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.
npx skills add takaoumehara/superforge-skill --skill superforge-testgit clone --depth 1 https://github.com/takaoumehara/superforge-skillWrote 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.
[](https://agentmods.dev/skills/takaoumehara/superforge-skill/superforge-test)<a href="https://agentmods.dev/skills/takaoumehara/superforge-skill/superforge-test"><img src="https://agentmods.dev/badge/skills/takaoumehara/superforge-skill/superforge-test.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00207 | $0.01108 |
| Opus 5 | $0.00103 | $0.00554 |
| Sonnet 5 | $0.00041 | $0.00222 |
| Haiku 4.5 | $0.00021 | $0.00111 |
Grade A, and why
superforge-test 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superforge Test — Multi-Platform Test-Driven Development Engine
Use this skill when implementing new features or refactoring existing code across Web, iOS, and Android. Code written without tests or written before tests violates this workflow.
0. Decide what to test before writing any of it
The cycle below tells you how to write a test. It does not tell you what to point it at, and that is the decision that makes a suite an asset or a tax. Both failure modes are common: testing everything produces a suite so slow and brittle that people stop running it; testing nothing produces a codebase nobody dares change.
The criterion is one line: a test earns its keep when it would catch a failure a human would not notice immediately. Business rules, money, dates, timezones, units, boundary conditions, and every bug already fixed — yes. Framework behaviour, pass-throughs, private internals, exact pixels — no.
The full decision table, the granularity rule (never write at E2E what a unit
test can prove), the mocking boundary, the brittle-test symptom index, why
coverage percentage is the wrong target, and the order for retrofitting tests to
untested code → references/what-to-test.md.
The Red-Green-Refactor Cycle
- RED: Write a focused failing test targeting the exact contract.
- VERIFY RED: Run the test runner immediately and confirm clean failure for the expected reason.
- GREEN: Write the minimal production code to satisfy the test.
- VERIFY GREEN: Re-run the test and confirm clean passing output.
- REFACTOR: Polish code for readability, dynamic layout, and performance without breaking tests.
Test Runners by Platform
- Web (JS/TS):
npm test -- path/to/spec.test.ts(Jest / Vitest / Playwright). - iOS Native:
xcodebuild test -scheme <Scheme> -destination 'platform=iOS Simulator,name=iPhone 16'orswift test. - Android Native:
./gradlew test(Unit tests) or./gradlew connectedCheck(Espresso/Compose UI tests).
What ships with it
6 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.
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.
- 7d ago First seen · 97 lines · 207 tokens per session scan A 305aa680a3fd
superforge-test is a skill published in the GitHub repository takaoumehara/superforge-skill (1 stars, last pushed 22d ago), licensed MIT. It adds 207 tokens to every session and 1,108 once invoked, about $0.0010 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.
Other skills, from other repositories
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
bats-testing-patterns
Master Bash Automated Testing System (Bats) for comprehensive shell script testing. Use when writing tests for shell scripts, CI/CD pipelines, or requiring test-driven development of shell utilities.
django-tdd
Django testing strategies with pytest-django, TDD methodology, factoryboy, mocking, coverage, and testing Django REST Framework APIs.
python-testing
Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.
perl-testing
Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.
cpp-testing
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.