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.
npx agentmods add rules/gcake119/joplin-llm-wiki/cursorrulesgit clone --depth 1 https://github.com/gcake119/joplin-llm-wikiWrote 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.
[](https://agentmods.dev/rules/gcake119/joplin-llm-wiki/cursorrules)<a href="https://agentmods.dev/rules/gcake119/joplin-llm-wiki/cursorrules"><img src="https://agentmods.dev/badge/rules/gcake119/joplin-llm-wiki/cursorrules.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00971 | $0.00971 |
| Opus 5 | $0.00485 | $0.00485 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spectra Instructions
This project uses Spectra for Spec-Driven Development(SDD).
Directory Structure
- Specs:
openspec/specs/- Current truth, what IS built - Changes:
openspec/changes/- Proposals, what SHOULD change - Archive:
openspec/changes/archive/- Completed changes - Config:
openspec/config.yaml- Project context and rules - Roadmap:
openspec/ROADMAP.md- Planned capabilities (non-normative until proposed)
Workflow
discuss? → propose → apply ⇄ ingest → archive
joplin-llm-wiki（實作速記）
- 本 repo 部分採用
gatelynch/llm-knowledge-base四層知識流：raw/→raw/，wiki/→wiki/，brainstorming/／artifacts/保留為探索與成品區；上游專案不是 runtime dependency。 - Joplin notebook 匯出使用
raw/<joined-notebook-slug>/<safe-title>.md；巢狀筆記本以-串接，例如工作/專案A/會議→工作-專案A-會議。compiled wiki 只能寫入wiki/summaries/*.md、wiki/concepts/*.md、wiki/indexes/All-Sources.md、wiki/indexes/All-Concepts.md，三個分類底下不得建立子資料夾；source_refs使用raw/下的相對路徑。 sqlite-sync正常模式匯出後會比對 raw snapshot，只在 raw 變更時依joplin_sqlite_sync.pipeline.compile_mode: local|agent|off觸發wiki-compile、agent-compile或不編譯。第一次非 dry-run 只建立 baseline；--export-only更新 raw/state 但不編譯；--snapshot-only只從既有raw/建 baseline，不開 SQLite、不刪檔、不編譯。sqlite-sync定時檢查是輪詢，不是檔案 watcher。常駐輪詢用joplin_sqlite_sync.schedule.every_seconds或--every <seconds>；若由 launchd/cron 重複啟動單輪命令，保持every_seconds: null，避免雙重排程。- 查詢指令是
query，預設優先讀wiki/，必要時補raw/；Q&A 先建立 pending capture，確認後才寫brainstorming/chat/或artifacts/projects/<project>/。ask、index、watch、RAG／Chroma／embedding vector 管線已移除。 - 人可讀的知識管理輸出使用繁體中文。技術名詞、source path、filename 可保留原文。
- 模型分流：本地預設是
wiki-compile+ Ollama；Codex 月訂閱路線是agent-compile+ 本機codex exec，不使用 OpenAI API key，也不等同 API 額度。兩條管路預設都掃完整個raw/筆記庫；--batch=true才是 10-15 頁單批次 fallback。OpenAI API provider 目前未實作。 wiki-compile/agent-compile可觸發joplin_wiki_writeback（預設開啟）；compile 寫回只同步@llm-wiki/wiki/{summaries,concepts,indexes}。brainstorming與artifacts只在需要整理問答、健康報告或作品時按需寫回。迷你測試用設定請見.cursor/rules/joplin-brain-config.mdc。- 本機小模型範例（
gemma4:e4b、corpus_digest_max_files: 40等）見config.yaml.example與 README「本機小模型」。
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.
- 4d ago First seen · 32 lines · 971 tokens per session scan A 7c5bc05228e6
cursorrules is a cursor rule published in the GitHub repository gcake119/joplin-llm-wiki (2 stars, last pushed 2mo ago), licensed MIT. It adds 971 tokens to every session, about $0.0049 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.
Other cursor rules, from other repositories
cursorrules
Always write tests before implementation code. Every feature and bugfix must be covered by a test that fails before the change and passes after it. Keep the test suite fast and deterministic.
cursorrules
When the user asks you to implement a feature or fix an issue, use mooquickstart to atomically create and claim the task in a single step with complete specifications.
agentmemory
AgentMemory MCP server rules — use addmemory before answering any question that introduces a project-specific convention, dependency, or constraint.
digital-brain
A Claude Code plugin and Obsidian vault that builds persistent, compounding knowledge bases using Andrej Karpathy's LLM Wiki pattern. This repo works with Cursor's AI through the cross-platform Agent Skills format.
blekline-chat-guard
Blekline chat guard — mask prompts via MCP and respect Cursor hook blocks.
cursorrules
TypeScript MCP server — queryable knowledge base for AI coding agents. npm: @compr/contextengine-mcp · License: BSL-1.1.