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.
npx agentmods add commands/ehmo/gum/gum-initgit clone --depth 1 https://github.com/ehmo/gumWhat 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 | $0.00000 | $0.00349 |
| Opus 5 | $0.00000 | $0.00175 |
| Sonnet 5 | $0.00000 | $0.00070 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade B, and why
gum-init scanned grade B 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `--global` | `bool` | false | Patch ~/.claude/settings.json and write ~/GUM.md (instead of project-local; claude-code target only) | What it actually says
gum init
Generated from
gum schema --json. Do not edit this page by hand; runmake docs-commands.
gum init bootstraps GUM for a new user or project. Default behavior is diff-and-prompt: gum init never silently patches a security-sensitive file. Use --target to pick the host (claude-code | claude-desktop | cursor). Use --refresh to regenerate GUM.md only after a gum upgrade.
Usage
gum init [flags]
Parent
Flags
| Flag | Type | Default | Help |
|---|---|---|---|
--global |
bool |
false | Patch ~/.claude/settings.json and write ~/GUM.md (instead of project-local; claude-code target only) |
--refresh |
bool |
false | Rewrite GUM.md only; do not touch the host config or credentials |
--target |
string |
claude-code | MCP host to patch: claude-code | claude-desktop | cursor |
--yes |
bool |
false | Skip interactive confirmation and apply the patch |
--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
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 · 33 lines · 0 tokens per session scan B a40abdc921e0
gum-init 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 349 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
/openspec-apply
Implement an approved OpenSpec change and keep tasks in sync.
/openspec-archive
Archive a deployed OpenSpec change and update specs.
/openspec-proposal
Scaffold a new OpenSpec change and validate strictly.
proposal
name: OpenSpec: Proposal description: Scaffold a new OpenSpec change and validate strictly. category: OpenSpec tags: [openspec, change].
archive
name: OpenSpec: Archive description: Archive a deployed OpenSpec change and update specs. category: OpenSpec tags: [openspec, archive].
apply
name: OpenSpec: Apply description: Implement an approved OpenSpec change and keep tasks in sync. category: OpenSpec tags: [openspec, apply].