cursor

A set of project rules for storing and retrieving business-domain knowledge through an MCP service. MCP is a way for an assistant to connect to external tools or data sources.

In plain words
What is it for?
Use it in projects that maintain shared domain knowledge, so the assistant can search existing context, stage branch-specific updates, and resolve contradictions before storing changes.
Why use it?
It keeps project decisions, workflows, integrations, and their reasons available across sessions while handling conflicts before new information is saved.

Cursor rule

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/mashware/domain-memory/cursor
Clone the repo
git clone --depth 1 https://github.com/mashware/domain-memory
Per session 221 This file is loaded in full into every session.
When invoked 221 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.

ModelPer sessionOnce invoked
Fable 5 $0.00221 $0.00221
Opus 5 $0.00111 $0.00111
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured yesterday against content hash 686b98534e9a, 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 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/pointer-blocks/cursor.mdc · 18 lines

What it actually says

Domain Memory

This project uses domain-memory to accumulate business-domain knowledge (flows, decisions, integrations, "why" nuances).

Read the full instructions at .domain-memory/instructions.md at the start of every session. They are mandatory and cover when to query the MCP, how to use per-branch staging, the "why vs what" rule, conflict handling, and the PR flow.

Minimum rules if you have not yet read the full instructions:

  • On startup, query the domain-memory MCP with search_knowledge using the current task. If it fails or takes >2s, continue without context.
  • Silence by default: do not propose saving knowledge unless there is a strong signal.
  • Before writing to the store, always re-query. Never trust what you remember from the start of the session.
  • Conflicts block the save and are resolved live with the user.
  • MCP failures must never break the session or surface as an unsolicited error to the user.
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. yesterday First seen · 18 lines · 221 tokens per session scan A 686b98534e9a

Subscribe to this mod's changes

cursor is a cursor rule published in the GitHub repository mashware/domain-memory (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 221 tokens to every session, about $0.0011 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.