rk-remote-init

rk-remote-init is a skill for Claude Code from Sixz-AI/repo-knowledge. It costs 95 tokens per session (779 once invoked), scanned A, original, MIT.

A setup procedure for synchronizing a local knowledge base through a remote Git repository. Git is a version-control system that can store and transfer changes between machines.

In plain words
What is it for?
Use it to initialize the knowledge-base repository, connect it to a user-provided remote, push the first machine's data, or pull existing data on another machine.
Why use it?
It lets multiple machines share the same indexed project documentation instead of maintaining separate copies. The procedure also warns that the remote repository contains code snippets and should be private.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the repo-knowledge plugin — 9 skills, 2 agents, 1 hook shipped together

Good fit Use it to initialize the knowledge-base repository, connect it to a user-provided remote, push the first machine's data, or pull existing data on another machine.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sixz-ai/repo-knowledge/rk-remote-init
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.

Any agent
npx skills add Sixz-AI/repo-knowledge --skill rk-remote-init
Clone the repo
git clone --depth 1 https://github.com/Sixz-AI/repo-knowledge

Made for: Claude Code.

Or install repo-knowledge, the plugin that ships this one along with the rest of its 9 skills, 2 agents, 1 hook.

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 rk-remote-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/sixz-ai/repo-knowledge/rk-remote-init/github.svg)](https://agentmods.dev/skills/sixz-ai/repo-knowledge/rk-remote-init)
Your own site
<a href="https://agentmods.dev/skills/sixz-ai/repo-knowledge/rk-remote-init"><img src="https://agentmods.dev/badge/skills/sixz-ai/repo-knowledge/rk-remote-init/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 rk-remote-init

Your own site · 80×15
<a href="https://agentmods.dev/skills/sixz-ai/repo-knowledge/rk-remote-init"><img src="https://agentmods.dev/badge/skills/sixz-ai/repo-knowledge/rk-remote-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 779 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00095 $0.00779
Opus 5 $0.00048 $0.00390
Sonnet 5 $0.00019 $0.00156
Haiku 4.5 $0.00010 $0.00078

Measured 10d ago against content hash 0c9ccad8963b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rk-remote-init 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 10d 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.

skills/rk-remote-init/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RK Remote Init — Initialize Remote Sync

Link the local knowledge base to a user-provided remote git repository.

Security warning: The remote repository will contain documentation that includes code snippets from your indexed projects. Always use a private repository.

Input

Step 1: Resolve home directory (cross-platform)

python3 -c "import os; print(os.path.expanduser('~'))"

Store result as {HOME}. Use {HOME}/.repo-knowledge as the base path for all operations.

Step 2: Ensure base directory exists

Use the Write tool to create {HOME}/.repo-knowledge/_registry.md if it does not already exist (this also creates the directory). Content if creating new:

# RepoKnowledge Registry

| Project | Git URL | Last Update | Docs |
|---------|---------|-------------|------|

Step 3: Check if already a git repo

git -C {HOME}/.repo-knowledge rev-parse --git-dir 2>/dev/null && echo "yes" || echo "no"

If not a git repo, initialize:

git -C {HOME}/.repo-knowledge init
git -C {HOME}/.repo-knowledge checkout -b main 2>/dev/null || true

Step 4: Create .gitignore

Use Write tool to create {HOME}/.repo-knowledge/.gitignore:

_repos/
*.tmp

Step 5: Configure remote

git -C {HOME}/.repo-knowledge remote add origin <git-url> 2>/dev/null || \
git -C {HOME}/.repo-knowledge remote set-url origin <git-url>

Step 6: Detect whether remote already has data

git -C {HOME}/.repo-knowledge fetch origin main 2>/dev/null && echo "has_data" || echo "empty"

If remote already has data (subsequent machine setup):

Run the full merge flow from rk-pull (Steps 3–7 of rk-pull) to bring remote knowledge into local before pushing.

Then:

git -C {HOME}/.repo-knowledge push -u origin main

If remote is empty (first machine):

git -C {HOME}/.repo-knowledge add -A
git -C {HOME}/.repo-knowledge commit -m "init: initial knowledge base" --allow-empty
git -C {HOME}/.repo-knowledge push -u origin main

Read the full file on GitHub · 97 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. 10d ago First seen · 97 lines · 95 tokens per session scan A 0c9ccad8963b

Subscribe to this mod's changes

rk-remote-init is a skill published in the GitHub repository Sixz-AI/repo-knowledge (2 stars, last pushed 4mo ago), licensed MIT. It adds 95 tokens to every session and 779 once invoked, about $0.0005 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 skills, from other repositories

procoder

Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…

azrtydxb/procoder · 101 tokens

writing-github-docs

Write the repository's public face — README.md, CONTRIBUTING.md, and the GitHub community health files (SECURITY, CODEOFCONDUCT, LICENSE, issue and pull request templates). Use this when creating or rewriting any of those, when deciding whether a sentence belongs in the README or in CONTRIBUTING, when GitHub's…

WangChangxin0809/repo-agent-harness · 123 tokens

open-pr

A helper for opening a new pull request, which is a request to merge changes from one Git branch into another. It pushes the current branch, chooses the target branch, and prepares a title and description for your confirmation.

dkmqflx/git-workflow-plugin · 126 tokens

worktree-done

A cleanup procedure for removing a Git worktree, returning the main checkout to its base branch, and deleting the related feature branch. A worktree is a separate working directory linked to the same Git repository.

dkmqflx/git-workflow-plugin · 111 tokens

start-branch

A Git workflow for creating and switching to a new branch, which is a separate line of work in a code repository. It chooses a name based on the task and can start from the current position or a named base branch.

dkmqflx/git-workflow-plugin · 145 tokens

branch-done

A Git cleanup workflow for deleting the current feature branch and returning to the project's base branch after a pull request is opened.

dkmqflx/git-workflow-plugin · 100 tokens