cursor

An adapter that lets an agent runner use Cursor, a code editor with an AI agent, from the command line. It supports prompts, model selection, project settings, hooks, tool calls, streaming, images, files, and MCP servers.

In plain words
What is it for?
Use it to run Cursor agents from scripts or other agent systems, configure project hooks, add MCP servers, and process Cursor session files.
Why use it?
It lets automated workflows start Cursor tasks and read their session output without requiring every task to be performed manually in the editor. It also connects Cursor to shared agent-runner features.

Agent

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 agents/a5c-ai/babysitter/cursor
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 349 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 $0.00349
Opus 5 $0.00000 $0.00175
Sonnet 5 $0.00000 $0.00070
Haiku 4.5 $0.00000 $0.00035

Measured 3d ago against content hash dbf06984aa59, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor 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 3d 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.

docs/adapters/reference/agents/cursor.md · 63 lines

What it actually says

Cursor

Adapter for the Cursor editor's agent CLI.

Install

adapters install cursor

Supported on macOS, Linux and Windows.

Auth

  • API keyCURSOR_API_KEY.
  • Browser login — sign in to your Cursor account.

Auth/config file: ~/.cursor/settings.json.

Minimal run

adapters run cursor --prompt "Refactor this function"

Notable flags

  • --model <id> — default cursor-fast.
  • --prompt <text> — forwarded from RunOptions.prompt.

Session files

  • Location: ~/.cursor/sessions/*.jsonl
  • JSONL format; events of type text, message, tool_call are parsed.

Hooks

Hook support: yes — Compatible with Claude Code hooks. Supports lifecycle events with cross-platform configuration.

Hook configuration:

  • Global: ~/.cursor/hooks.json
  • Project: .cursor/hooks.json
  • Enterprise: /etc/cursor/hooks.json

MCP Servers

adapters mcp install cursor <mcp-server>
adapters mcp list cursor

Registry: https://modelcontextprotocol.io

Capabilities

Tool calling with parallel tool calls, text and tool-call streaming, image input, file input, 128k context. Project-level config is supported.

Known limitations

  • Installation is manual (no npm/brew); adapters agent install cursor reports manual-only.
  • No thinking / reasoning modes.
  • No JSON / structured-output mode.
  • Approval modes are not explicitly wired (no --yolo flag emitted).
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. 3d ago First seen · 63 lines · 0 tokens per session scan A dbf06984aa59

Subscribe to this mod's changes

cursor is an agent published in the GitHub repository a5c-ai/babysitter (1,757 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 349 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.

Related

Other agents, from other repositories

questioner

Use as the first agent of the QRSPI pipeline. Decomposes a user's task description into a full task record (task.md) and neutral research questions (questions.md), plus conditional artifacts — a prd.md when the PRD criteria apply, and a repos.md listing the repos the topic touches when the description names more than…

bostonaholic/team · 89 tokens

file-finder

Use when you need to locate files in a codebase relevant to a specific area. Maps conceptual goals to actual file locations even when exact names are unknown. Operates from questions.md only, never the original task description.

bostonaholic/team · 48 tokens

maintaining-agent-docs

Agent "maintaining-agent-docs" from martin-francois/symphony-trello, covering maintaining agent docs, progressive disclosure contract, what may be added to agents.md (allowlist), what must not be added to agents.md (denylist) and where to put new guidance (decision tree).

martin-francois/symphony-trello · 0 tokens

progressive-disclosure-source

This file is the source of truth for the structure and maintenance approach.

martin-francois/symphony-trello · 0 tokens

documentation-analyst-writer

Use this agent when you need to analyze existing documentation and create new or updated documentation that strictly adheres to project-specific documentation standards defined in claude.md. This agent excels at maintaining consistency with established documentation patterns, ensuring technical accuracy, and producing…

shanraisshan/claude-code-best-practice · 62 tokens

Explore

Fast read-only codebase & docs exploration. Returns structured findings, never raw file dumps.

BlackBeltTechnology/pi-agent-dashboard · 18 tokens