agentmods.dev

claude-xcindex: Instructions file for Claude Code

CLAUDE.md

claude-xcindex CLAUDE.md is an instructions file for Claude Code from drewalth/claude-xcindex. It costs 1,438 tokens per session, scanned A, original, MIT.

Repository instructions for a Claude Code plugin that lets the agent look up Swift and Objective-C code by its symbols, using Xcode's index instead of text searches.

In plain words
What is it for?
Building, testing, formatting, and maintaining the plugin and its MCP server, skills, hooks, subagent, and slash command.
Why use it?
They give the agent the repository's architecture, build commands, tests, and contracts so changes do not leave related parts out of sync.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is drewalth/claude-xcindex's own configuration. It tells Claude Code how to work on claude-xcindex 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 claude-xcindex configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 3repo 1mo ago A scan 1,438 tokens original MIT
View source ↗ drewalth/claude-xcindex drewalth.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to drewalth/claude-xcindex. 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/drewalth/claude-xcindex/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/drewalth/claude-xcindex

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 claude-xcindex CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/drewalth/claude-xcindex/claude-md.svg)](https://agentmods.dev/instructions/drewalth/claude-xcindex/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/drewalth/claude-xcindex/claude-md"><img src="https://agentmods.dev/badge/instructions/drewalth/claude-xcindex/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,438 This file is loaded in full into every session.
When invoked 1,438 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 $0.01438 $0.01438
Opus 5 $0.00719 $0.00719
Sonnet 5 $0.00288 $0.00288
Haiku 4.5 $0.00144 $0.00144

Measured 7d ago against content hash 7e472a0b2ff8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claude-xcindex 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 7d 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 · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 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.

What this repo is

A Claude Code plugin that wraps Xcode's pre-built SourceKit symbol index (indexstore-db) as MCP tools so Claude can do semantic Swift/ObjC symbol lookups instead of textual grep. Ships an MCP server, skills, hooks, a subagent, and a slash command. See README.md for user-facing docs.

Build & run

make build                         # release build
make build-debug                   # debug build
make test                          # run tests
make test_ci                       # tests as CI runs them (skips fixtures)
make lint                          # swiftformat --lint .
make format                        # swiftformat .
make help                          # list all targets

cd service && swift test --filter xcindexTests.example   # single test

The Makefile at the repo root is the canonical dev entrypoint and is what CI invokes. Its build target wraps scripts/build.sh, which runs swift build -c release in the service/ directory. Re-run after git pull. The binary Claude Code launches is service/.build/release/xcindex.

Developer scripts live under scripts/ (e.g. scripts/build.sh); they never ship with the plugin. Distributed scripts are in hooks/ and bin/.

Architecture

Single Swift binary. Claude Code spawns service/.build/release/xcindex directly via .mcp.json; the binary speaks MCP over stdio using the official modelcontextprotocol/swift-sdk.

Claude Code ──MCP/stdio──▶ xcindex (Swift) ──▶ IndexStoreDB

The source tree:

  • service/Sources/xcindex/main.swift — starts the MCP Server with a StdioTransport and parks on waitUntilCompleted().
  • service/Sources/xcindex/MCPServer.swift — tool registration (schemas, descriptions) and the CallTool dispatcher that formats text output. All user-visible strings live here.
  • service/Sources/xcindex/RequestProcessor.swift — an actor that caches IndexQuerier instances by store path and routes internal ops.
  • service/Sources/xcindex/Queries.swift — the actual IndexStoreDB queries.
  • service/Sources/xcindex/Freshness.swift — session-edited-file tracking shared with the bash hooks via a state file in $TMPDIR.
  • service/Sources/xcindex/DerivedData.swift — resolves the IndexStore DataStore path from a project path.
  • service/Sources/xcindex/Models.swift — internal wire types used by RequestProcessor (not MCP-visible).

Read the full file on GitHub · 130 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. 7d ago First seen · 130 lines · 1,438 tokens per session scan A 7e472a0b2ff8

Subscribe to this mod's changes

claude-xcindex CLAUDE.md is an instructions file published in the GitHub repository drewalth/claude-xcindex (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,438 tokens to every session, about $0.0072 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.

Claude CodeKotlin and SwiftLanguagesdeveloper-toolsindexstore-dbmcpobjective-csourcekit
Related

Other instructions, from other repositories

plan-forge swiftui.instructions.md

SwiftUI patterns — state management, navigation, async data loading, previews.

srnichols/plan-forge · 1,004 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

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

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

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