cursorrules

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.

In plain words
What is it for?
Use it when developing CRATE features, compiling notes into wiki pages, maintaining provenance, searching the knowledge base, or producing optional question-and-answer outputs.
Why use it?
It protects original captures, keeps sources traceable, prevents unsafe file access, and requires tests and code-quality checks for substantive changes.

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/guiminchen/crate/cursorrules
Clone the repo
git clone --depth 1 https://github.com/GuiminChen/crate

Made for: Cursor.

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. 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 $0.00605 $0.00605
Opus 5 $0.00302 $0.00302
Sonnet 5 $0.00121 $0.00121
Haiku 4.5 $0.00060 $0.00060

Measured 2d ago against content hash f2bef828d022, 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 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.

.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

  1. Local-first: The vault on disk is the source of truth; cloud is for inference only when the user opts in.
  2. Zone boundaries: Default policy — do not overwrite files under raw/**. LLM write paths are wiki/** and configured output dirs (e.g. wiki/outputs/**).
  3. Provenance: Compiled pages must tie back to raw/ or URLs via front matter (sources).
  4. Safety: Canonicalize paths; reject escape from vault root. No secrets in repo or wiki. No arbitrary shell from agents unless explicitly scoped and documented.
  5. Budgets: Compile and Q&A runs should respect token/page budgets and remain idempotent where possible.
  6. Quality: New Python code uses type hints, structured logging, tests for non-trivial logic, and matches pyproject tool settings (black, isort, flake8, mypy).
  7. Testing: Follow .cursor/rules/testing.md: every feature or substantive change updates tests/; run pytest and ensure green before calling work done.
  8. 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.

  1. 2d 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 3mo ago), licensed Apache-2.0. It adds 605 tokens to every session, about $0.0030 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 2026-08-30.