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/squaduplabs/agent-ios/agents-mdgit clone --depth 1 https://github.com/squaduplabs/agent-iosWhat 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 | $0.00909 | $0.00909 |
| Opus 5 | $0.00454 | $0.00454 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
agent-ios 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 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Start-here instructions for any AI coding agent working in this repository. This
is the single source of truth; tool-specific files (CLAUDE.md, .cursor/rules,
etc.) just point back here.
Two different jobs - make sure you know which one you are doing:
- Working ON agent-ios (fixing bugs, adding features to this codebase): read on.
- Using agent-ios to drive a simulator (from inside some other project): you want docs/integrations.md and docs/usage.md, not this file.
What this project is
A Swift command-line tool (agent-ios) that drives the iOS Simulator for AI
agents - accessibility snapshots with element refs, taps, gestures, typing,
screenshots. It talks over HTTP to a small in-simulator XCUITest "runner" (an
Xcode project under Runner/) that the CLI builds and launches on demand.
Architecture and rationale are in the README.
Build, run, test
swift build # build the CLI
.build/debug/agent-ios doctor # sanity-check the environment
./scripts/e2e.sh # end-to-end smoke test (needs a booted simulator)
- After changing anything under
Runner/, runagent-ios server restartso the new runner build is used (the CLI otherwise caches it). swift buildmust stay clean with no new warnings.- There is no unit-test suite; verification is the e2e script plus driving a real app in the simulator.
Where to find things
| You need | Look in |
|---|---|
| Architecture and quickstart | README.md |
| Full CLI command reference | docs/usage.md |
| Driving any app (native, SwiftUI, RN, Expo, Flutter) | docs/configuring-your-app.md |
| Wiring agent-ios into AI agents | docs/integrations.md |
| The CLI ↔ runner HTTP contract | docs/protocol.md |
| The agent workflow (snapshot → act → verify) | docs/skill/SKILL.md |
| How to contribute | CONTRIBUTING.md |
| Cutting a release | RELEASING.md |
| Version history | CHANGELOG.md |
| Reporting a vulnerability | SECURITY.md |
| Community expectations | CODE_OF_CONDUCT.md |
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 · 75 lines · 909 tokens per session scan A 6f1eff93c22c
agent-ios AGENTS.md is an instructions file published in the GitHub repository squaduplabs/agent-ios (2 stars, last pushed 1mo ago), licensed MIT. It adds 909 tokens to every session, about $0.0045 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
ios-swiftui-accessibility-techniques CLAUDE.md
Instructions for cvs-health/ios-swiftui-accessibility-techniques, covering project rules, copyright header (required), rules, swift files and markdown files.
AppBootstrapAI CLAUDE.md
Instructions for kelvinkosbab/AppBootstrapAI, covering claude.md, project overview, what's in the box, how to onboard this into a new app project and update an already-managed repo — never a plain re-install.
AppBootstrapAI AGENTS.md
Instructions for kelvinkosbab/AppBootstrapAI, covering agents.md — operating appbootstrapai, golden path — do this, the three situations recommend resolves, what recommend keys on (framework → feature category) and scaffolding a local swift package (separate tool).
Pepper CLAUDE.md
Instructions for skwallace36/Pepper, covering pepper, mcp tools, conventions, writing docs and work tracking.
flutter-design-engineer AGENTS.md
Instructions for musabekisakov-imj/flutter-design-engineer, a project described as: Agent skills for product-aware, adaptive, accessible, and visually verified Flutter UI design engineering.
sim-use CLAUDE.md
Instructions for lycorp-jp/sim-use, a project described as: Give your AI agent eyes and hands on iOS Simulator and Android emulator/devices.