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 | $0.00005 | $0.01538 |
| Sonnet 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 11d 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.
- 11d 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 1mo ago), licensed MIT. It adds 9 tokens to every session and 3,076 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.