iosef CLAUDE.md

iosef CLAUDE.md is an instructions file for coding agents from riwsky/iosef. It costs 376 tokens per session, scanned A, original, MIT.

Project instructions for iosef, a Swift command-line tool for controlling the iOS Simulator with support for agent tool calls.

In plain words
What is it for?
Use them when changing simulator features or interfaces, comparing local implementations with related projects, validating iOS or watchOS playground apps, or updating project references.
Why use it?
They provide the project's testing and maintenance rules, including checking playground apps and keeping related skills, benchmarks, documentation, and generated Xcode projects aligned.

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/riwsky/iosef/claude-md
Clone the repo
git clone --depth 1 https://github.com/riwsky/iosef

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 iosef CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/riwsky/iosef/claude-md.svg)](https://agentmods.dev/instructions/riwsky/iosef/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/riwsky/iosef/claude-md"><img src="https://agentmods.dev/badge/instructions/riwsky/iosef/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 376 This file is loaded in full into every session.
When invoked 376 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 $0.00376 $0.00376
Opus 5 $0.00188 $0.00188
Sonnet 5 $0.00075 $0.00075
Haiku 4.5 $0.00038 $0.00038

Measured 5d ago against content hash 297bf5492349, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

iosef 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 5d 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 · 18 lines

What it actually says

iosef

A Swift CLI for the iOS simulator (with MCP server support) that's optimized for agent usage.

Work guidelines

Use local checkout for researching other repositories: You will, reasonably, often want to compare approaches against joshuayoes/ios-simulator-mcp or facebook/idb. Do NOT compare by browsing raw.githubcontent or the github web interface - instead, clone the repos locally. Another useful source of comparison is ldomaradzki/xctree.

Test against the playground apps: the repo also includes two playground apps (one iOS, one watchOS); changes should generally be validated against one or both of those.

Keep references updated: the following locations are pretty cross-cutting, and should be reviewed (especially after changes to the interface) in case they need updating: [ ] The guidance in skills/ios-simulator-interaction [ ] The benchmarking in scripts/benchmark.py [ ] The documentation in the README.md [ ] Playground Xcode projects: the .xcodeprojs are generated by XcodeGen from MCPTestApp/project.yml and WatchTestApp/project.yml (and are gitignored — treat them as build artifacts). Sources are globbed from the app folder, so adding/renaming/removing a .swift file needs no project edits: just run xcodegen generate in the app dir (or scripts/build-test-app.sh, which regenerates automatically). Install the generator once with brew install xcodegen. Edit project.yml only to change build settings, deployment target, or schemes.

Scripts for frequent commands: ls the scripts directory to see commands for building and benchmarking. Consider adding more if you find yourself running any commands pretty often.

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. 5d ago First seen · 18 lines · 376 tokens per session scan A 297bf5492349

Subscribe to this mod's changes

iosef CLAUDE.md is an instructions file published in the GitHub repository riwsky/iosef (18 stars, last pushed 10d ago), licensed MIT. It adds 376 tokens to every session, about $0.0019 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.

Related

Other instructions, from other repositories