projectbrief

A project-planning template for defining the project name, purpose, requirements, success criteria, constraints, users, major features, and work that is out of scope. Its fields are still placeholders.

In plain words
What is it for?
Use it to write the initial project brief, define requirements and boundaries, identify users, and agree on completion criteria.
Why use it?
It provides a shared starting point for deciding what the project should build and how to know it is done, but it currently contains no project-specific answers.

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/hansonli05/cursor-rules-system/projectbrief
Clone the repo
git clone --depth 1 https://github.com/Hansonli05/Cursor-rules-system

Made for: Cursor.

Per session 259 This file is loaded in full into every session.
When invoked 259 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 $0.00259 $0.00259
Opus 5 $0.00130 $0.00130
Sonnet 5 $0.00052 $0.00052
Haiku 4.5 $0.00026 $0.00026

Measured 2d ago against content hash 3420ae423478, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

projectbrief 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 2d 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/memory-bank/projectbrief.mdc · 49 lines

What it actually says

Project Brief

Project Name

[Your Project Name]

Core Purpose

[Brief description of what problem this project solves]

Key Requirements

  • [Primary requirement 1]
  • [Primary requirement 2]
  • [Primary requirement 3]
  • [Additional requirements as needed]

Success Criteria

  • [How will you know the project is successful?]
  • [What are the key metrics or outcomes?]
  • [What defines "done" for this project?]

Project Constraints

  • [Timeline constraints]
  • [Budget constraints]
  • [Technical constraints]
  • [Resource constraints]

Target Users/Audience

  • [Primary user group]
  • [Secondary user groups]
  • [User personas if relevant]

Key Features (High Level)

  • [Feature 1]: [Brief description]
  • [Feature 2]: [Brief description]
  • [Feature 3]: [Brief description]

Out of Scope

  • [What will NOT be included in this project]
  • [Features deliberately excluded]
  • [Future phase considerations]

Note: This file serves as the foundation for all other memory bank files. Update it when project scope or core requirements change.

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. 2d ago First seen · 49 lines · 259 tokens per session scan A 3420ae423478

Subscribe to this mod's changes

projectbrief is a cursor rule published in the GitHub repository Hansonli05/Cursor-rules-system (2 stars, last pushed 1y ago), licensed MIT. It adds 259 tokens to every session, about $0.0013 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.