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 skills add felipeinf/cursor-for-claude --skill cursor-promptinggit clone --depth 1 https://github.com/felipeinf/cursor-for-claudeWrote 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/skills/felipeinf/cursor-for-claude/cursor-prompting)<a href="https://agentmods.dev/skills/felipeinf/cursor-for-claude/cursor-prompting"><img src="https://agentmods.dev/badge/skills/felipeinf/cursor-for-claude/cursor-prompting/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/skills/felipeinf/cursor-for-claude/cursor-prompting"><img src="https://agentmods.dev/badge/skills/felipeinf/cursor-for-claude/cursor-prompting.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 | $0.00013 | $0.00183 |
| Opus 5 | $0.00006 | $0.00092 |
| Sonnet 5 | $0.00003 | $0.00037 |
| Haiku 4.5 | $0.00001 | $0.00018 |
Grade A, and why
cursor-prompting 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.
What it actually says
Cursor Prompting
- Name explicit files, commands, errors, and acceptance criteria when the user provided them.
- Prefer
--mode planfor unfamiliar codebases or fuzzy tasks. - Ask Cursor for a written plan before edits when scope is unclear.
- Keep delegated prompts under roughly 2k tokens.
- Do not add Claude-side conclusions or file inspection results you did not gather.
- When
/cursor:agentwas invoked with--context, the natural-language prompt already includes a fixed five-line session block (Goal, Recent decisions, Files touched, Current state, Open question). Facts only; no transcripts, secrets, or code. If nothing concrete exists to summarize, that block is omitted by the slash command—do not invent one in the subagent.
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 · 14 lines · 13 tokens per session scan A a2103c539735
cursor-prompting is a skill published in the GitHub repository felipeinf/cursor-for-claude (7 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 183 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 2026-08-31.
Other skills, from other repositories
composer-prompting
Internal guidance for shaping a well-specified coding task into a tight Cursor/Composer prompt before delegating it via /cursor:delegate.
prompt-design
A structured method for designing prompts, the instructions given to an AI system. It covers the situation, the desired output, constraints, context, user input, and replaceable variables.
prompt-evaluation
A structured method for testing and comparing prompts, the instructions given to an AI. It uses defined criteria, test examples, comparisons, scores, and a recommendation.
prompt-pilot
Rewrite a rough, vague prompt into a precise, context-enriched prompt. Explores the codebase read-only and weaves real file paths and symbols into the rewritten prompt — never implements the task itself. Use when the user asks to optimize, enrich, or improve a prompt before running it.
prompt-engineering
A set of rules for managing AI prompts and cleaning user input before it is placed into a prompt. Prompt injection is an attempt to make an AI ignore its intended instructions or perform an unintended action.
prompt-cookbook
Build a prompt cookbook for one company's actual vertical and roles rather than generic examples. Each recipe names the job it does, who runs it, the prompt itself, what good output looks like, and how to tell when it went wrong. Written for people who have never written a prompt and will not read documentation about…