A Cursor project rule connects coding work to dotdog, a tool that stores structured specifications about entities and their relationships.

Use it in projects where entity or relationship changes require dotdog context such as properties, states, and connections.

It tells the agent to load the relevant specifications before changing related code, reducing guesses about the system.

cursorrules — Cursor rule by specdog

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/specdog/dotdog/cursorrules

Clone the repo

git clone --depth 1 https://github.com/specdog/dotdog

Made for: Cursor.

Per session 427 This file is loaded in full into every session.

When invoked 427 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00427	$0.00427
Opus 5	$0.00214	$0.00214
Sonnet 5	$0.00085	$0.00085
Haiku 4.5	$0.00043	$0.00043

Measured yesterday against content hash f6cfe75ff69b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

templates/.cursorrules · 60 lines

What it actually says

dotdog — spec-driven context for Cursor

Copy this file to your project root as .cursorrules

Cursor will auto-load dotdog MCP context on relevant tasks

Dotdog MCP Server

This project uses dotdog for structured specifications. Before any coding task that touches entities or relationships, query the dotdog MCP server to load relevant context.

Quick commands for your agent:

# Start the MCP server (if not running)
dotdog serve

# Or add to your Cursor MCP config (~/.cursor/mcp.json):
{
  "mcpServers": {
    "dotdog": {
      "command": "npx",
      "args": ["-y", "dotdog@latest", "serve"]
    }
  }
}

MCP tools available:

getEntity — Get entity properties, states, lifecycle
traverse — Walk the graph from any node, BFS to depth N
search — Find entities by name or type
schema — Property definitions, zero prose
summary — Node count, edge count, token savings
listProjects — List all spec projects

Workflow:

dotdog doctor — verify specs are clean
listProjects → find your project
getEntity → understand an entity's properties and relationships
traverse → explore connected entities
Code with full context — no hallucinated APIs

When to query:

Before creating/editing any file that touches spec entities
Before suggesting API changes
When you need to understand relationships between concepts
When the user asks "how does X relate to Y?"

Spec files live in:

specs/<project>/SPEC.dog          # product spec
specs/<project>/data-model.dog    # entities, relationships, states
specs/<project>/constitution.dog  # rules, constraints
specs/<project>/plan.dog          # phases, tasks, predictions

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.

yesterday First seen · 60 lines · 427 tokens per session scan A f6cfe75ff69b

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository specdog/dotdog (4 stars, last pushed 1mo ago), licensed MIT. It adds 427 tokens to every session, about $0.0021 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.

Planning ai cli dogfood dotdog spec specification

cursorrules