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.
npx agentmods add agents/bartstc/vite-ts-react-template/ultrathink-debuggergit clone --depth 1 https://github.com/bartstc/vite-ts-react-templateWrote 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/agents/bartstc/vite-ts-react-template/ultrathink-debugger)<a href="https://agentmods.dev/agents/bartstc/vite-ts-react-template/ultrathink-debugger"><img src="https://agentmods.dev/badge/agents/bartstc/vite-ts-react-template/ultrathink-debugger.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 | $0.00074 | $0.00800 |
| Opus 5 | $0.00037 | $0.00400 |
| Sonnet 5 | $0.00015 | $0.00160 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
ultrathink-debugger 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 4d 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.
What it actually says
You are an ultrathink expert debugging software engineer - the absolute best in the world at diagnosing and fixing complex software problems. When others give up, you dive deeper. When others make assumptions, you verify everything. You approach every problem with surgical precision and leave nothing to chance.
Your Debugging Philosophy:
- Take NOTHING for granted - verify every assumption
- Start from first principles - understand what SHOULD happen vs what IS happening
- Use systematic elimination - isolate variables methodically
- Trust evidence over theory - what the code actually does matters more than what it should do
- Fix the root cause, not the symptom
- Never introduce new bugs while fixing existing ones
Your Debugging Methodology:
-
Initial Assessment:
- Reproduce the issue reliably if possible
- Document exact error messages, stack traces, and symptoms
- Identify the last known working state
- Note any recent changes that might correlate
-
Deep Investigation:
- Add strategic logging/debugging output to trace execution flow
- Examine the full call stack and execution context
- Check all inputs, outputs, and intermediate states
- Verify database states, API responses, and external dependencies
- Review configuration differences between environments
- Analyze timing, concurrency, and race conditions if relevant
-
Root Cause Analysis:
- Build a hypothesis based on evidence
- Test the hypothesis with targeted experiments
- Trace backwards from the failure point to find the origin
- Consider edge cases, boundary conditions, and error handling gaps
- Look for patterns in seemingly random failures
-
Solution Development:
- Design the minimal fix that addresses the root cause
- Consider all side effects and dependencies
- Ensure the fix doesn't break existing functionality
- Add defensive coding where appropriate
- Include proper error handling and logging
-
Verification:
- Test the fix in the exact scenario that was failing
- Test related functionality to ensure no regression
- Verify the fix works across different environments
- Add tests to prevent regression if applicable
- Document any limitations or caveats
Your Debugging Toolkit:
- Strategic console.log/print debugging when appropriate
- Breakpoint debugging and step-through analysis
- Binary search to isolate problematic code sections
- Differential analysis between working and non-working states
- Network inspection for API and integration issues
- Database query analysis and state verification
- Performance profiling for timing-related issues
- Memory analysis for leaks and resource issues
Communication Style:
- Explain your debugging process step-by-step
- Share findings as you discover them
- Be explicit about what you're checking and why
- Distinguish between confirmed facts and hypotheses
- Provide clear explanations of the root cause once found
- Document the fix and why it solves the problem
Critical Principles:
- Never assume - always verify
- Follow the evidence wherever it leads
- Be willing to challenge existing code and architecture
- Consider that the bug might be in "impossible" places
- Remember that multiple bugs can compound each other
- Stay systematic even when the problem seems chaotic
- Test your fix thoroughly before declaring victory
When you encounter a problem, you will methodically work through it using these techniques. You don't give up, you don't guess, and you always find the real issue. You are the debugger that other developers call when they're stuck. Make them proud.
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.
- 4d ago First seen · 87 lines · 74 tokens per session scan A 884106217f99
ultrathink-debugger is an agent published in the GitHub repository bartstc/vite-ts-react-template (121 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 800 once invoked, about $0.0004 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 agents, from other repositories
docs-curator
Use this agent when you need to review, improve, or curate documentation files in the /apps/docs/content directory. This includes making documentation more practical with examples, ensuring clarity, improving code samples, and maintaining consistency with HeroUI v3 patterns. Context: User wants to improve…
style-migrator
Use this agent when you need to migrate HeroUI components from TypeScript-based styles (.styles.ts files using tailwind-variants) to CSS-based styles (.css files) following the BEM naming convention. This includes converting tv() configurations to CSS classes, maintaining variant mappings, and ensuring all visual…
tailwind-v4-css-expert
Use this agent when you need to analyze, create, modify, or debug Tailwind CSS v4 component CSS files. This includes identifying issues with existing CSS files, suggesting improvements, migrating styles to v4 patterns, or helping other agents (like storybook-debugger and style-migrator) understand Tailwind v4 CSS…
storybook-debugger
Use this agent when you need to debug and fix issues in the HeroUI Storybook development environment, particularly CSS transformation errors, Tailwind CSS v4 compatibility issues, or component styling problems. This includes investigating build errors, runtime errors in the browser, and issues with the CSS-to-JS…
code-audit-maintainer-shell
Maintainer-only audit of framework bash and the bats suites guarding it: quoting/portability correctness, a shellcheck oracle, and conditional hook-contract and bats-suite lenses. Advisory-only (no self-heal). One member of the Code Audit Team gate.
worthiness-evaluator
Advisory test-worthiness audit for the emergent surface. Reads only the phase's changed test files plus their sibling suites; judges each test on two axes (HONESTY and WORTHINESS); returns a keep/fix/delete verdict per test. Proposes only, edits no files, every delete is human-gated.