nanoclaw-gws-ea: Skill for Claude Code

.claude/skills/setup-gws-ea/SKILL.md

setup-gws-ea is a skill for Claude Code from taslim/nanoclaw-gws-ea. It costs 68 tokens per session (908 once invoked), scanned A, original, MIT.

An automated setup script for the GWS-EA version of NanoClaw, including configuration, cloud services, dependencies, and initial agents.

In plain words
What is it for?
Use it to install or repeat setup, configure Google Cloud and related services, start the service, and migrate custom agents from a v1 installation.
Why use it?
It gathers the many first-time installation steps into one repeatable setup process and can offer to import data from version 1.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is taslim/nanoclaw-gws-ea's own configuration. It tells Claude Code how to work on nanoclaw-gws-ea 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 nanoclaw-gws-ea configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is git worktree add ../nanoclaw-gws-ea-v2 origin/main.

Reuse

Borrowing it

Nothing to install: this file belongs to taslim/nanoclaw-gws-ea. 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/taslim/nanoclaw-gws-ea/main/.claude/skills/setup-gws-ea/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/taslim/nanoclaw-gws-ea

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 setup-gws-ea

README.md
[![agentmods](https://agentmods.dev/badge/skills/taslim/nanoclaw-gws-ea/setup-gws-ea/github.svg)](https://agentmods.dev/skills/taslim/nanoclaw-gws-ea/setup-gws-ea)
Your own site
<a href="https://agentmods.dev/skills/taslim/nanoclaw-gws-ea/setup-gws-ea"><img src="https://agentmods.dev/badge/skills/taslim/nanoclaw-gws-ea/setup-gws-ea/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 setup-gws-ea

Your own site · 80×15
<a href="https://agentmods.dev/skills/taslim/nanoclaw-gws-ea/setup-gws-ea"><img src="https://agentmods.dev/badge/skills/taslim/nanoclaw-gws-ea/setup-gws-ea.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 908 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 $0.00068 $0.00908
Opus 5 $0.00034 $0.00454
Sonnet 5 $0.00014 $0.00182
Haiku 4.5 $0.00007 $0.00091

Measured 12d ago against content hash 1e35671cba41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

setup-gws-ea 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 12d 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/skills/setup-gws-ea/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nanoclaw GWS-EA Setup

Tell the user to run bash setup-gws-ea.sh from the project root. That script handles the full end-to-end setup — .env config, GCP provisioning (project, SA, DWD), deps, container image, OneCLI vault, Claude auth, service, first agent (GChat DM), email channel, heartbeat — and then offers to import data from a v1 install if one is detected. It's idempotent: the bootstrap and init steps re-run safely, and the v1-import prompt is asked every run (decline to skip).

The fork ships v2 on main, so a fresh install is just:

git clone https://github.com/taslim/nanoclaw-gws-ea.git
cd nanoclaw-gws-ea
bash setup-gws-ea.sh

Importing from v1

Existing v1 users keep their old checkout running and build v2 in a sibling worktree. Don't git pull v2 onto the v1 checkout — that mixes v1 data with v2 code (the script detects this and refuses).

cd ~/Projects/nanoclaw-gws-ea
git fetch origin
git worktree add ../nanoclaw-gws-ea-v2 origin/main
cd ../nanoclaw-gws-ea-v2
bash setup-gws-ea.sh

The script bootstraps v2, runs the canonical init scripts (main, email, heartbeat), then — once v2 is wired end-to-end — asks whether to import v1's custom agents and active scheduled tasks on top. Answer yes to copy them over, lift matters, and swap launchd from v1 to v2. Answer no to leave v1 alone and keep both running independently.

Override the v1 location with --v1-path PATH or NANOCLAW_V1_PATH=PATH if your layout differs.

Non-interactive flags

  • --migrate — auto-yes to the v1-import prompt (CI / scripted use)
  • --no-migrate — auto-no (keep v1 alone, just bootstrap + init v2)

There is no separate "fresh" / "reconfigure" mode — re-running is always safe. If init partially completed in a prior failed run, the next run picks up where it left off.

Reinstall and uninstall

For a destructive reset, use these instead of running setup-gws-ea repeatedly:

bash setup-gws-ea.sh --reinstall    # wipe v2 state, then re-run setup. Preserves .env, plist, GCP.
bash setup-uninstall.sh             # tear down v2 entirely. GCP resources retained.
bash setup-uninstall.sh --gcp       # also delete GCP project (separate confirmation).

Read the full file on GitHub · 62 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. 12d ago First seen · 62 lines · 68 tokens per session scan A 1e35671cba41

Subscribe to this mod's changes

setup-gws-ea is a skill published in the GitHub repository taslim/nanoclaw-gws-ea (11 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 908 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens