add-rtk

by nanocoai 31k MIT Updated Aug 18, 2026
add-rtk skill by nanocoai
Social preview for nanocoai/nanoclaw

add-rtk is an open-source testing skill for Claude Code and compatible agents, published by nanocoai. Its author describes it as: “Install rtk token-compression proxy into agent containers. Routes Bash tool calls through rtk for 60–90% token savings on dev commands (git, cargo, pytest, docker, kubectl, etc.).”. The project has 31k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/nanocoai/nanoclaw ~/.claude/skills/add-rtk`.

What add-rtk does

Install rtk — a CLI proxy delivering 60–90% token savings on common dev commands (git, cargo, pytest, docker, kubectl, etc.) — and wire it transparently into agent containers via the Claude Code `PreToolUse` hook.

Installation

Add add-rtk to your agent with:

git clone https://github.com/nanocoai/nanoclaw ~/.claude/skills/add-rtk

Always review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.

What's inside

The SKILL.md for add-rtk is organised into these sections:

  • What this sets up
  • Integration tests
  • Step 1 — Install rtk on the host
  • Step 2 — Identify the target agent group
  • Step 3 — Mount rtk into the container config
  • Step 4 — Add the PreToolUse hook to settings.json
  • Step 5 — Restart the container
  • Verify
  • Troubleshooting
  • rtk: command not found inside the container
  • Hook not firing
  • Binary won't execute — permission denied

When to use it

Reach for add-rtk when you want testing help from your agent without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.

Strengths

  • Clear MIT license — safe to read and adapt
  • Ships in nanocoai/nanoclaw, an established project with 30,542 GitHub stars
  • Actively maintained (recent commits)

Topics

ai-agentsai-assistantclaude-codeclaude-skillsopenclaw

Frequently asked questions

What does add-rtk do?
Install rtk token-compression proxy into agent containers. Routes Bash tool calls through rtk for 60–90% token savings on dev commands (git, cargo, pytest, docker, kubectl, etc.).
How do I install add-rtk?
Run git clone https://github.com/nanocoai/nanoclaw ~/.claude/skills/add-rtk in your agent, then reload your skills. Review the source at https://github.com/nanocoai/nanoclaw before installing.
Is add-rtk free to use?
Yes. add-rtk is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
Where does add-rtk come from?
add-rtk ships inside nanocoai/nanoclaw, a repository that contains 41 catalogued skills in total. The repository's 30,542 GitHub stars apply to that whole collection, not to this skill on its own.

Related skills

More Testing →

When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.

25k alirezarezvani MIT

Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.

39k wshobson MIT

Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.

39k wshobson MIT

Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.

39k wshobson MIT

Designs chaos experiments, creates failure injection frameworks, and facilitates game day exercises for distributed systems — producing runbooks, experiment manifests, rollback procedures, and post-mortem templates. Use when designing chaos experiments, implementing failure injection frameworks, or conducting game day exercises. Invoke for chaos experiments, resilience testing, blast radius control, game days, antifragile systems, fault injection, Chaos Monkey, Litmus Chaos.

11k Jeffallan MIT