Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add 7xuanlu/ultrapowers/plugin install ultrapowersWrote 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.
[](https://agentmods.dev/skills/7xuanlu/ultrapowers/workflows-driven-development)<a href="https://agentmods.dev/skills/7xuanlu/ultrapowers/workflows-driven-development"><img src="https://agentmods.dev/badge/skills/7xuanlu/ultrapowers/workflows-driven-development/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00025 | $0.01129 |
| Opus 5.5 | $0.00010 | $0.00452 |
| Sonnet 5.5 | $0.00005 | $0.00226 |
| Haiku 4.5 | $0.00003 | $0.00113 |
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 1mo 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.
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.
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.
- 1mo ago First seen · 80 lines · 25 tokens per session scan A a37a5ac0680f
workflows-driven-development is a skill published in the GitHub repository 7xuanlu/ultrapowers (10 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 1,129 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 2026-08-31.
Other skills, from other repositories
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
test-driven-development-codex
Enforce strict test-driven development via Codex-backed implementation. Use only when the user explicitly asks for the Codex-backed TDD workflow.
testing-principles
Language-agnostic testing principles for choosing which tests a change needs, test quality, and proof ownership, with frontend and browser E2E implementation references. Use when writing tests, deciding test scope, or reviewing test quality.
linked-intent-dev
Guide for linked-intent development (LID). Consult for ALL code changes. Walks changes through a mode-aware six-phase workflow (HLD → LLD → EARS → intent-narrowing edge audit → tests-first → code) with mandatory stops between each phase. Bugs walk the arrow like any other change — no short-circuit. Enforces cascade…
building
Use when writing production code test-first: the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns.