A command that rebuilds a local HTML setup guide for the toolkit components and MCP servers installed on a machine, then opens it in a browser. MCP servers are connections that let a coding agent use external tools or information.

Use it after installation changes to regenerate and view the current local setup guide.

It keeps the post-install guide aligned with the machine's current setup when components are added or changed. It can also skip opening the browser in headless environments.

setup-guide — Command by sergei-aronsen

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.

agentmods

npx agentmods add commands/sergei-aronsen/claude-code-toolkit/setup-guide

Clone the repo

git clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkit

Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 602 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

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	$0.00024	$0.00602
Opus 5	$0.00012	$0.00301
Sonnet 5	$0.00005	$0.00120
Haiku 4.5	$0.00002	$0.00060

Measured 2d ago against content hash 1506aaf1076c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup-guide scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

The post-install guide is what an end user sees right after running `bash <(curl -sSL .../scripts/install.sh)`. It only lists sections for things they actually installed — but their setup drifts after the first install (

commands/setup-guide.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/setup-guide

Purpose

Regenerate ~/.claude/setup-guide.html (or .claude/setup-guide.html if a project-local copy already exists) from the current state of installed toolkit components + MCP servers, then open it in the default browser.

The post-install guide is what an end user sees right after running bash <(curl -sSL .../scripts/install.sh). It only lists sections for things they actually installed — but their setup drifts after the first install (they enable a new MCP, install claude-memo later, etc.). This command rebuilds the guide so the page reflects the current machine.

Usage

/setup-guide

No arguments. Re-runs the generator and reopens the HTML in the browser. Honour TK_NO_OPEN=1 to skip auto-open in headless contexts.

What you should do

Locate the generator. In priority order:
- ~/.claude/scripts/lib/post-install-guide.sh (installed by update-toolkit)
- <repo>/scripts/lib/post-install-guide.sh (developer mode — running from inside a clone)
Run it. The script auto-detects:
- Components from filesystem probes (~/.claude/CLAUDE.md, ~/.claude/cc-safety-net.json, ~/.claude/statusline-refresh.sh, rtk on PATH, ~/.claude/council/brain.py, ~/.claude/skills/memo-skill/.git, project GEMINI.md/AGENTS.md).
- MCPs from ~/.claude.json .mcpServers keys.
Run with: bash ~/.claude/scripts/lib/post-install-guide.sh. Default output is ~/.claude/setup-guide.html. The script prints the path on success.
Open the output:
- macOS: open <path>
- Linux: xdg-open <path>
If the generator emits templates dir not found, the user is missing the templates/post-install/ payload. Tell them to run /update-toolkit (or bash <(curl -sSL .../scripts/install.sh)) so the templates land under ~/.claude/templates/post-install/.

Output

A short confirmation: which components + which MCPs ended up in the guide, plus the absolute path of the generated HTML file. Do not dump the HTML.

Read the full file on GitHub · 47 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.

2d ago First seen · 47 lines · 24 tokens per session scan A 1506aaf1076c

Subscribe to this mod's changes

setup-guide is a command published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 16d ago), licensed MIT. It adds 24 tokens to every session and 602 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation

setup-guide

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Makes network callslowCapability

How it starts

/setup-guide

Purpose

Usage

What you should do

Output

What this file has done since we first saw it

Other commands, from other repositories

auto-browse

research-perplexity

webapp-testing

review

graphify

laravel-playwright