Development rules for CRATE, a local-first tool that turns captured material into a linked Markdown encyclopedia. Source captures stay in raw files, while compiled pages are written to a wiki.

Use it when developing CRATE features, compiling notes into wiki pages, maintaining provenance, searching the knowledge base, or producing optional question-and-answer outputs.

It protects original captures, keeps sources traceable, prevents unsafe file access, and requires tests and code-quality checks for substantive changes.

How GuiminChen/crate configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to GuiminChen/crate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/GuiminChen/crate/main/.cursorrules

Clone the repo

git clone --depth 1 https://github.com/GuiminChen/crate

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/guiminchen/crate/cursorrules/github.svg)](https://agentmods.dev/rules/guiminchen/crate/cursorrules)

Your own site

<a href="https://agentmods.dev/rules/guiminchen/crate/cursorrules"><img src="https://agentmods.dev/badge/rules/guiminchen/crate/cursorrules/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/rules/guiminchen/crate/cursorrules"><img src="https://agentmods.dev/badge/rules/guiminchen/crate/cursorrules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 605 This file is loaded in full into every session.

When invoked 605 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00605	$0.00605
Opus 5.5	$0.00242	$0.00242
Sonnet 5.5	$0.00121	$0.00121
Haiku 4.5	$0.00060	$0.00060

Measured 1mo ago against content hash f2bef828d022, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

.cursorrules · 28 lines

How it starts

The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRATE AI development guidelines

Product shape

CRATE is a file-first personal knowledge compiler: raw/ captures stay traceable; wiki/ holds a linked Markdown encyclopedia maintained by LLM-assisted compile passes, plus lint, search, and optional Q&A outputs.

Non-negotiables

Local-first: The vault on disk is the source of truth; cloud is for inference only when the user opts in.
Zone boundaries: Default policy — do not overwrite files under raw/**. LLM write paths are wiki/** and configured output dirs (e.g. wiki/outputs/**).
Provenance: Compiled pages must tie back to raw/ or URLs via front matter (sources).
Safety: Canonicalize paths; reject escape from vault root. No secrets in repo or wiki. No arbitrary shell from agents unless explicitly scoped and documented.
Budgets: Compile and Q&A runs should respect token/page budgets and remain idempotent where possible.
Quality: New Python code uses type hints, structured logging, tests for non-trivial logic, and matches pyproject tool settings (black, isort, flake8, mypy).
Testing: Follow .cursor/rules/testing.md: every feature or substantive change updates tests/; run pytest and ensure green before calling work done.
Bug memory: Follow .cursor/rules/lessons_from_bugs.md: when fixing a bug, append docs/lessons-learned.md and add a regression test when feasible.

When implementing features

M0–M3 scope and cross-cutting commands (compile --wiki-graph, wiki graph, report raw-wiki, ingest, wiki index-extend, lint --http-external, etc.) are summarized in .cursor/rules/architecture.md.
Read docs/PRD.md for scope and priorities; docs/technical-design.md for flows and vault layout; docs/providers.md for OpenAI-compatible chat/embedding env (CRATE_LLM_PROVIDER, CRATE_EMBEDDING_*).
Repo entrypoints: README.md (English) · README.zh.md (简体中文).
Prefer small, reviewable diffs; extend existing abstractions instead of duplicating vault/path logic.

Read the full file on GitHub · 28 lines

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.

1mo ago First seen · 28 lines · 605 tokens per session scan A f2bef828d022

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository GuiminChen/crate (16 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 605 tokens to every session, about $0.0024 per session on Opus 5.5. 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 2026-08-30.

Memory and context

mempalace-recall-always

Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.

MemPalace/mempalace · 260 tokens

dreamd-recall

Search dreamd at the start of a task and quote a hit. Append when the user corrects you or states a decision.

botzrDev/dreamd · 136 tokens

session-memory

Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.

major7apps/pensyve · 22 tokens

common_memory_bank

I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…

shalomeir/common-memory-bank · 1,801 tokens

self-improving-obsidian-llm-wiki

LLM Wiki OS operating rules.

Bahgs/Self-Improving-Obsidian-LLM-Wiki · 146 tokens

memsprout

Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.

memsprout/agents · 519 tokens

crate: Cursor rule for Cursor