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/jellydn/my-ai-toolsWrote 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/jellydn/my-ai-tools/ultrathink)<a href="https://agentmods.dev/commands/jellydn/my-ai-tools/ultrathink"><img src="https://agentmods.dev/badge/commands/jellydn/my-ai-tools/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/jellydn/my-ai-tools/ultrathink"><img src="https://agentmods.dev/badge/commands/jellydn/my-ai-tools/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 | $0.00000 | $0.00290 |
| Opus 5.5 | $0.00000 | $0.00116 |
| Sonnet 5.5 | $0.00000 | $0.00058 |
| Haiku 4.5 | $0.00000 | $0.00029 |
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 28d 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
Usage
/ultrathink <TASK_DESCRIPTION>
Context
- Task description: $ARGUMENTS
- Relevant code or files will be referenced ad-hoc using @ file syntax.
Your Role
Complete the task and verify the result. Use specialist sub-agents only when they provide useful expertise or independent work:
- Architect Agent – designs high-level approach.
- Research Agent – gathers external knowledge and precedent.
- Coder Agent – writes or edits code.
- Tester Agent – proposes tests and validation strategy.
Process
- State the goal, material assumptions, unknowns, and observable done conditions.
- If delegating, give each sub-agent a bounded task, file ownership, and required evidence. Run independent tasks in parallel; keep dependent work in order.
- Check returned claims against the cited code, sources, or test output before accepting them. Integrate the results and run the relevant combined checks yourself.
- Continue until the done conditions are met or a blocker needs user input. Follow the repository's approval rules for destructive or external actions.
Output Format
- Needs From You – blockers or approvals, only if needed.
- Outcome – completed work and a short decision summary with evidence and trade-offs, not an internal reasoning transcript.
- Verification – checks run, results, and anything not confirmed, including where you looked.
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.
- 28d ago Changed 1e86650e5b2b
- 1mo ago First seen · 31 lines · 0 tokens per session scan A 6de018b4036f
ultrathink is a command published in the GitHub repository jellydn/my-ai-tools (124 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 290 tokens. 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
cancel-ralph
Cancel active Ralph Loop.
constraints
A command for defining a project's quality standards through a short interview and a written CONSTRAINTS.md file. It records checks, thresholds, exceptions, and commands for enforcing them.
release
Git geçmişinden hedef kitleye uygun sürüm notları oluştur.
rclone_config_dump
Dump the config file as JSON.
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.