workflows-driven-development

workflows-driven-development is a skill for Claude Code, Codex from 7xuanlu/ultrapowers. It costs 25 tokens per session (1,129 once invoked), scanned A, original, MIT.

A workflow for breaking a software goal into tasks and building each task with tests written first. TDD, or test-driven development, means writing a test before the code that should pass it.

In plain words
What is it for?
It helps plan a goal, implement its tasks one at a time, review the results, rerun tests, and create a separate commit for each task.
Why use it?
It gives coding work a repeatable structure and checks each change through tests and review, reducing the chance of unnoticed mistakes.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the ultrapowers plugin — 1 skill, 1 agent, 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/7xuanlu/ultrapowers/workflows-driven-development
Any agent
npx skills add 7xuanlu/ultrapowers --skill workflows-driven-development
Clone the repo
git clone --depth 1 https://github.com/7xuanlu/ultrapowers

Made for: Claude Code, Codex.

Or install ultrapowers, the plugin that ships this one along with the rest of its 1 skill, 1 agent, 2 hooks.

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 workflows-driven-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/7xuanlu/ultrapowers/workflows-driven-development.svg)](https://agentmods.dev/skills/7xuanlu/ultrapowers/workflows-driven-development)
Your own site
<a href="https://agentmods.dev/skills/7xuanlu/ultrapowers/workflows-driven-development"><img src="https://agentmods.dev/badge/skills/7xuanlu/ultrapowers/workflows-driven-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,129 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 $0.00025 $0.01129
Opus 5 $0.00013 $0.00564
Sonnet 5 $0.00005 $0.00226
Haiku 4.5 $0.00003 $0.00113

Measured 3d ago against content hash a37a5ac0680f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflows-driven-development 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.

skills/workflows-driven-development/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/workflows-driven-development

User-only entry to the ultrapowers harness. Spends real tokens → never auto-invoked. You (the model running this command) own the two human gates and dispatch the deterministic Workflow engine. Do not re-implement the loop, dispatch the engine.

Usage

/workflows-driven-development <goal>                 plan → build the planned tasks → stop
/workflows-driven-development <goal> --thorough      + completeness-critic loop until clean (GOAL MODE ONLY)
/workflows-driven-development --tasks <tasks.json>    advanced: run a pre-decomposed [{id,spec}] list
/workflows-driven-development help                   modes, cost, task-list format

On help

Print the Usage block above, then: "default = one disciplined pass; --thorough adds a completeness critic that loops until no new findings (goal mode only). Built-in always-on: strict TDD, merged opus review (spec + quality, fail-closed), re-witness RED, per-task commit. Task-list format: see ${CLAUDE_PLUGIN_ROOT}/reference/task-list.md. Cost scales with task count, each task runs an implementer plus one merged opus review (plus re-witness RED)." Then stop.

Workspace isolation (do first, before any gate)

If the target repo is on main/master, create a feature worktree/branch first (EnterWorktree or git checkout -b feature/<goal-slug>). The harness commits per task.

GATE 1, plan approval (goal mode)

For a <goal>: dispatch planning only, then present the task list to the human.

Workflow({ scriptPath:'${CLAUDE_PLUGIN_ROOT}/workflow/ultrapowers-development.js', args:{ goal:<goal>, planOnly:true } })

Show the proposed tasks and ask: Approve this plan / edit / abort? Do not build until approved.

A Workflow cannot pause mid-run (ADR-0001), so approval happens before the build dispatch.

For --tasks <file>: validate first. Read the file; if any entry is not a {id,spec} object, reject with: "tasks must be [{id,spec}] objects, bare strings are silently dropped (see ${CLAUDE_PLUGIN_ROOT}/reference/task-list.md)." If --thorough was also passed, warn: "--thorough is ignored in --tasks mode (the completeness critic runs in goal mode only)." Then skip to dispatch.

Read the full file on GitHub · 80 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.

  1. 3d ago First seen · 80 lines · 25 tokens per session scan A a37a5ac0680f

Subscribe to this mod's changes

workflows-driven-development is a skill published in the GitHub repository 7xuanlu/ultrapowers (10 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 1,129 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.