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/arclabs-studio/arclineargithub-mcp/claude-mdgit clone --depth 1 https://github.com/arclabs-studio/ARCLinearGitHub-MCPWrote 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/arclabs-studio/arclineargithub-mcp/claude-md)<a href="https://agentmods.dev/instructions/arclabs-studio/arclineargithub-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/arclabs-studio/arclineargithub-mcp/claude-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 | $0.01790 | $0.01790 |
| Opus 5 | $0.00895 | $0.00895 |
| Sonnet 5 | $0.00358 | $0.00358 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
ARCLinearGitHub-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 3d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — AI Agent Context
Context for Claude Code and other AI agents working in this repository.
Project Overview
ARCLinearGitHub-MCP is a native Swift Model Context Protocol (MCP) server that
bridges Linear (issue tracking) and GitHub (repository management) for ARC Labs
Studio workflows. Built on modelcontextprotocol/swift-sdk, it exposes 21 tools
that mirror the original Python implementation byte-for-byte, so any Claude Code
configuration that pointed at the Python arc-mcp can switch to the Swift
binary by only changing the command path.
Key principle: the server is multi-tenant. It works with any Linear project
and any GitHub repository in your org. Defaults come from DEFAULT_PROJECT and
DEFAULT_REPO but every tool accepts an explicit override.
Tech Stack
| Component | Technology |
|---|---|
| Language | Swift 6.0 (.v6 language mode, strict concurrency) |
| Package manager | Swift Package Manager (multi-target) |
| MCP framework | modelcontextprotocol/swift-sdk 0.12.x |
| Linear API | Hand-rolled GraphQL over URLSession + Codable |
| GitHub API | Hand-rolled REST over URLSession + Codable |
| Logging | swift-log |
| Tests | Swift Testing |
| Docs | DocC (Sources/ARCMCPCore/Documentation.docc) |
Repository Layout
ARCLinearGitHub-MCP/
├── Package.swift
├── Makefile lint / format / build / test / docs / run
├── README.md
├── CHANGELOG.md
├── CLAUDE.md (this file)
├── ASC.md
├── .swiftlint.yml from ARCDevTools
├── .swiftformat from ARCDevTools
├── .spi.yml Swift Package Index manifest
├── .github/workflows/
│ ├── enforce-gitflow.yml
│ ├── tests.yml
│ └── docs.yml dormant until repo goes public
├── Sources/
│ ├── ARCMCPModels/ Codable Sendable entities + errors
│ ├── ARCMCPNetworking/ HTTPClient actor + RetryPolicy
│ ├── ARCMCPValidators/ Branch + commit validators (pure)
│ ├── ARCMCPLinear/ GraphQL client + WorkspaceRegistry
│ ├── ARCMCPGitHub/ REST client + Endpoint enum
│ ├── ARCMCPCore/ AppDependencies + MCP tool registry
│ ├── ARCMCPMocks/ StubURLProtocol + AppDependencies.mock
│ └── arc-mcp/ @main stdio executable
└── Tests/ one test target per source library
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.
- 3d ago First seen · 190 lines · 1,790 tokens per session scan A 5dd3877003be
ARCLinearGitHub-MCP CLAUDE.md is an instructions file published in the GitHub repository arclabs-studio/ARCLinearGitHub-MCP (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,790 tokens to every session, about $0.0089 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
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
vscode-gitlens CLAUDE.md
Claude Code instructions for gitkraken/vscode-gitlens, a project described as: Supercharge Git inside VS Code and unlock untapped knowledge within each repository — Visualize code authorship at a glance via Git blame annotations and CodeLens, seamlessly navigate and explore Git repositories, gain valuable insights via…
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.