tdd

A test-first development workflow that writes a small test for one observable behavior, makes it pass, then improves the code. TDD means test-driven development.

In plain words
What is it for?
Use it to build or fix features test-first, follow red-green-refactor cycles, and add integration tests where appropriate.
Why use it?
It provides quick feedback about whether a change works and helps keep tests focused on expected behavior instead of internal code details.

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

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 348 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 $0.00039 $0.00348
Opus 5 $0.00019 $0.00174
Sonnet 5 $0.00008 $0.00070
Haiku 4.5 $0.00004 $0.00035

Measured 3d ago against content hash 2d2418a666ff, 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 3d 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.

.agents/skills/tdd/SKILL.md · 39 lines

What it actually says

Test-Driven Development

Use small red → green → refactor cycles when a test-first feedback loop is practical. Treat repository conventions, existing tests, and the requested behavior as authoritative.

Loop

  1. Identify one observable behavior and the seam through which callers see it.
  2. Write the smallest meaningful test and confirm that it fails for the expected reason.
  3. Add only enough implementation to make the test pass.
  4. Refactor when doing so improves clarity or design; keep the suite green.
  5. Repeat with the next vertical slice.

Infer seams from public interfaces and nearby tests. Ask the user only when choosing a seam would materially change the product contract, cost, or scope.

Judgment

  • Prefer behavior-focused tests that survive internal refactors.
  • Derive expected results from a specification, worked example, or other independent source rather than duplicating the implementation.
  • Mock external or nondeterministic boundaries when useful; follow established repository patterns where they provide an adequate feedback loop.
  • Prefer vertical slices over a speculative batch of tests. Batch closely related mechanical cases when that is clearer and faster.
  • If a failing-first cycle is impractical—for example in legacy code with no usable seam—state the limitation and establish the nearest reliable characterization or integration test.

Read tests.md for examples and mocking.md when deciding whether and where to use test doubles.

Files

What ships with it

3 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.

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. 3d ago First seen · 39 lines · 39 tokens per session scan A 2d2418a666ff

Subscribe to this mod's changes

tdd is a skill published in the GitHub repository stevesolun/ctx (581 stars, last pushed 10d ago), licensed MIT. It adds 39 tokens to every session and 348 once invoked, about $0.0002 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.