists directly from mission.md and task group scopes — nothing implied

3. Test Strategy

Level	What is tested	Tooling	Who
Integration	Multi-component flows, API contracts, DB state	(from tech-stack.md)	QA
E2E / Acceptance	Full user journeys from UI to persistence	(from tech-stack.md)	QA
UAT	Business scenarios validated against real requirements	Manual	Product owner / stakeholders
Exploratory	Edge cases, UX, error recovery, accessibility	Manual	QA

Read the full file on GitHub · 161 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.

1mo ago First seen · 161 lines · 43 tokens per session scan A 77037497f423

Subscribe to this mod's changes

write-test-plan is a skill published in the GitHub repository andresharpe/dotbot (52 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,562 once invoked, about $0.0002 per session on Opus 5.5. 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.

E2E testing Testing ai-assisted-development ai-coding claude developer-tools gemini mcp-server

e2e-testing

Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…

QwenLM/qwen-code · 94 tokens

agent-reproduce-align

Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough.

QwenLM/qwen-code · 62 tokens

write-test-plan