What is claude-teleport CLAUDE.md?

A guide to a Claude Code plugin that synchronizes a complete Claude Code setup between computers through a private GitHub repository. It separates conversational instructions from a command-line program that performs the actual work.

Use it when developing, building, releasing, or troubleshooting the teleport plugin, especially its command-line interface, compiled files, and environment paths.

It explains the boundary between the readable plugin instructions and the tested engine, and prevents releases from missing the built files users need.

How seilk/claude-teleport configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to seilk/claude-teleport. 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/seilk/claude-teleport/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/seilk/claude-teleport

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/seilk/claude-teleport/claude-md/github.svg)](https://agentmods.dev/instructions/seilk/claude-teleport/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/seilk/claude-teleport/claude-md"><img src="https://agentmods.dev/badge/instructions/seilk/claude-teleport/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/seilk/claude-teleport/claude-md"><img src="https://agentmods.dev/badge/instructions/seilk/claude-teleport/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,287 This file is loaded in full into every session.

When invoked 2,287 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.

Model	Per session	Once invoked
Fable 5.1	$0.02287	$0.02287
Opus 5	$0.01144	$0.01144
Sonnet 5	$0.00457	$0.00457
Haiku 4.5	$0.00229	$0.00229

Measured 9d ago against content hash 5ca043c23084, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-teleport 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 · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Teleport — CLAUDE.md

Claude Code plugin that syncs your entire Claude Code environment across machines using a private GitHub repo as a hub.

Core Design Philosophy: Skills call Engine via CLI

This is the single most important thing to understand about this codebase:

Skill (SKILL.md)
    -> Claude reads it, runs:
       node "${CLAUDE_PLUGIN_ROOT}/dist/cli.js" <subcommand> --flags
    -> CLI outputs JSON to stdout
    -> Claude reads JSON, presents results conversationally

Skills are the conversational layer (markdown in skills/). The TypeScript CLI (src/cli.ts -> dist/cli.js) is the deterministic engine. They are deliberately separate: the engine is testable and pure; the agent layer is human-friendly.

Why dist/ is committed to git

dist/ is NOT in .gitignore. It is committed so the plugin works immediately after /plugin install without requiring npm install or a build step on the user's machine. Always run npm run build and commit dist/ before pushing a release.

CLAUDE_PLUGIN_ROOT

Claude Code injects CLAUDE_PLUGIN_ROOT when executing a plugin skill — it points to the plugin's install directory (e.g., ~/.claude/plugins/cache/claude-teleport/). Skills reference the CLI as: node "${CLAUDE_PLUGIN_ROOT}/dist/cli.js". If unset (local dev), skills fall back to searching ~/.claude/plugins/cache/ for the dir.

Data Transport: Temp Files, Not CLI Args

Large payloads (snapshots, diffs, selections) are passed via temp files, never as args:

node dist/cli.js scan --output /tmp/teleport-scan.json
node dist/cli.js diff --source-file /tmp/a.json --target-file /tmp/b.json --output /tmp/diff.json
node dist/cli.js apply --diff-file /tmp/diff.json --selections-file /tmp/sel.json

Skills use Write to create input files, Bash to invoke the CLI, Read to consume output. Temp files must be cleaned up after use.

Quick Commands

npm run build        # tsc -> dist/
npm test             # node --import tsx --test src/__tests__/**/*.test.ts

Read the full file on GitHub · 179 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.

9d ago First seen · 179 lines · 2,287 tokens per session scan A 5ca043c23084

Subscribe to this mod's changes

claude-teleport CLAUDE.md is an instructions file published in the GitHub repository seilk/claude-teleport (6 stars, last pushed 3mo ago), licensed MIT. It adds 2,287 tokens to every session, about $0.0114 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.

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

claude-teleport: Instructions file for Claude Code