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/rayfernando1337/minimal-realtime-kit/agents-mdgit clone --depth 1 https://github.com/RayFernando1337/minimal-realtime-kitWrote 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.
[](https://agentmods.dev/instructions/rayfernando1337/minimal-realtime-kit/agents-md)<a href="https://agentmods.dev/instructions/rayfernando1337/minimal-realtime-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/rayfernando1337/minimal-realtime-kit/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01871 | $0.01871 |
| Opus 5 | $0.00936 | $0.00936 |
| Sonnet 5 | $0.00374 | $0.00374 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
minimal-realtime-kit 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 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — minimal-realtime-kit
A minimal, bring-your-own-key iOS voice agent: realtime voice + tool calling against the latest OpenAI GPT Realtime API, distilled into a clean, PUBLIC open-source repo. Voice is OpenAI Realtime via AIProxySwift (direct BYO-key mode) over AVFoundation; the mic is always open. Tools render agent-driven cards via a data-only factory; an audio-reactive SpriteKit character embodies the agent.
Read first, in order:
SPEC.md(architecture + invariants N1–N6 + the latest-API truth + decision D1) →PROJECT-PLAN.md(tiers, task cards T0.1…T5.x, the wave table §3, the verify loop §4). Then theresearch/01..07file(s) andsnippets/*your task card cites. This repo is PUBLIC — secret hygiene is non-negotiable (N1).
Canonical project facts (do not drift)
- Project:
MinimalRealtimeKit.xcodeproj· schemeMinimalRealtimeKit· target/productMinimalRealtimeKit. - Bundle id:
com.example.MinimalRealtimeKit(neutral — never acom.rayfernando.*id or any Apple Team ID). - App source dir:
MinimalRealtimeKit/— aPBXFileSystemSynchronizedRootGroup: new files in this folder auto-include in the target. NEVER hand-edit the.pbxproj. (Config templates live inConfig/.) - Deployment target: iOS 26.0. Sim: iPhone 17 Pro (iOS 26.x). An iOS 18 sim cannot install.
- One SPM dependency: AIProxySwift
0.153.0(MIT), productAIProxy. No other third-party deps. - Default actor isolation is MainActor (
SWIFT_DEFAULT_ACTOR_ISOLATION = MainActor,SWIFT_APPROACHABLE_CONCURRENCY = YES, Swift language mode 5.0). The realtime networking layer is the@AIProxyActorglobal actor; mark its membersnonisolatedwhere they cross to the stream.
Build / Run / Verify
Use the XcodeBuildMCP tools (preferred) or xcodebuild. Build Debug AND Release for every change
(Release proves nothing leaked outside #if DEBUG). There is no test target and no CI — the
build + sim-screenshot + grep loop below is the only safety net; the live realtime loop cannot be
driven headlessly (no live key/backend in QA), so verify the realtime invariants by code audit.
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.
- 5d ago First seen · 96 lines · 1,871 tokens per session scan A 07a2a8548924
minimal-realtime-kit AGENTS.md is an instructions file published in the GitHub repository RayFernando1337/minimal-realtime-kit (20 stars, last pushed 2mo ago), licensed MIT. It adds 1,871 tokens to every session, about $0.0094 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.
Other instructions, from other repositories
MobiAI-Core CLAUDE.md
Claude Code instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.
freetube CLAUDE.md
Instructions for leshkodev/freetube, covering claude.md, 1. what this project is, 2. non-negotiable constraints, 3. tech stack (locked) and 4. project structure.
ConsultMe CLAUDE.md
Claude Code instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
dev-challenge CLAUDE.md
Claude Code instructions for micheltlutz/dev-challenge, covering claude.md, the one rule to internalise, slash commands, subagents and skills.
android-media-pack CLAUDE.md
Instructions for sunnat629/android-media-pack, covering claude.md, what this repository is, commands, markdown lint (config in .markdownlint-cli2.jsonc) and shell script lint.