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/dotclaude/marketplaceWrote 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/dotclaude/marketplace/ultrathink)<a href="https://agentmods.dev/commands/dotclaude/marketplace/ultrathink"><img src="https://agentmods.dev/badge/commands/dotclaude/marketplace/ultrathink/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/dotclaude/marketplace/ultrathink"><img src="https://agentmods.dev/badge/commands/dotclaude/marketplace/ultrathink.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 | $0.00010 | $0.02014 |
| Opus 5 | $0.00005 | $0.01007 |
| Sonnet 5 | $0.00002 | $0.00403 |
| Haiku 4.5 | $0.00001 | $0.00201 |
Grade A, and why
ultrathink 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 9d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ultra-Cognitive Analysis Engine
Execute maximum cognitive diversity analysis by assuming multiple expert personas simultaneously and orchestrating complex problem-solving with constructive disagreement protocols. Transform any challenge into a comprehensive multi-expert consultation with structured dissent and synthesis integration.
Operational Parameters
Challenge Intensity Levels
- foundation: 3-4 perspectives, basic questioning, gentle challenge
- advanced: 5-7 perspectives, systematic disagreement, assumption testing
- maximum: 8-12 perspectives, assumption deconstruction, paradigm questioning
- research: 10+ perspectives, fundamental premise challenging, breakthrough thinking
Domain Expertise Categories
- technical: Systems architecture, performance optimization, security analysis, implementation strategy
- strategic: Business positioning, market analysis, competitive intelligence, growth planning
- creative: Innovation pathways, design thinking, user experience optimization, possibility exploration
- analytical: Data interpretation, research methodology, evidence evaluation, statistical reasoning
- operational: Process optimization, workflow design, efficiency analysis, resource management
Ultra-Cognitive Protocol
Phase 1: Problem Space Deconstruction
[Extended thinking: Analyze the challenge across multiple dimensions to understand complexity, stakeholder impact, constraint boundaries, and success criteria. Map interdependencies and identify hidden assumptions that may limit solution space.]
Analysis Framework:
- Stakeholder impact mapping and priority assessment
- Constraint identification with flexibility evaluation
- Success criteria definition with measurement methodology
- Risk landscape mapping with mitigation pathways
- Resource requirement analysis with optimization opportunities
Phase 2: Expert Persona Assembly
[Extended thinking: Dynamically generate expert personalities with authentic voices, distinct analytical approaches, and specialized vocabularies. Each persona must maintain consistency while contributing unique insights that create constructive interference patterns.]
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.
- 9d ago First seen · 219 lines · 10 tokens per session scan A de8f54ef7253
ultrathink is a command published in the GitHub repository dotclaude/marketplace (43 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 2,014 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.