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 agentmods add skills/google-labs-code/design.md/tddnpx skills add google-labs-code/design.md --skill tddgit clone --depth 1 https://github.com/google-labs-code/design.mdWhat 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 | $0.00053 | $0.00753 |
| Opus 5 | $0.00026 | $0.00377 |
| Sonnet 5 | $0.00011 | $0.00151 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
tdd-red-green-refactor 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red-Green-Refactor (TDD) Skill: TypeScript Edition
This skill implements a structural framework for AI-assisted programming to ensure every line of code is verifiable, typed, and purposeful.
The Three-Phase Cycle
Phase 1: Red (Establish Failure)
You must prove the feature does not exist and that your test is valid.
- Write One Test: Create a single test case (e.g., in Vitest or Jest) for the next small piece of behavior.
- Execute & Fail: Run the test. It must fail.
- Verify: Ensure the failure is related to the missing logic (e.g.,
ReferenceError: add is not defined) and not a configuration error.
Phase 2: Green (Minimal Pass)
Make the test pass as quickly and simply as possible.
- Minimal Implementation: Write the simplest code that satisfies the test. Do not build for the future; focus strictly on the current "Red" test.
- Run Tests: Execute the suite. All tests must be Green.
- Evidence: The transition from Red to Green is the "Proof of Work" for the developer.
Phase 3: Refactor (Clean Up)
Improve the code structure while maintaining the "Green" state.
- Clean Up: Improve naming, remove duplication, and optimize the code written in Phase 2.
- Safety Net: Rerun the tests after every change. If they turn Red, revert the change immediately.
Core Operational Rules
1. No "Horizontal Splurging"
You are strictly forbidden from writing a large "splurge" of multiple tests at once. You must follow a strictly incremental loop:
- Write 1 Test -> See it Fail -> Write 1 Fix -> See it Pass.
- Repeat this loop for every sub-feature.
2. Impose Backpressure
Use automated assertions and strong typing (TypeScript) as backpressure to prevent the AI from "guessing" the solution or "playing in the mud" with low-quality code.
3. Verification of Integrity
Never modify an existing test to make a failing implementation pass. If a test must change, it must be because the requirement changed, not because the code is difficult to write.
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.
- 2d ago First seen · 82 lines · 53 tokens per session scan A 8df7a9e382da
tdd-red-green-refactor is a skill published in the GitHub repository google-labs-code/design.md (27,650 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 753 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.