make-test-plan

A tool that creates a plan for end-to-end tests from a product requirements document and an implementation plan. End-to-end tests check a feature through its full user-facing flow.

In plain words
What is it for?
Use it to create test file skeletons, mark each test for automated, agent, or human verification, and record the planned coverage.
Why use it?
It turns written requirements into an organized testing checklist without pretending the tests are already implemented.

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/context4ai/workflow/make-test-plan
Any agent
npx skills add context4ai/workflow --skill make-test-plan
Clone the repo
git clone --depth 1 https://github.com/context4ai/workflow

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,135 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 $0.00049 $0.02135
Opus 5 $0.00024 $0.01068
Sonnet 5 $0.00010 $0.00427
Haiku 4.5 $0.00005 $0.00214

Measured 2d ago against content hash ddee7b6e65ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

make-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 2d 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.

skills/make-test-plan/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Make Test Plan

Generates E2E test skeleton files from a PRD (Product Requirements Document) and Plan. Creates a version test index (README.md) and bone-skeleton test files using test.todo(...) placeholders, categorized by verification type.


Agent Responsibility Boundaries

The agent's role when running /make-test-plan is strictly limited to:

  1. Generate test skeleton files with test.todo(...) placeholders
  2. Create a version test index (README.md) documenting all planned tests
  3. Categorize each test by verification type (AUTO / AGENT / HUMAN)
  4. Update the Plan file with E2E coverage references

The agent MUST NOT:

  • Implement test assertions or actual test logic — only test.todo(...) placeholders
  • Modify feature source code
  • Run or execute any tests
  • Make decisions about feature implementation

Three Verification Types

Tests are categorized by how they can be verified. The guiding principle is to minimize HUMAN tests — prefer AUTO whenever possible, fall back to AGENT, and only use HUMAN as a last resort.

Type Symbol Meaning Who Verifies
AUTO [A] Fully automatable with deterministic assertions CI / /verify
AGENT [G] Requires agent judgment (visual diff, semantic check, heuristic) AI agent during /verify
HUMAN [H] Requires human interaction, subjective evaluation, or physical device Human tester

Preference Order: AUTO > AGENT > HUMAN

When deciding the verification type for a test:

  1. Can the assertion be expressed as a deterministic code check? (string match, status code, DOM state, data comparison) → AUTO
  2. Can an AI agent evaluate it with sufficient confidence? (visual layout, semantic content quality, heuristic rules) → AGENT
  3. Does it require physical interaction, subjective judgment, or real-world side effects? (UX feel, hardware behavior, payment flow) → HUMAN

E2E Implementation Ownership

Read the full file on GitHub · 274 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. 2d ago First seen · 274 lines · 49 tokens per session scan A ddee7b6e65ff

Subscribe to this mod's changes

make-test-plan is a skill published in the GitHub repository context4ai/workflow (4 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 2,135 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens