xcforge CLAUDE.md

A set of Claude Code instructions for working on the xcforge Swift project, covering its build, tests, architecture, tools, and web-site commands.

In plain words
What is it for?
Guiding work on xcforge, including Swift builds and tests, the MCP server, diagnostics, formatting, and the separate Bun-based website.
Why use it?
It gives the coding agent the repository-specific commands and rules needed to build, test, format, and run the project correctly.

Instructions file

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 instructions/justinthevoid/xcforge/claude-md
Clone the repo
git clone --depth 1 https://github.com/justinthevoid/xcforge
Per session 1,033 This file is loaded in full into every session.
When invoked 1,033 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 $0.01033 $0.01033
Opus 5 $0.00517 $0.00517
Sonnet 5 $0.00207 $0.00207
Haiku 4.5 $0.00103 $0.00103

Measured 2d ago against content hash d382cc15ee25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xcforge 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 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.

CLAUDE.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build & Test Commands

swift build                  # Debug build
swift build -c release       # Release build (~8 MB stripped)
swift test                   # Run all tests
swift test --filter TestName # Run a single test suite
swift run xcforge             # Start MCP server (stdio JSON-RPC)
swift run xcforge build --help # CLI mode

Test timeout defaults (build-test, test run, test_sim, build_and_test):

  • Default timeout: 180s. Pass --long (CLI) or long: true (MCP) to use 1800s.
  • Pass --diagnose / diagnose: true to capture a diagnostic snapshot even on success.
  • On timeout, the result includes a /tmp/xcf-diag-<pid>-<ts>.txt path and a summary line.
  • build_sim and build_run_sim share the same watchdog design; build (build-only) remains at 1800s.

Formatting (CI enforces strict lint):

swift-format format --in-place --recursive Sources/ Tests/  # Fix
swift format lint --strict --recursive Sources/ Tests/       # Check (matches CI)

Web site (separate workspace in Web/, uses Bun — not npm):

cd Web && bun install && bun run build   # Full build with validation
bun run dev                               # Local dev at localhost:4321
bun run lint && bun run format            # Biome lint/format

Architecture

Dual-mode single binary: no args → MCP server (stdio JSON-RPC); with args → CLI (ArgumentParser). Mode detection in Sources/XCForgeCLI/Main.swift.

Two targets (see Package.swift):

  • XCForgeKit — shared library containing all 102+ MCP tools
  • XCForgeCLI — CLI layer wrapping the library with ArgumentParser commands

Tool Provider System

Tools are organized into providers that implement ProviderProtocol and self-register in ProviderRegistry. Each provider owns its tool definitions + dispatch logic. There is no central switch statement.

Key providers in Sources/XCForgeKit/Tools/: BuildProvider, TestProvider, SimulatorProvider, InteractionProvider, LogProvider, DeviceProvider, DebuggerProvider, VisualTools, AccessibilityTools, GitProvider, SwiftPackageProvider, DiagnoseTools, PlanTools, MultiDeviceTools, ConsoleProvider, CaptureProvider.

Read the full file on GitHub · 85 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 · 85 lines · 1,033 tokens per session scan A d382cc15ee25

Subscribe to this mod's changes

xcforge CLAUDE.md is an instructions file published in the GitHub repository justinthevoid/xcforge (1 stars, last pushed 3mo ago), licensed MIT. It adds 1,033 tokens to every session, about $0.0052 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.

Related

Other instructions, from other repositories

MarkdownView AGENTS.md

Instructions for keitaoouchi/MarkdownView, covering agents, technical components, relationships (data/event flow overview), extension points (overview) and platform / distribution.

keitaoouchi/MarkdownView · 722 tokens

swift-architecture-skill CLAUDE.md

Instructions for efremidze/swift-architecture-skill, covering swift architecture skill, project structure, how the skill works and key conventions.

efremidze/swift-architecture-skill · 422 tokens

swift-architecture-skill AGENTS.md

Instructions for efremidze/swift-architecture-skill, covering agents guidelines for swift architecture skill, working with this repository, 1. understanding the skill, 2. modifying architecture playbooks and 3. testing and validation.

efremidze/swift-architecture-skill · 987 tokens

swift-kmp-skill AGENTS.md

Instructions for sorunokoe/swift-kmp-skill, covering agents.md — swift-kmp, what this repository is, repository structure, how to apply this skill and skill loading order.

sorunokoe/swift-kmp-skill · 675 tokens

xtool CLAUDE.md

Instructions for 2389-research/xtool, covering xtool plugin, skills included, using-xtool (main skill), key patterns and xtool is not xcodegen.

2389-research/xtool · 525 tokens

swift-patterns-skill AGENTS.md

Instructions for efremidze/swift-patterns-skill, covering agent guidelines for swift patterns, core principles, 1. swift and swiftui focus, 2. no code formatting or linting and 3. no architectural opinions.

efremidze/swift-patterns-skill · 1,145 tokens