tdd

A test-review guide that uses questions to decide which tests protect real user or business behavior. TDD, or test-driven development, is a practice of designing tests around expected behavior while building software.

In plain words
What is it for?
Use it when planning tests, adding a regression test for a bug, or reviewing an existing test suite to focus coverage on observable behavior rather than internal implementation details.
Why use it?
Test suites can contain tests that merely repeat the code, echo mock data, or add no useful protection. This guide helps identify tests whose absence would allow a meaningful bug into production.

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/tiltely/lens/tdd
Any agent
npx skills add Tiltely/lens --skill tdd
Clone the repo
git clone --depth 1 https://github.com/Tiltely/lens

Made for: Claude Code, Codex.

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,758 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 $0.00086 $0.01758
Opus 5 $0.00043 $0.00879
Sonnet 5 $0.00017 $0.00352
Haiku 4.5 $0.00009 $0.00176

Measured 2d ago against content hash 10a31403845c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tdd 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/tdd/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Lens of TDD

Read first: ${CLAUDE_PLUGIN_ROOT}/core/protocol.md and ${CLAUDE_PLUGIN_ROOT}/core/dossier.md. Dossier rules: read it, skip answered questions WITH skip lines, append your outputs.

Division of labor: if a TDD process skill is available in the session (e.g. superpowers:test-driven-development), it governs the red-green-refactor loop. This lens governs judgment — which tests deserve to exist and what they must pin down. They compose; this lens never overrides process discipline.

Mode selection

  • Explicit argument wins ("audit" / "design").
  • Otherwise infer: planning/writing tests → design; reviewing tests that already exist → audit. Confirm your inference in one line.

Question battery — design mode

Tier 1 — framing (always)

  1. State the behavior under test as one sentence in DOMAIN language — "rejects expired tokens", "splits the bill evenly among present members". If you cannot phrase it without naming functions, mocks, or internals, you are about to test implementation, not behavior. Rephrase before continuing.
  2. The deletion test: if this test never existed, what bug would reach production undetected? If the honest answer is "none", the test is theater — do not write it.

Tier 2 — per proposed test

  1. What is the ONE reason this test can fail? (Many reasons → bad alarm, split it. Zero reasons → decoration, delete it. Exactly one → a test.)
  2. Red-phase honesty: will you SEE it fail first, and fail for the RIGHT reason? A test that passes on first run has verified nothing — including itself.
  3. What does the assertion actually pin? Distinguish:
    • outcome assertions (returned value, persisted state, emitted event) — strong
    • interaction assertions (mock called with X) — weak; justified ONLY when the interaction IS the contract (e.g., "charges Stripe exactly once")
  4. Boundaries, with criterio: list the edges (empty, one, many, duplicate, malformed, concurrent, unauthorized) — then say which you will NOT test and WHY. Knowing what not to test is the skill; "all of them" is not an answer.
  5. Stack-conditional:
    • nestjs-api → what is the unit/e2e split here? What deserves the real database and what tolerates a mock — and does any mock re-implement query logic (red flag)?
    • nextjs-web / expo-mobile → does the test exercise what the USER does (render, interact, observe) rather than component internals/state shape?

Read the full file on GitHub · 131 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 · 131 lines · 86 tokens per session scan A 10a31403845c

Subscribe to this mod's changes

tdd is a skill published in the GitHub repository Tiltely/lens (5 stars, last pushed 23d ago), licensed MIT. It adds 86 tokens to every session and 1,758 once invoked, about $0.0004 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 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

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.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens