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.
git clone --depth 1 https://github.com/rocky2431/ultra-builder-proWrote 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/commands/rocky2431/ultra-builder-pro/ultra-dev)<a href="https://agentmods.dev/commands/rocky2431/ultra-builder-pro/ultra-dev"><img src="https://agentmods.dev/badge/commands/rocky2431/ultra-builder-pro/ultra-dev.svg" alt="Measured on agentmods" 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 | $0.00008 | $0.04395 |
| Opus 5 | $0.00004 | $0.02197 |
| Sonnet 5 | $0.00002 | $0.00879 |
| Haiku 4.5 | $0.00001 | $0.00439 |
Grade A, and why
ultra-dev 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 7d 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 — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ultra-dev
Workflow Tracking (MANDATORY)
On command start, create tasks for each major step using TaskCreate:
| Step | Subject | activeForm |
|---|---|---|
| 1 | Task Selection | Selecting task... |
| 1.5 | Update Status to In-Progress | Updating task status... |
| 2 | Environment Setup | Setting up environment... |
| 3 | TDD Cycle | Running TDD cycle... |
| 3.1 | TDD: RED Phase | Writing failing tests... |
| 3.2 | TDD: GREEN Phase | Writing minimal code... |
| 3.3 | TDD: REFACTOR Phase | Refactoring code... |
| 4 | Quality Gates | Running quality gates... |
| 4.5 | Ultra Review | Running ultra-review... |
| 5 | Update Status to Completed | Updating task status... |
| 5.5 | Pre-Commit Checklist | Verifying checklist... |
| 6 | Commit and Merge | Committing and merging... |
| 7 | Report | Generating report... |
Before each step: TaskUpdate → status: "in_progress"
After each step: TaskUpdate → status: "completed"
On context recovery: TaskList → resume from last incomplete step
Execute development tasks using TDD workflow.
Arguments
$1: Task ID (if empty, auto-select next pending task)
Workflow
Step 0: Workflow Resume Check (Before Task Selection)
- Check if
.ultra/workflow-state.jsonexists - If yes AND branch matches current branch:
- Display: "Resuming task {id} from Step {step}: {status}"
- Skip to the step AFTER the last completed checkpoint
- If review_session exists, skip re-running review
- If no or branch mismatch: proceed to Step 0.5
Step 0.5: Design Approval Gate (First Run Only)
Trigger: .ultra/workflow-state.json does NOT exist (first run, not resume)
- Check
.ultra/tasks/tasks.jsonexists- If missing → "No task plan found. Run /ultra-plan first to create task decomposition." → EXIT
- If ANY task has status
completedorin_progress→ plan was already approved in a prior run → skip gate, proceed to Step 1
- Read tasks.json, display overview:
- Total tasks, priority distribution (P0/P1/P2), complexity range
- Full task list (ID, title, priority, dependencies)
- Whether Walking Skeleton is Task #1
- Use AskUserQuestion to request confirmation:
- "Confirm this task breakdown to start implementation?"
- Option A: "Confirm, start implementation" → Continue to Step 1
- Option B: "Revise plan first" → Suggest /ultra-plan → EXIT
- On approval, write workflow-state.json:
{"command":"ultra-dev","task_id":0,"branch":"","step":"0.5","status":"design_approved","ts":"ISO8601"}
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.
- 7d ago First seen · 456 lines · 8 tokens per session scan A e56e41a4559d
ultra-dev is a command published in the GitHub repository rocky2431/ultra-builder-pro (11 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 4,395 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
dashboard
Generar dashboard HTML local con métricas de eficiencia del proyecto SDD.
usage-add
PitWay: Accumulate measured planning or qa token usage onto a milestone.
hub-tdd
TDD workflow for MCP Hub implementation. Types → Tests (red) → Implementation (green) with git gates.
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.
tdd
A command that follows test-driven development (TDD), a method where you write tests before the code they check. It moves through writing a failing test, adding the smallest implementation, and then improving the code.