SimView AGENTS.md

Repository instructions for SimView, a Bun workspace with a web preview, command-line tool, MCP server, and native Swift simulator backend.

In plain words
What is it for?
Building, testing, and developing SimView packages, its Swift backend, MCP tools, command-line interface, and integration tests.
Why use it?
They provide the project layout and development rules needed to change the right package and keep the browser, native code, and communication contracts aligned.

Instructions file for CodexOpenCode

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/toolingtools/simview/agents-md
Clone the repo
git clone --depth 1 https://github.com/ToolingTools/SimView

Made for: Codex, OpenCode.

Per session 3,957 This file is loaded in full into every session.
When invoked 3,957 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 $0.03957 $0.03957
Opus 5 $0.01978 $0.01978
Sonnet 5 $0.00791 $0.00791
Haiku 4.5 $0.00396 $0.00396

Measured yesterday against content hash 0a7c90a2634a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SimView 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 yesterday.

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 · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

These instructions describe the current source tree and release workflow. Keep documentation aligned with the implementation, especially the shared native backend and per-review MCP boundaries.

Project Structure & Module Organization

SimView is a Bun workspace with a native Swift boundary:

  • packages/app: Preact MCP App preview.
  • packages/contracts: browser-safe Zod schemas, inferred wire types, method maps, protocol constants, and MCP/relay payload contracts.
  • packages/client: binary framing, validated method-keyed requests, request deadlines/cancellation, ephemeral process lifecycle, and the race-safe shared per-Simulator daemon registry.
  • packages/core: packaged simview-core resolver.
  • packages/cli: command-line interface.
  • packages/mcp: MCP tools, session state, and authenticated relay.
  • native/SimViewCore: Swift executable, Objective-C accessibility shim, and XCTest suite.
  • tests: Bun integration and protocol tests.
  • scripts: release, plugin, MCPB, and simulator-smoke tooling.
  • docs, plans, skills, and assets: contracts, implementation plans, agent guidance, operational instructions, and branded media.

Keep private selectors, ABI assumptions, and framework paths inside native compatibility modules. Shared wire types and runtime schemas belong in packages/contracts; packages/client owns native framing and process/daemon transport, while MCP-specific review state stays in packages/mcp.

Build, Test, and Development Commands

Use Bun 1.3.14 and commit bun.lock. bun run check:toolchain fails fast when another Bun version is active.

bun install --frozen-lockfile  # Install exact dependencies
bun run build                  # Build app, packages, and release-mode native core
bun run typecheck              # Run TypeScript without emitting files
bun test                       # Run Bun tests
bun run check                  # Typecheck plus Bun and Swift tests
bun run check:format           # Biome, swift-format, and clang-format checks
bun run check:version          # Reject version drift across manifests and native sources
bun run check:release          # Verify maintainer-only binary release acknowledgements
bun run dev:app                # Start the hot-reloading preview
bun run dev:mcp                # Run the MCP server over stdio
bun run doctor                 # Report Xcode, Simulator, capture, and input capabilities

Read the full file on GitHub · 199 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. yesterday First seen · 199 lines · 3,957 tokens per session scan A 0a7c90a2634a

Subscribe to this mod's changes

SimView AGENTS.md is an instructions file published in the GitHub repository ToolingTools/SimView (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 3,957 tokens to every session, about $0.0198 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.