Agmente: Agent for Claude Code

.github/agents/Beast.agent.md

Beast is an agent for Claude Code from rebornix/Agmente. It costs 15 tokens per session (667 once invoked), scanned B, original, MIT.

An iOS development agent for the Agmente app, connected to a VS Code terminal and Xcode tools. iOS is Apple's operating system for iPhone and iPad.

In plain words
What is it for?
Use it for Agmente iOS development, including terminal work, Xcode integration, background server checks, and safe retrieval of process logs.
Why use it?
It provides project-specific guidance for running commands and handling background processes without disrupting development servers.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions Gemini CLI.

This is rebornix/Agmente's own configuration. It tells Claude Code how to work on Agmente 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 Agmente configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rebornix/Agmente. 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/rebornix/Agmente/main/.github/agents/Beast.agent.md
Clone the repo
git clone --depth 1 https://github.com/rebornix/Agmente

Made for: Claude Code.

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 Beast

README.md
[![agentmods](https://agentmods.dev/badge/agents/rebornix/agmente/beast/github.svg)](https://agentmods.dev/agents/rebornix/agmente/beast)
Your own site
<a href="https://agentmods.dev/agents/rebornix/agmente/beast"><img src="https://agentmods.dev/badge/agents/rebornix/agmente/beast/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Beast

Your own site · 80×15
<a href="https://agentmods.dev/agents/rebornix/agmente/beast"><img src="https://agentmods.dev/badge/agents/rebornix/agmente/beast.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 667 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00015 $0.00667
Opus 5.5 $0.00006 $0.00267
Sonnet 5.5 $0.00003 $0.00133
Haiku 4.5 $0.00002 $0.00067

Measured 2mo ago against content hash af6e197d16af, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

Beast scanned grade B with 1 finding 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 2mo 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- Run any command in the server's terminal context (kills the process)
.github/agents/Beast.agent.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Beast Agent for Agmente Development

You are an expert iOS developer working on the Agmente app. See claude.md for full project documentation.

Critical Rules for VS Code Terminal Usage

These rules apply when using VS Code's run_in_terminal and get_terminal_output tools.

Background Processes

When running long-running processes (servers, watchers):

  1. Start with isBackground: true - Returns immediately with a terminal ID
  2. Track the terminal ID - Note it for later log retrieval
  3. Use get_terminal_output(id) to check logs - Don't run commands in the server's terminal
  4. Use read-only commands in separate terminals - ps aux | grep, lsof -i :PORT

❌ NEVER DO

  • Run any command in the server's terminal context (kills the process)
  • Use sleep commands (can interfere with background processes)
  • Interrupt (Ctrl+C) a running server before cleanup
  • Use pgrep in a way that attaches to the process

✅ ALWAYS DO

# Start server (background)
run_in_terminal(command: "npx ... --port 8765", isBackground: true)
# Returns terminal ID → save it!

# Check logs safely
get_terminal_output(id: "<terminal-id>")

# Check if running (separate terminal, read-only)
ps aux | grep "process-name" | grep -v grep

# Only at cleanup time
pkill -9 -f "process-pattern"

Testing with Xcode Build MCP

  • Use mcp_xcodebuildmcp_build_sim for building - Don't use run_in_terminal with xcodebuild commands
  • Always use describe_ui before tapping (don't guess coordinates from screenshots)
  • Use tap(postDelay: N) instead of separate sleep commands
  • Complete cleanup even on test failure (kill server + uninstall app)

Build Commands

# Build for simulator (preferred)
mcp_xcodebuildmcp_build_sim()

# Build and run on simulator
mcp_xcodebuildmcp_build_run_sim()

# Run tests on simulator
mcp_xcodebuildmcp_test_sim()

Standard Agent Commands

Start agent server:

npx -y @rebornix/stdio-to-ws --persist --grace-period 604800 "npx @google/gemini-cli --experimental-acp" --port 8765

Read the full file on GitHub · 83 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. 2mo ago First seen · 83 lines · 15 tokens per session scan B af6e197d16af

Subscribe to this mod's changes

Beast is an agent published in the GitHub repository rebornix/Agmente (548 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 667 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

ux-flow-auditor

Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app.

CharlesWiltgen/Axiom · 43 tokens

android-performance-specialist

Specialist in Android app performance & diagnostics — app startup (cold/warm/hot, TTID/TTFD, App Startup lib), Baseline Profiles & Macrobenchmark, rendering/jank (frame budgets, slow/frozen frames, JankStats), ANRs (ApplicationExitInfo), memory (LeakCanary, LMK, onTrimMemory), Perfetto/Studio Profiler, Play Vitals…

SteveGJones/ai-first-sdlc-practices · 128 tokens

swiftui-architect

Specialist in modern iOS app architecture with SwiftUI (iOS 26 / Swift 6.2) — the Observation framework (@Observable), MV vs MVVM vs TCA, NavigationStack & deep linking, SwiftData persistence, structured concurrency at the UI boundary, dependency injection & SwiftPM modularization, UIKit interop, and Swift Testing.…

SteveGJones/ai-first-sdlc-practices · 97 tokens

android-kotlin-expert

Android native specialist for Kotlin, Java, Gradle/AGP, the Jetpack libraries, JNI/NDK, OpenGL ES and camera pipelines (Camera2, CameraX, MediaCodec, MediaPipe, ML Kit), and React Native / Expo Modules native bridging. Use when the task touches android/ (.kt, .java, .gradle / .gradle.kts, AndroidManifest.xml…

simiancraft/simiancraft-skills · 276 tokens

crash-classifier-ios

Fast iOS crash classification by type, component, and trigger (Swift/Objective-C).

IvanLutsenko/awac-ai-agent-plugins · 24 tokens

code-reviewer

Senior Android code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, performance. Use for thorough code review before merge.

GuillemRoca/agent-skills-android · 33 tokens