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/zdrjson/thinking-prompts-skillWrote 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/rules/zdrjson/thinking-prompts-skill/thinking-prompts)<a href="https://agentmods.dev/rules/zdrjson/thinking-prompts-skill/thinking-prompts"><img src="https://agentmods.dev/badge/rules/zdrjson/thinking-prompts-skill/thinking-prompts/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/rules/zdrjson/thinking-prompts-skill/thinking-prompts"><img src="https://agentmods.dev/badge/rules/zdrjson/thinking-prompts-skill/thinking-prompts.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 | $0.00055 | $0.01861 |
| Opus 5.5 | $0.00022 | $0.00744 |
| Sonnet 5.5 | $0.00011 | $0.00372 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade A, and why
thinking-prompts 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 2mo 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 2mo ago First seen · 96 lines · 55 tokens per session scan A 1f153360707b
thinking-prompts is a cursor rule published in the GitHub repository zdrjson/thinking-prompts-skill (3 stars, last pushed 2mo ago), with no licence file. It adds 55 tokens to every session and 1,861 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other cursor rules, from other repositories
pytorch-deep-learning
A set of Python guidelines for building and training deep-learning models with PyTorch, a machine-learning framework. It covers model structures, training loops, loss calculation, optimization, and choosing available hardware.
scikit-learn-machine-learning
A set of Python guidelines for building machine-learning models with scikit-learn, a library for training models from data. It covers preparing data, linking processing steps into pipelines, training models, and checking results with cross-validation.
tensorflow-handbook
A set of guidelines for building and training neural networks with TensorFlow and Keras, Python tools for machine learning. It covers sequential models, model training, distributed training, and using multiple GPUs.
t-800-operator-routing
A routing rule for explaining Cursor and its agent features to Russian-speaking beginners. Cursor is a code editor with built-in AI assistance.
learn-as-you-build
Learn As You Build — name concepts and teach reasoning during every session.
bootstrap-alwayson
Minimal always-required LLM fixes.