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 instructions/justinthevoid/xcforge/claude-mdgit clone --depth 1 https://github.com/justinthevoid/xcforgeWhat 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 | $0.01033 | $0.01033 |
| Opus 5 | $0.00517 | $0.00517 |
| Sonnet 5 | $0.00207 | $0.00207 |
| Haiku 4.5 | $0.00103 | $0.00103 |
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.
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) orlong: true(MCP) to use 1800s. - Pass
--diagnose/diagnose: trueto capture a diagnostic snapshot even on success. - On timeout, the result includes a
/tmp/xcf-diag-<pid>-<ts>.txtpath and a summary line. build_simandbuild_run_simshare 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 toolsXCForgeCLI— 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.
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.
- 2d ago First seen · 85 lines · 1,033 tokens per session scan A d382cc15ee25
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.
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.
swift-architecture-skill CLAUDE.md
Instructions for efremidze/swift-architecture-skill, covering swift architecture skill, project structure, how the skill works and key conventions.
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.
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.
xtool CLAUDE.md
Instructions for 2389-research/xtool, covering xtool plugin, skills included, using-xtool (main skill), key patterns and xtool is not xcodegen.
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.