agent

agent is a cursor rule for Cursor from ctxs-ai/ctxs.ai. It costs 0 tokens per session (281 once invoked), scanned A, original, MIT.

A TypeScript agent built with Mastra to organize documents stored in Markdown files. It uses Bun, Commander.js, frontmatter, and language-model interactions.

In plain words
What is it for?
Use it to organize Markdown documents, validate or create frontmatter, manage files, and run the librarian-style command-line agent.
Why use it?
It separates document handling, agent decisions, file operations, language-model calls, and the command-line interface so the project is easier to maintain.

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/ctxs-ai/ctxs.ai/agent
Clone the repo
git clone --depth 1 https://github.com/ctxs-ai/ctxs.ai

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 agent

README.md
[![agentmods](https://agentmods.dev/badge/rules/ctxs-ai/ctxs.ai/agent.svg)](https://agentmods.dev/rules/ctxs-ai/ctxs.ai/agent)
Your own site
<a href="https://agentmods.dev/rules/ctxs-ai/ctxs.ai/agent"><img src="https://agentmods.dev/badge/rules/ctxs-ai/ctxs.ai/agent.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 281 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 $0.00281
Opus 5 $0.00000 $0.00140
Sonnet 5 $0.00000 $0.00056
Haiku 4.5 $0.00000 $0.00028

Measured 4d ago against content hash 7e7ac3a12025, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent 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/agent.mdc · 33 lines

What it actually says

This is an agent implementation that will serve as an intelligent librarian, organizing and managing information in markdown files. The implementation uses Mastra as its foundation.

Key Architectural Points:

  1. The agent is implemented as a TypeScript application using Bun as the runtime
  2. Core functionality is centered around markdown file processing and LLM interactions
  3. Uses Commander.js for CLI interface design
  4. Implements frontmatter validation and generation capabilities

Development Guidelines:

  1. Keep the agent's core responsibilities separate from the file processing logic
  2. Use TypeScript types rigorously, especially for frontmatter and configuration interfaces
  3. Maintain clear separation between:
    • Agent core logic
    • File system operations
    • LLM interactions
    • CLI interface

When implementing new features:

  1. Consider the agent's primary role as a librarian/organizer
  2. Ensure proper error handling for file operations and LLM interactions
  3. Add appropriate logging for debugging and monitoring
  4. Keep the CLI interface intuitive and consistent

Code Style:

  1. Use async/await for asynchronous operations
  2. Implement proper TypeScript types for all functions and data structures
  3. Document complex logic with clear comments
  4. Use meaningful variable names that reflect the librarian/organizer domain
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 · 33 lines · 0 tokens per session scan A 7e7ac3a12025

Subscribe to this mod's changes

agent is a cursor rule published in the GitHub repository ctxs-ai/ctxs.ai (27 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 281 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.