xdd

xdd is a skill for Claude Code, Codex from stagentic/stagentic-xdd. It costs 20 tokens per session (368 once invoked), scanned A, original, MIT.

A test-driven development (TDD) rule set for adding or changing code. It requires a failing test before production or test code is changed.

In plain words
What is it for?
Use it before any TDD task to write the failing test, implement only enough code to pass it, and then refactor when appropriate.
Why use it?
It gives each code change a specific expected outcome and helps reveal whether the test fails for the intended reason. This reduces reliance on unverified implementation choices.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before any TDD task to write the failing test, implement only enough code to pass it, and then refactor when appropriate.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stagentic/stagentic-xdd/stage-02-subsections-examples
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.

Any agent
npx skills add stagentic/stagentic-xdd --skill stage-02-subsections-examples
Clone the repo
git clone --depth 1 https://github.com/stagentic/stagentic-xdd

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for xdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/stagentic/stagentic-xdd/stage-02-subsections-examples/github.svg)](https://agentmods.dev/skills/stagentic/stagentic-xdd/stage-02-subsections-examples)
Your own site
<a href="https://agentmods.dev/skills/stagentic/stagentic-xdd/stage-02-subsections-examples"><img src="https://agentmods.dev/badge/skills/stagentic/stagentic-xdd/stage-02-subsections-examples/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.

agentmods 80×15 button for xdd

Your own site · 80×15
<a href="https://agentmods.dev/skills/stagentic/stagentic-xdd/stage-02-subsections-examples"><img src="https://agentmods.dev/badge/skills/stagentic/stagentic-xdd/stage-02-subsections-examples.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 368 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00020 $0.00368
Opus 5.5 $0.00008 $0.00147
Sonnet 5.5 $0.00004 $0.00074
Haiku 4.5 $0.00002 $0.00037

Measured 4d ago against content hash 3ab4aaedab20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-30, from the pricing page.

Security

Grade A, and why

xdd 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 4d 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.

docs/architecture/decisions/0020-drive-skill-invocation-from-the-frontmatter-description/superseded-wordings/stage-02-subsections-examples-SKILL.md · 46 lines

What it actually says

Apply the disciplines of TDD for adding or changing code overriding your understanding with the following principles:

Always write the test first

The test should always be written before the production code that makes it pass.

Failing for the right reason

A test fails for the right reason when it has an assertion failure where the actual result is not matching the expected result.

Making a test pass

Make a failing test pass using 'Fake-It' with 'Triangulation'; do not use 'Obvious Implementation'.

Fake-It

Fake-It makes a test pass by making the smallest possible change to the code that will pass the test, no matter how naive — and without breaking other tests. Use Fake-It as the default way to make a failing test pass.

For example, to pass a first test is_even(2) == True, return the literal True.

Triangulation

Triangulation is the process of each new test forcing an ever less naive implementation until the real implementation satisfies the desired capability.

For example, adding is_even(3) == False — which the return True fake-it implementation cannot pass — forces the naive code towards the real return n % 2 == 0.

Obvious Implementation

Do not use Obvious Implementation. You can recognise it when you skip Fake-It and write the general implementation directly. Instead, use Fake-It, then Triangulation, to reach the real implementation.

For example, if you have a test asserting only is_even(2) == True then writing return n % 2 == 0 is applying the Obvious Implementation strategy.

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. 4d ago First seen · 46 lines · 20 tokens per session scan A 3ab4aaedab20

Subscribe to this mod's changes

xdd is a skill published in the GitHub repository stagentic/stagentic-xdd (5 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 368 once invoked, about $0.0001 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 2026-09-26.