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 robisson/build-like-amazon-agent-skills --skill test-driven-developmentgit clone --depth 1 https://github.com/robisson/build-like-amazon-agent-skillsWrote 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/robisson/build-like-amazon-agent-skills/test-driven-development)<a href="https://agentmods.dev/skills/robisson/build-like-amazon-agent-skills/test-driven-development"><img src="https://agentmods.dev/badge/skills/robisson/build-like-amazon-agent-skills/test-driven-development/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.
<a href="https://agentmods.dev/skills/robisson/build-like-amazon-agent-skills/test-driven-development"><img src="https://agentmods.dev/badge/skills/robisson/build-like-amazon-agent-skills/test-driven-development.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00050 | $0.02864 |
| Opus 5.5 | $0.00020 | $0.01146 |
| Sonnet 5.5 | $0.00010 | $0.00573 |
| Haiku 4.5 | $0.00005 | $0.00286 |
Grade A, and why
test-driven-development 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 27d 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-Driven Development
Overview
Test-Driven Development (TDD) at Amazon means writing the test before the implementation—always. The Red-Green-Refactor cycle is not a suggestion; it is the mechanism that ensures code correctness, enables fearless refactoring, and keeps deployment pipelines green.
Amazon's test philosophy follows the test pyramid: a broad base of fast unit tests (80%), a middle layer of integration tests (15%), and a thin cap of end-to-end tests (5%). This ratio exists because unit tests are fast, deterministic, and cheap to maintain. Integration tests verify contracts between components. End-to-end tests validate customer-visible behavior but are slow and brittle.
Beyond pre-deployment testing, Amazon runs canary tests in production—synthetic requests that continuously verify real system behavior. When canaries fail, alarms fire before customers notice.
When to Use
- Before writing any production code (the "Red" step comes first)
- When fixing a bug (write the failing test that reproduces it first)
- When refactoring existing code (ensure tests exist before changing behavior)
- During code review (verify test coverage for every behavior change)
- When setting up deployment pipelines (configure coverage gates)
- When onboarding a new service (establish canary tests immediately)
Amazon Context
At Amazon, untested code does not ship. Pipelines enforce minimum coverage thresholds (typically 80% line coverage, 90% branch coverage for critical paths). Code review explicitly evaluates test quality—a change without tests is rejected regardless of how correct the implementation appears.
The CI/CD toolchain (build system, deployment pipelines, code analysis) integrates testing at every stage: pre-commit hooks run unit tests locally, CI runs the full suite, and post-deployment canaries verify production health. Teams own their test infrastructure the same way they own their production infrastructure.
Amazon's testing culture learned from expensive failures: services that shipped with "we'll add tests later" invariably accumulated tech debt that made changes risky, deployments scary, and on-call rotations miserable. TDD inverts this—tests are the first thing you build, not the last.
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.
- 27d ago Changed · +2 lines · -1 tokens per session 1fa8147c7434
- 1mo ago First seen · 265 lines · 51 tokens per session scan A 3f70131ecc59
test-driven-development is a skill published in the GitHub repository robisson/build-like-amazon-agent-skills (16 stars, last pushed 22d ago), licensed MIT. It adds 50 tokens to every session and 2,864 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.
Other skills, from other repositories
testing-setup
Analyze and create a testing strategy for Android apps - install testing libraries, set up test infrastructure, create harnesses for unit tests, UI tests, screenshot tests, and end-to-end tests.
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
verify
Verification loop — lint -> typecheck -> unit -> integration -> e2e.
check-coverage
Comprehensive assessment of Unit / Integration / E2E three-layer test coverage, identify gaps and provide actionable recommendations.
loom-test-strategy
Test strategy guidance covering pyramid design, coverage, test categorization, flaky tests, infrastructure, and risk-based prioritization.
loom-testing
Test implementation across unit, integration, e2e, security, infrastructure, data pipeline, and ML domains.