swift-index: Instructions file for Codex

AGENTS.md

swift-index AGENTS.md is an instructions file for Codex, OpenCode from alexey1312/swift-index. It costs 5,281 tokens per session, scanned A, original, MIT.

Project instructions for swift-index, a local code-search tool and MCP server for Swift codebases. Swift is Apple's programming language; the project combines keyword and meaning-based search and is intended for Apple Silicon Macs.

In plain words
What is it for?
Use them when building, testing, linting, formatting, initializing, indexing, or searching a Swift project with swift-index.
Why use it?
They give an agent the project-specific build, test, formatting, initialization, indexing, and search commands needed to work on the codebase consistently.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is alexey1312/swift-index's own configuration. It tells Codex and OpenCode how to work on swift-index 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 swift-index configures →

Reuse

Borrowing it

Nothing to install: this file belongs to alexey1312/swift-index. 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/alexey1312/swift-index/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/alexey1312/swift-index

Made for: Codex, OpenCode.

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 swift-index AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alexey1312/swift-index/agents-md.svg)](https://agentmods.dev/instructions/alexey1312/swift-index/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/alexey1312/swift-index/agents-md"><img src="https://agentmods.dev/badge/instructions/alexey1312/swift-index/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,281 This file is loaded in full into every session.
When invoked 5,281 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 $0.05281 $0.05281
Opus 5 $0.02641 $0.02641
Sonnet 5 $0.01056 $0.01056
Haiku 4.5 $0.00528 $0.00528

Measured 4d ago against content hash 4490d92ee132, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

swift-index AGENTS.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 4d 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.

AGENTS.md · 479 lines

How it starts

The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SwiftIndex - Project Guide

Overview

  • Purpose: Semantic code search engine for Swift codebases
  • CLI tool + MCP server for AI assistants
  • Hybrid search: BM25 + semantic + RRF fusion
  • Privacy-first: local embeddings by default
  • Platform: Apple Silicon (ARM) only — Intel not supported
  • Terminal UI: Use Noora components for CLI progress, spinners, and status steps (avoid custom print-based animations)

Note: CLAUDE.md is a symlink to AGENTS.md — editing either file modifies both.

Quick Reference

Build & Test Commands

Command Description
./bin/mise run build Debug build
./bin/mise run build:release Release build (no WMO) + MLX metallib
./bin/mise run test Run all tests
./bin/mise run test:filter <name> Run filtered tests
./bin/mise run lint Run linters
./bin/mise run format Format all code

CLI Commands

Command Description
swiftindex init Initialize config (required first step)
swiftindex index [PATH] Index a codebase
swiftindex search <QUERY> Search indexed code
swiftindex search-docs <QUERY> Search documentation snippets
swiftindex parse-tree [PATH] Visualize Swift AST structure
swiftindex watch [PATH] Watch mode (incremental)
swiftindex serve Start MCP server
swiftindex providers List embedding providers
swiftindex auth status Check OAuth token status
swiftindex auth login Set up Claude Code OAuth token
swiftindex auth logout Remove OAuth token from Keychain
swiftindex status Show config, index and freshness status
swiftindex install Configure all detected AI agents
swiftindex parse-tree <PATH> Visualize Swift AST structure

Read the full file on GitHub · 479 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. 4d ago Changed · +8 lines · +178 tokens per session 4490d92ee132
  2. 8d ago First seen · 471 lines · 5,103 tokens per session scan A 42cacb953e32

Subscribe to this mod's changes

swift-index AGENTS.md is an instructions file published in the GitHub repository alexey1312/swift-index (5 stars, last pushed 5d ago), licensed MIT. It adds 5,281 tokens to every session, about $0.0264 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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens