What is dev-tdd-loop?

A structured development workflow for delivering a non-trivial feature through brainstorming, planning, implementation, and final checks.

It is for shipping features that take more than a small edit, producing a design brainstorm and implementation plan, carrying out the work, and checking the result before release.

It gives larger changes explicit steps and verification points, reducing the chance of declaring a feature finished when it still fails its acceptance requirements.

dev-tdd-loop — Skill by redhuntlabs

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/redhuntlabs/wizard/dev-tdd-loop

Any agent

npx skills add redhuntlabs/wizard --skill dev-tdd-loop

Clone the repo

git clone --depth 1 https://github.com/redhuntlabs/wizard

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,234 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.

Model	Per session	Once invoked
Fable 5	$0.00029	$0.01234
Opus 5	$0.00015	$0.00617
Sonnet 5	$0.00006	$0.00247
Haiku 4.5	$0.00003	$0.00123

Measured 2d ago against content hash f87b49ddf5b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-tdd-loop 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.

spells/chains/dev-tdd-loop/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev TDD Loop

What this does

The default chain for shipping any non-trivial dev feature. Runs four bundled spells in sequence: brainstorm the approach, write the implementation plan, execute step-by-step with per-step verification, and run a final verification pass before declaring "done." Equivalent in spirit to a TDD-rigorous engineering workflow.

When to use

Shipping a feature beyond a one-line tweak
Onboarding a team to a structured engineering workflow
When "we shipped it but it broke" has happened more than once
When the implementation will span more than a few hours

Do not use when

Trivial fix (typo, copy change, single-line guard)
Pure exploration / spike — use it AFTER the spike, when productionizing
Emergency hotfix where the verification step happens via post-mortem instead

What you bring (Inputs)

A feature request, ticket, or one-line description
Codebase access
A definition of "shipped" (deploy, merge to main, release tag, etc.)

What you get (Output)

A brainstorm document
An implementation plan with per-step verifications
The implemented feature with all step verifications passing
A verification pass against acceptance criteria, completed before shipping

How it works (Steps)

This is a chain of 4 spells. Each stage hands an artifact to the next.

Stages

Stage 1: Brainstorm (brainstorming-a-feature)

Skill: brainstorming-a-feature
Input: feature request
Output handoff: brainstorm doc with sharp problem statement, 3-5 candidate approaches, recommendation, alternative considered, top assumptions
Gate: problem statement passes the "stranger could understand it" test; alternative is plausible

Stage 2: Plan (writing-an-implementation-plan)

Skill: writing-an-implementation-plan
Input: chosen approach from Stage 1
Output handoff: implementation plan with file-level changes, ordering, per-step verifications, risks, acceptance criteria
Gate: every step has explicit verification; another engineer could execute without clarifying questions

Read the full file on GitHub · 123 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.

2d ago First seen · 123 lines · 29 tokens per session scan A f87b49ddf5b3

Subscribe to this mod's changes

dev-tdd-loop is a skill published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 1,234 once invoked, about $0.0001 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.

Data and AI Git and workflow Testing ai-agents ai-skills ai-tools ai-workflow automation claude-code

dev-tdd-loop