test-gen

test-gen is a command for Claude Code from kid-sid/claude-spellbook. It costs 0 tokens per session (463 once invoked), scanned A, original, MIT.

A command that creates unit and integration tests for a specified file or function. Unit tests check one piece of code, while integration tests check how it works with dependencies such as databases, networks, or files.

In plain words
What is it for?
Run it to generate tests for Python, TypeScript, Go, or Rust code using the test framework already present in the project.
Why use it?
It turns the code's inputs, outputs, side effects, and error cases into repeatable checks, including edge cases that are easy to overlook.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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 commands/kid-sid/claude-spellbook/test-gen
Clone the repo
git clone --depth 1 https://github.com/kid-sid/claude-spellbook

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 test-gen

README.md
[![agentmods](https://agentmods.dev/badge/commands/kid-sid/claude-spellbook/test-gen.svg)](https://agentmods.dev/commands/kid-sid/claude-spellbook/test-gen)
Your own site
<a href="https://agentmods.dev/commands/kid-sid/claude-spellbook/test-gen"><img src="https://agentmods.dev/badge/commands/kid-sid/claude-spellbook/test-gen.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 463 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 $0.00000 $0.00463
Opus 5 $0.00000 $0.00231
Sonnet 5 $0.00000 $0.00093
Haiku 4.5 $0.00000 $0.00046

Measured 6d ago against content hash b4994f8dd911, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

test-gen 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.

.claude/commands/test-gen.md · 39 lines

What it actually says

Generate unit and integration tests for a given file or function.

Instructions

  1. Read the target file the user specifies (or the most recently edited file if none given).

  2. Identify the language and detect the existing test framework:

    • Python: pytest (check for conftest.py, pytest.ini, pyproject.toml)
    • TypeScript: Jest or Vitest (check package.json for jest or vitest)
    • Go: stdlib testing package
    • Rust: stdlib #[cfg(test)] module
  3. Identify all public functions/methods and their behavior:

    • What inputs do they accept?
    • What outputs do they produce?
    • What side effects do they have (DB, HTTP, file I/O)?
    • What error conditions exist?
  4. Generate tests following the unit-testing skill patterns:

    • AAA pattern (Arrange / Act / Assert)
    • Naming: test_<unit>_<scenario>_<expected> (Python), describe/it (TS), TestXxx (Go)
    • Edge cases: null/None/nil, empty collections, boundary values
    • Error paths: invalid input, missing dependencies, timeout
    • Parameterized tests where multiple input/output pairs test the same logic
  5. For functions with external dependencies (DB, HTTP, filesystem):

    • Generate integration test stubs using Testcontainers or test clients
    • Mock external I/O with appropriate library (unittest.mock, jest.fn(), interface-based in Go)
  6. Place the test file in the correct location:

    • Python: tests/test_<module>.py
    • TypeScript: <module>.test.ts (co-located) or __tests__/<module>.test.ts
    • Go: <module>_test.go (same package)
    • Rust: #[cfg(test)] mod tests at bottom of same file, or tests/ for integration
  7. Run the tests to verify they pass. Fix any failures.

Output

  • The generated test file
  • A summary of what was tested and what was deliberately excluded (with reasoning)
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 · 39 lines · 0 tokens per session scan A b4994f8dd911

Subscribe to this mod's changes

test-gen is a command published in the GitHub repository kid-sid/claude-spellbook (188 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 463 tokens. 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.