A test-driven development process for implementing one observable behavior at a time. TDD means writing a failing test first, adding the smallest code that passes it, and then refactoring safely.

Use it for ready-to-build feature tasks: read the feature plan, write a unit or integration test, make it pass, run the relevant test suites, and mark progress through the defined lifecycle.

It keeps feature work tied to stated requirements and catches regressions as each behavior is added. It also distinguishes implementation work from planning and diagnosis.

tdd — Skill for Claude Code and Codex by woliveiras

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 woliveiras/geremmyas --skill tdd

Clone the repo

git clone --depth 1 https://github.com/woliveiras/geremmyas

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/woliveiras/geremmyas/tdd/github.svg)](https://agentmods.dev/skills/woliveiras/geremmyas/tdd)

Your own site

<a href="https://agentmods.dev/skills/woliveiras/geremmyas/tdd"><img src="https://agentmods.dev/badge/skills/woliveiras/geremmyas/tdd/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/woliveiras/geremmyas/tdd"><img src="https://agentmods.dev/badge/skills/woliveiras/geremmyas/tdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 680 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.00680
Opus 5	$0.00020	$0.00340
Sonnet 5	$0.00008	$0.00136
Haiku 4.5	$0.00004	$0.00068

Measured 10d ago against content hash 80a7690644ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

content/skills/tdd/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD

Use one behavior as the unit of progress. Run when the feature is Ready: its spec, plan, tasks, acceptance criteria, and test strategy pass the repository's machine-readable readiness checks. Human approval is not a feature gate.

Process

Read spec.md, plan.md, and tasks.md in the feature folder.
Pick the next task with - [ ] or continue - [~] in progress. Mark the task - [~] when starting and - [x] when done.
Read the task's test-type (unit, integration, or both) and the spec's Test Strategy. If missing, decide using the same rules as test generation reference.
Write one test that verifies observable behavior through the appropriate boundary (unit: public API of a module; integration: cross-module or I/O).
Run the test and confirm it fails for the expected reason.
Implement the minimum production code to pass that test.
Run the focused test and the nearest relevant suite.
Repeat for the next behavior or task.
Refactor only when tests are green; rerun tests after each refactor.
Use the lifecycle Draft -> Ready -> In Progress -> Verified. Set In Progress when implementation begins.
Before Verified or any handoff, mark every finished task [x], clear stale [~], reconcile required docs and plan items, and obtain independent review with no actionable finding.
Set Verified in spec.md and update specs/README.md only when every acceptance criterion has fresh evidence and step 11 is complete. Merge, commit, push, and deployment are separate authority dimensions and do not change feature lifecycle state.

Rules

Do not write all tests first and then all implementation.
Do not test private functions, call order, or internal collaborators.
Mock only system boundaries (network, time, filesystem, external services).
If a test appears wrong, revisit the spec before changing the test.
When the user only wants tests from acceptance criteria without implementation, follow test generation.
When progress becomes circular or scope changes materially, follow abort criteria.
Escalate to the user only for unresolved material product ambiguity, or when blast radius is high and at least one evidence gap remains: rollback is unproven, or critical harness evidence is missing. Otherwise document the decision, use specialist review when useful, and continue through the executable gates.
Update tasks.md checkboxes as each task starts ([~]) and finishes ([x]). Stale checkboxes block reliable resumption from specs/README.md and the feature folder.

Read the full file on GitHub · 56 lines

Files

What ships with it

2 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.

10d ago First seen · 56 lines · 40 tokens per session scan A 80a7690644ac

Subscribe to this mod's changes

tdd is a skill published in the GitHub repository woliveiras/geremmyas (10 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 680 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 2026-08-31.

TDD Testing

tdd

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

TDD

Process

Rules

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

engram-testing-coverage

iterative-development

python

nw-fp-clojure

strict-tdd

mobiai-mobile-tdd