hyper-tdd

A test-driven development, or TDD, workflow for behavior-changing code. It requires writing a test that fails first, then the smallest code change that makes it pass.

In plain words
What is it for?
Use it before writing functions, business logic, or bug fixes, following a fail, implement, pass, commit, and refactor cycle.
Why use it?
It helps catch incorrect assumptions early and limits production changes to behavior that is covered by a test.

Skill for Claude CodeCodex

Part of the hyperclaude plugin — 19 skills, 6 agents, 2 hooks shipped together

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

Made for: Claude Code, Codex.

Or install hyperclaude, the plugin that ships this one along with the rest of its 19 skills, 6 agents, 2 hooks.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 397 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 $0.00058 $0.00397
Opus 5 $0.00029 $0.00198
Sonnet 5 $0.00012 $0.00079
Haiku 4.5 $0.00006 $0.00040

Measured 2d ago against content hash c653dbdc4692, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hyper-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/hyper-tdd/SKILL.md · 36 lines

What it actually says

hyper-tdd

Test-driven discipline tailored to this author's preferences.

The loop

  1. Write the failing test first. Name the behavior, not the implementation. The test should compile/import but fail because the behavior doesn't exist yet.
  2. Run it. Confirm it fails for the right reason. "Cannot find function" is fine. "ReferenceError because of typo in test" is not — fix the test.
  3. Write the minimum code to make it pass. Resist scope creep. No "while I'm here" edits.
  4. Run it. Confirm it passes.
  5. Commit. One behavior, one commit. Commit messages describe the behavior, not the code.
  6. Refactor if there's a clear smell. Tests must still pass after.

Skip TDD when

  • Touching only documentation, comments, or formatting.
  • Renaming a symbol (an LSP/grep operation, not a behavior change).
  • One-shot migration scripts that run once and get deleted.
  • Config-only changes (e.g., updating a .gitignore).

What "minimum" means here

Implement only what the current test requires. If you need a helper, add the simplest version. Do not pre-build for tests you might write later — write that test first, then the helper.

What good test names look like

  • slugify drops non-ASCII characters
  • cli --dry-run prints JSON without spawning codex
  • test_slugify (says nothing)
  • slugify works correctly (vague)
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 · 36 lines · 58 tokens per session scan A c653dbdc4692

Subscribe to this mod's changes

hyper-tdd is a skill published in the GitHub repository zeikar/hyperclaude (3 stars, last pushed 15d ago), licensed MIT. It adds 58 tokens to every session and 397 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 2026-08-31.