agentmods.dev

apfel: Instructions file for Claude Code

CLAUDE.md

apfel CLAUDE.md is an instructions file for Claude Code from Arthur-Ficial/apfel. It costs 6,943 tokens per session, scanned A, original, MIT.

Repository instructions for apfel, a Unix command-line tool and OpenAI-compatible local server that exposes Apple’s on-device language model. They define the product’s main purpose and messaging boundaries.

In plain words
What is it for?
Implementing or documenting prompts, shell pipelines, JSON output, streaming, HTTP endpoints, tool calling, and supported or unsupported server features.
Why use it?
They keep development and documentation focused on the command-line tool and local server instead of presenting secondary features as the core product.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is Arthur-Ficial/apfel's own configuration. It tells Claude Code how to work on apfel itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything apfel configures →

not rated 6.4krepo +13 changed yesterday A scan 6,943 tokens original MIT
View source ↗ Arthur-Ficial/apfel apfel.franzai.com
About the project

apfel is a macOS command-line tool and local OpenAI-compatible server that exposes the language model built into Apple Silicon Macs through Apple Foundation Models. Mac users and developers use it for on-device prompts, shell pipelines, interactive chat, and applications that support OpenAI-compatible APIs. Catalogue add-ons provide agent workflows that use apfel as a local AI backend.

Arthur-Ficial/apfel · 6,359 stars · on GitHub · apfel.franzai.com

Reuse

Borrowing it

Nothing to install: this file belongs to Arthur-Ficial/apfel. 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/Arthur-Ficial/apfel/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Arthur-Ficial/apfel

Made for: Claude Code.

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.

agentmods badge for apfel CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arthur-ficial/apfel/claude-md/github.svg)](https://agentmods.dev/instructions/arthur-ficial/apfel/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/arthur-ficial/apfel/claude-md"><img src="https://agentmods.dev/badge/instructions/arthur-ficial/apfel/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.

agentmods 80×15 button for apfel CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/arthur-ficial/apfel/claude-md"><img src="https://agentmods.dev/badge/instructions/arthur-ficial/apfel/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,943 This file is loaded in full into every session.
When invoked 6,943 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.06943 $0.06943
Opus 5 $0.03472 $0.03472
Sonnet 5 $0.01389 $0.01389
Haiku 4.5 $0.00694 $0.00694

Measured yesterday against content hash 3f317fb50a11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

apfel 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 yesterday.

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.

CLAUDE.md · 388 lines

How it starts

The opening of the file, as written. The whole thing — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.

apfel - Project Instructions

The free AI already on your Mac. This is our claim. Every surface (README, landing page, repo description) must reinforce it.

The Golden Goal

apfel exposes Apple's on-device FoundationModels LLM. Two things are the product. Two things are byproducts.

Core product (this is what apfel IS)

  1. UNIX tool (apfel "prompt", echo "text" | apfel, apfel --stream)

    • Pipe-friendly, composable, correct exit codes
    • Works with jq, xargs, shell scripts
    • --json output for machine consumption
    • Respects NO_COLOR, --quiet, stdin detection

  2. OpenAI API-compatible HTTP server (apfel --serve)

    • Drop-in replacement for openai.OpenAI(base_url="http://localhost:11434/v1")
    • /v1/chat/completions (streaming + non-streaming)
    • /v1/models, /health, tool calling, response_format
    • Honest 501s for unsupported features (embeddings, legacy completions)
    • CORS for browser clients

These two modes are what the README.md leads with. Every design decision, test, and release gate is scored against them first.

Byproducts (useful, but not the pitch)

  1. Interactive mini TUI chat (apfel --chat) - a byproduct for quick testing, not a main product.

    • Ships because the pieces are already there (Session, ContextManager, tool calling)
    • Handy for quick testing a prompt or a local MCP server without writing a client
    • Should not dominate README real-estate; a short Quick Start entry is enough
    • For a GUI chat app, point users to apfel-chat (separate repo)

  2. Swift library (import ApfelCore, first shipped in 1.1.0) - a goal, but a secondary surface.

    • Pure, FoundationModels-free Swift Package library product
    • OpenAI-compatible request/response types, validation, tool-call handling, schema parsing, MCP protocol, error classification, retry logic, context-trimming strategies
    • Downstream apps call FoundationModels themselves - apfel just supplies the types and policies
    • DocC catalog at Sources/Core/ApfelCore.docc/, runnable examples at Examples/, stability contract in STABILITY.md
    • API-breakage guarded in CI via swift package diagnose-api-breaking-changes
    • Must NOT be front-and-center in README.md. One single link to docs/swift-library.md further down the page - no install snippet, no import ApfelCore sample, no types list. All Swift-library README content lives on dedicated docs pages.

Read the full file on GitHub · 388 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. yesterday Changed · -133 tokens per session 3f317fb50a11
  2. 10d ago First seen · 388 lines · 7,076 tokens per session scan A 012b22fedc37

Subscribe to this mod's changes

apfel CLAUDE.md is an instructions file published in the GitHub repository Arthur-Ficial/apfel (6,359 stars, last pushed yesterday), licensed MIT. It adds 6,943 tokens to every session, about $0.0347 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.

Apple SiliconLLMapple-intelligenceclifoundationmodelsmacos
Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens