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 Armert-Labs/cursor-plugin --skill cursor-promptinggit clone --depth 1 https://github.com/Armert-Labs/cursor-pluginWrote 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/armert-labs/cursor-plugin/cursor-prompting)<a href="https://agentmods.dev/skills/armert-labs/cursor-plugin/cursor-prompting"><img src="https://agentmods.dev/badge/skills/armert-labs/cursor-plugin/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/armert-labs/cursor-plugin/cursor-prompting"><img src="https://agentmods.dev/badge/skills/armert-labs/cursor-plugin/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 | $0.00027 | $0.00417 |
| Opus 5.5 | $0.00011 | $0.00167 |
| Sonnet 5.5 | $0.00005 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00042 |
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 1mo 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
Treat cursor-agent like an operator, not a collaborator. Prompts should be compact and specific.
Principles:
- State the task and the done-state in one or two sentences. Avoid long preambles.
- Name the concrete output you expect (a patch, a diagnosis, a list, a one-line answer).
- Give one task per run. Do not bundle unrelated work.
- Add constraints only where they matter (files to touch or avoid, tests to keep green, "do not refactor unrelated code").
- Prefer explicit contracts over vague nudges. If you need verification, say "run the tests and report the result".
Cursor specifics:
cursor-agentis headless and write-capable by default in this plugin (--force).--read-onlymaps to--mode ask(read-only Q&A): Cursor reads and answers but never edits.- Cursor resolves its own model unless
--modelis set. There is no reasoning-effort flag. - The agent already has read/write access to the working directory, so reference files by path rather than pasting their contents.
Recommended models per task (set via --model <alias>):
- Routine rescue / quick edits:
spark(composer-2.5) — fast and cheap. - Deep implementation or debugging:
review/codex(gpt-5.1-codex-max-high) ormax(gpt-5.5-high). - Code review / adversarial review:
review(gpt-5.1-codex-max-high). - A second opinion from a different model family:
opus(claude-opus-4-8-high). - Any concrete
cursor-agentmodel id fromcursor-agent --list-modelsalso works.
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.
- 1mo ago First seen · 29 lines · 27 tokens per session scan A bd253b7e1684
cursor-prompting is a skill published in the GitHub repository Armert-Labs/cursor-plugin (3 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 417 once invoked, about $0.0001 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 skills, from other repositories
refine
Crossover layer between the user's intent and LLM execution: takes a raw prompt (terse, frustrated, ambiguous, or shorthand), resolves every vague reference to a concrete artifact, recalls past decisions and lessons, and compiles a verifiable execution contract BEFORE any code is touched. Invoke explicitly as $refine…
llm-eng-checks
Use when building or hardening an LLM feature — prompt design, RAG, eval harness, model/provider selection, guardrails, and token/cost budgeting — with omp-native tools (bash for real API round-trips, read/grep for the repo's own client, no vendor-plugin dependency, provider-agnostic). PRIME RULE — no LLM feature is…
nativeprompt
A prompt editor that adapts a user's request to the rules of a selected coding model, such as Claude Code, Codex, Gemini CLI, or GPT-5.
cortex-prompt
Build a production-ready prompt package — system prompt, few-shot examples, output format, edge case handling, eval criteria. Use when asked to "prompt engineering", "build a prompt", "write a system prompt", or "improve this prompt".
agy-prompting
Internal helper — how to tighten a user request into a sharp prompt for the Antigravity CLI (agy / Gemini 3.x with native web search and agentic tools).
c-ai
Query LLMs from the CLI — pipe text for summarization, chat interactively, use local or cloud models with llm or aichat.