prompts

prompts is a cursor rule for Cursor from thearnavrustagi/marketmenow. It costs 0 tokens per session (804 once invoked), scanned A, original, MIT.

A set of rules for managing prompts used by language models, including where prompt text belongs and how application code should load it.

In plain words
What is it for?
Use it when adding or changing chat prompts, user templates, in-context examples, or deterministic prompts such as grading and rubric generation.
Why use it?
It prevents prompt text from being scattered through source code or loaded inconsistently, making prompts easier to maintain and reuse.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/thearnavrustagi/marketmenow/prompts
Clone the repo
git clone --depth 1 https://github.com/thearnavrustagi/marketmenow

Made for: Cursor.

Wrote 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.

agentmods badge for prompts

README.md
[![agentmods](https://agentmods.dev/badge/rules/thearnavrustagi/marketmenow/prompts.svg)](https://agentmods.dev/rules/thearnavrustagi/marketmenow/prompts)
Your own site
<a href="https://agentmods.dev/rules/thearnavrustagi/marketmenow/prompts"><img src="https://agentmods.dev/badge/rules/thearnavrustagi/marketmenow/prompts.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 804 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00804
Opus 5 $0.00000 $0.00402
Sonnet 5 $0.00000 $0.00161
Haiku 4.5 $0.00000 $0.00080

Measured 4d ago against content hash e2a0a624c01e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

.cursor/rules/prompts.mdc · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Management Rules

PromptBuilder Required for Content Generation

All content generation prompts MUST use PromptBuilder (core/prompt_builder.py). Do NOT create new load_prompt() helper functions. Use PromptBuilder.build() with decomposed persona + function YAML files.

Deterministic tool prompts (autograde, rubric generation, sentiment scoring, guideline generation, worksheet gen/fill) may use direct YAML loading since they don't need persona/brand injection.

No Inline Prompts

All LLM prompt text — system prompts, user prompts, image-generation prompts, and ICL templates — MUST live in YAML files under prompts/.

Python code loads prompts via PromptBuilder.build() (preferred) or yaml.safe_load + Jinja2 (tool prompts only); it must never contain hardcoded prompt strings.

Standard YAML Schema

Chat prompts use two keys:

system: |
  The AI's persona, rules, and constraints.
  Uses {{ jinja2_variables }} for dynamic data.

user: |
  The per-request template with {{ variables }}.

ICL (in-context learning) templates use the block: key:

block: |
  {% for ex in examples %}...{% endfor %}

Image-generation fallback prompts may use custom keys (e.g. simplify_template:, fallback:).

Resolution Order

PromptBuilder and adapter load_prompt() helpers resolve files in this order:

  1. projects/{slug}/prompts/{platform}/{file} — project + platform override
  2. projects/{slug}/prompts/{file} — project-level default
  3. prompts/{platform}/{file} — global default

Onboarding Templates

Persona templates used during mmn project add live in prompts/templates/. These are YAML files with placeholder tokens ({{ persona_description }}, etc.) that get filled in by core/project_templates.py and written to the new project.

Exempt from This Rule

  • LangChain tool docstrings (integrations/langchain.py) — required by framework
  • Error messages, CLI help text, log messages
  • The labeling_instruction conditional fragment in worksheet.py which is a short inline string passed as a template variable, not a standalone prompt

Read the full file on GitHub · 93 lines

Changes

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.

  1. 4d ago First seen · 93 lines · 0 tokens per session scan A e2a0a624c01e

Subscribe to this mod's changes

prompts is a cursor rule published in the GitHub repository thearnavrustagi/marketmenow (132 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 804 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 2026-09-01.