specter-mcp: Instructions file for Claude Code

CLAUDE.md

specter-mcp CLAUDE.md is an instructions file for Claude Code from abd3lraouf/specter-mcp. It costs 800 tokens per session, scanned A, original, MIT.

A set of project instructions for Claude Code, an AI coding assistant, in a file named `CLAUDE.md`. These instructions describe how the assistant should communicate and explain the Specter MCP project's context, technology, architecture, and tools.

In plain words
What is it for?
Use it to guide Claude Code when working on Specter MCP, a Kotlin Multiplatform Mobile diagnostic and execution engine for mobile projects.
Why use it?
It gives the assistant the project knowledge and working rules it needs to make more suitable changes and responses.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

This is abd3lraouf/specter-mcp's own configuration. It tells Claude Code how to work on specter-mcp 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 specter-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to abd3lraouf/specter-mcp. 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/abd3lraouf/specter-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/abd3lraouf/specter-mcp

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 specter-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/abd3lraouf/specter-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/abd3lraouf/specter-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/abd3lraouf/specter-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/abd3lraouf/specter-mcp/claude-md/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 specter-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/abd3lraouf/specter-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/abd3lraouf/specter-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 800 This file is loaded in full into every session.
When invoked 800 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00800 $0.00800
Opus 5 $0.00400 $0.00400
Sonnet 5 $0.00160 $0.00160
Haiku 4.5 $0.00080 $0.00080

Measured 9d ago against content hash a45c633617ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

specter-mcp 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 9d 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Project Instructions for Claude

Communication Style

ALWAYS use the AskUserQuestion tool when presenting questions or options to the user. Do not ask questions inline in text responses. The AskUserQuestion tool provides a better UX with structured options.

Project Context

Specter MCP is a KMM (Kotlin Multiplatform Mobile) Diagnostic & Execution Engine that acts as "hands and eyes" for AI agents working with mobile projects.

Tech Stack

  • TypeScript 5.x (Node.js 20+)
  • @modelcontextprotocol/sdk
  • sharp (image processing)
  • xml2js (UI hierarchy parsing)

Architecture

  • Primary Agent + Specialized Worker model
  • Primary agent (Claude Sonnet) handles high-level reasoning
  • Worker models handle specific tasks:
    • Log analysis → Claude Haiku
    • Vision/UI analysis → Vision-capable model
    • Code reasoning → Primary model

Tool Domains

  1. Environment & Build: Device management, cache cleaning, builds
  2. Testing & QA: Unit tests, Maestro E2E, linting
  3. UI & Observability: Screenshots, UI hierarchy, interactions, logs, deep links, app state
  4. iOS Crash Diagnostics: Crash log parsing, symbolication, pattern detection
  5. Model Routing: Task dispatching to specialized AI models
  6. Concurrency & Error Handling: Sequential queue, device discovery, timeouts

Design Decisions

Access & Security

  • No authentication required - Claude AI or users call directly on trusted local machine

Concurrency

  • Queue requests and execute sequentially to prevent resource conflicts (no parallel tool execution)

Error Handling

  • When a requested device/emulator doesn't exist: Return error plus list of available devices for agent to choose
  • If configured worker model (e.g., Claude Haiku) is unavailable: Fallback to primary model, accept higher cost

Timeouts

  • Maximum build timeout: 30 minutes (accommodates complex projects with many dependencies)

iOS Debugging

  • Crash log analysis: Parse .crash/.ips files, symbolicate with dSYM, detect crash patterns
  • Xcode Instruments: Out of scope - focus on functional debugging, not performance profiling

Read the full file on GitHub · 85 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. 9d ago First seen · 85 lines · 800 tokens per session scan A a45c633617ae

Subscribe to this mod's changes

specter-mcp CLAUDE.md is an instructions file published in the GitHub repository abd3lraouf/specter-mcp (1 stars, last pushed 8mo ago), licensed MIT. It adds 800 tokens to every session, about $0.0040 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens