Borrowing it
Nothing to install: this file belongs to yinanli1917-cloud/searching-apple-notes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yinanli1917-cloud/searching-apple-notes/main/CLAUDE.mdgit clone --depth 1 https://github.com/yinanli1917-cloud/searching-apple-notesWrote 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/instructions/yinanli1917-cloud/searching-apple-notes/claude-md)<a href="https://agentmods.dev/instructions/yinanli1917-cloud/searching-apple-notes/claude-md"><img src="https://agentmods.dev/badge/instructions/yinanli1917-cloud/searching-apple-notes/claude-md/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.
<a href="https://agentmods.dev/instructions/yinanli1917-cloud/searching-apple-notes/claude-md"><img src="https://agentmods.dev/badge/instructions/yinanli1917-cloud/searching-apple-notes/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00529 | $0.00529 |
| Opus 5 | $0.00264 | $0.00264 |
| Sonnet 5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
searching-apple-notes CLAUDE.md 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 9d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
apple-notes-mcp
MCP server for searching, retrieving, and creating Apple Notes.
Tech Stack
- Python 3.12 (MCP server, indexing, search)
- Qwen/Qwen3-Embedding-0.6B via sentence-transformers (1024-dim, fp16, MPS)
- ChromaDB (vector index at
chroma_db/, gitignored) - AppleScript (Notes.app integration)
- SQLite (Apple Notes mirror at
~/notes.db)
Directory Structure
| Path | Purpose |
|---|---|
scripts/ |
MCP server, indexer, shared embedding_backend.py |
skills/searching-apple-notes/ |
Claude Code skill (search/sync/create helpers) |
tests/ |
unittest suite (embedding guards; run with python3.12) |
legacy/ |
Previous versions; legacy/scripts/export_notes_fixed.py is still the active export path |
Conventions
- MCP tool responses must be JSON-serializable
- Search is semantic: Qwen3 vectors in ChromaDB, collection
apple_notes_qwen3_0_6b. One collection per model — the legacy BGE-M3 collectionapple_notesstays on disk untouched; a model swap means a full rebuild into a new collection - Embedding memory guards live in
scripts/embedding_backend.py(seq 2048, batch 4, 8000-char truncation) and are regression-tested intests/test_embedding_backend.py— never raise them without re-reading the crash notes there - Queries are prefix-instructed, documents raw; query paths must use
encode_query()+query_embeddings=, neverquery_texts= - Never modify Notes.app database directly — use AppleScript for writes
Codex Harness
Codex does not receive Claude hook injections automatically. Treat .codex/workflow.md and scripts/codex_harness.py context as the native pull-based context layer.
Common commands:
python3 scripts/codex_harness.py context
python3 scripts/codex_harness.py health
python3 scripts/codex_harness.py task create "<title>"
python3 scripts/codex_harness.py task start <slug-or-dir>
python3 scripts/codex_harness.py task finish [slug-or-dir]
python3 scripts/codex_harness.py task archive <slug-or-dir>
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.
- 9d ago First seen · 49 lines · 529 tokens per session scan A c469a791c58b
searching-apple-notes CLAUDE.md is an instructions file published in the GitHub repository yinanli1917-cloud/searching-apple-notes (2 stars, last pushed 1mo ago), licensed MIT. It adds 529 tokens to every session, about $0.0026 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.