gum-setup

A guided command for setting up a local gum installation for coding agents.

In plain words
What is it for?
Use it to configure Codex, Claude, Cursor, or Gemini, choose installation scope and targets, preview changes, or apply the setup automatically.
Why use it?
It writes the required agent skills and tool configuration, while providing the commands needed to complete Google sign-in and check the setup.

Command

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/ehmo/gum/gum-setup
Clone the repo
git clone --depth 1 https://github.com/ehmo/gum
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 411 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00411
Opus 5 $0.00000 $0.00205
Sonnet 5 $0.00000 $0.00082
Haiku 4.5 $0.00000 $0.00041

Measured 2d ago against content hash 589a8c05205d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gum-setup 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 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.

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.

docs/commands/gum-setup.md · 38 lines

What it actually says

gum setup

Generated from gum schema --json. Do not edit this page by hand; run make docs-commands.

Guided setup for a local gum install. It writes agent skills and MCP config for Codex, Claude, Cursor, or Gemini, then prints the Google OAuth and doctor commands needed for first success.

Usage

gum setup [flags]

Parent

Flags

Flag Type Default Help
--dry-run bool false Print the write plan without changing files
--features string skills,mcp Comma-separated features: skills,mcp
--force bool false Overwrite existing skill files and replace managed MCP blocks
--format string text Output format: text|json
--mcp-arg stringArray [] Extra argument appended to the gum mcp command
--scope string user Install scope: user|project
--target string all Agent target: codex|claude|cursor|gemini|all
--toolset string core MCP toolset (core)
--yes bool false Apply without an interactive confirmation
--log-format string json Log format: json|text
--log-level string info Log level: debug|info|warn|error (overrides GUM_LOG_LEVEL)
--profile string default Profile name to read/write config under

See also

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. 2d ago First seen · 38 lines · 0 tokens per session scan A 589a8c05205d

Subscribe to this mod's changes

gum-setup is a command published in the GitHub repository ehmo/gum (32 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 411 tokens. 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.