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-think)<a href="https://agentmods.dev/commands/rocky2431/ultra-builder-pro/ultra-think"><img src="https://agentmods.dev/badge/commands/rocky2431/ultra-builder-pro/ultra-think/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-think"><img src="https://agentmods.dev/badge/commands/rocky2431/ultra-builder-pro/ultra-think.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 | $0.00012 | $0.00909 |
| Opus 5 | $0.00006 | $0.00454 |
| Sonnet 5 | $0.00002 | $0.00182 |
| Haiku 4.5 | $0.00001 | $0.00091 |
Grade A, and why
ultra-think 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 10d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ultra-think
Workflow Tracking (MANDATORY)
On command start, create tasks for each major step using TaskCreate:
| Step | Subject | activeForm |
|---|---|---|
| 1 | Scope Check | Clarifying problem... |
| 2 | Evidence Gathering | Gathering evidence... |
| 3 | Multi-Perspective Analysis | Analyzing perspectives... |
| 4 | Adversarial Stress-Testing | Stress-testing reasoning... |
| 5 | Synthesis | Synthesizing recommendation... |
Before each step: TaskUpdate → status: "in_progress"
After each step: TaskUpdate → status: "completed"
On context recovery: TaskList → resume from last incomplete step
Respond in Chinese per CLAUDE.md. Deep analysis for complex problems and decisions.
Problem
Analysis Protocol
Step 1: Scope Check
If the problem is ambiguous or underspecified, ask up to 3 clarifying questions via AskUserQuestion before proceeding. If the problem is simple enough for a direct answer, skip the full framework and respond concisely — mark all remaining tasks as completed with note "skipped: simple answer path".
Step 2: Evidence Gathering
For any factual claim about technology, APIs, or best practices, verify via Context7/Exa MCP before asserting. Label each assertion:
- Fact: Verified from official source
- Inference: Deduced from facts
- Speculation: Needs verification (list verification steps)
Step 3: Multi-Perspective Analysis
Generate at least 3 distinct approaches. For each, analyze through whichever lenses are relevant:
- Technical: Feasibility, scalability, security, maintainability
- Business: Value, cost, time-to-market, competitive advantage
- User: Needs, experience, edge cases, accessibility
- System: Integration, dependencies, emergent behaviors
Step 4: Adversarial Stress-Testing
Apply these techniques to pressure-test your reasoning:
- Steel Man: Before recommending, build the strongest possible case FOR the option you're inclined to reject
- Pre-Mortem: Assume the recommended option has failed in 6 months. List the 3 most likely causes
- Sensitivity: Identify which assumption, if wrong, would reverse your recommendation
- Second-Order: What new problems does the recommended option create 6-12 months out?
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.
- 10d ago First seen · 102 lines · 12 tokens per session scan A da16b2ed8f86
ultra-think is a command published in the GitHub repository rocky2431/ultra-builder-pro (11 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 909 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 2026-08-30.
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.