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-plan)<a href="https://agentmods.dev/commands/rocky2431/ultra-builder-pro/ultra-plan"><img src="https://agentmods.dev/badge/commands/rocky2431/ultra-builder-pro/ultra-plan/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/commands/rocky2431/ultra-builder-pro/ultra-plan"><img src="https://agentmods.dev/badge/commands/rocky2431/ultra-builder-pro/ultra-plan.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 | $0.00009 | $0.03076 |
| Opus 5.5 | $0.00004 | $0.01230 |
| Sonnet 5.5 | $0.00002 | $0.00615 |
| Haiku 4.5 | $0.00001 | $0.00308 |
Grade A, and why
ultra-plan 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 2mo 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ultra-plan
Workflow Tracking (MANDATORY)
On command start, create tasks for each major step using TaskCreate:
| Step | Subject | activeForm |
|---|---|---|
| 0 | Specification Validation | Validating specs... |
| 1 | Requirements Analysis | Analyzing requirements... |
| 2 | Codebase Analysis | Analyzing codebase... |
| 3 | Task Generation | Generating tasks... |
| 4 | Dependency Analysis | Analyzing dependencies... |
| 5 | Save Tasks | Saving tasks to files... |
| 6 | Generate 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
Purpose
Generate task breakdown from complete specifications (created by /ultra-research).
Step 0: Scope Mode Selection
Use AskUserQuestion to determine planning posture before any analysis:
| Mode | Posture | When to Use |
|---|---|---|
| EXPAND | Challenge scope upward. For each task, ask "what would make this 10x better for 2x effort?" Surface expansion opportunities as individual AskUserQuestion decisions. | New product, greenfield, user wants to think bigger |
| SELECTIVE | Hold current scope as baseline. Surface optional expansions individually — user cherry-picks. Neutral recommendation posture. | Most common. Existing product, feature work. |
| HOLD | Scope is locked. Make it bulletproof — catch every failure mode, test every edge case. Do not add or remove scope. | User has clear requirements, just needs execution plan |
| REDUCE | Find the minimum viable version. Cut everything non-essential. Be ruthless. | Time pressure, MVP, proof of concept |
Default: SELECTIVE (if user doesn't specify)
Commitment rule: Once mode is selected, COMMIT to it. Do not silently drift. EXPAND mode does not argue for less work. REDUCE mode does not sneak scope back in.
Dual-scale effort (show on every expansion decision in EXPAND/SELECTIVE mode):
Complete: ~X LOC, AI ~Y min | Shortcut: ~X LOC, saves Y min but ___
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.
- 2mo ago First seen · 369 lines · 9 tokens per session scan A 2f874c432aef
ultra-plan is a command published in the GitHub repository rocky2431/ultra-builder-pro (11 stars, last pushed 3mo ago), licensed MIT. It adds 9 tokens to every session and 3,076 once invoked, about $0.0000 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 2026-08-30.
ultra-plan compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ultra-planrocky2431/ultra-builder-pro | Command | 11 | 3mo ago | MIT | A | 9 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |