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-plugingit 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 | $0.00475 |
| Opus 5 | $0.00000 | $0.00237 |
| Sonnet 5 | $0.00000 | $0.00095 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
gum-plugin 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.
What it actually says
gum plugin
Generated from
gum schema --json. Do not edit this page by hand; runmake docs-commands.
Manage gum plugins: install, list, run, and curate third-party subprocess plugins. Installing a plugin launches an untrusted subprocess, so 'install' requires --yes to acknowledge that trust boundary. See the subcommands below.
Usage
gum plugin
Parent
Subcommands
- gum plugin install - Installs a plugin through an atomic registry update: validates the manifest,
- gum plugin list - List installed plugins with their quarantine state
- gum plugin reload - Clears any quarantine state for the named plugin, then spawns the subprocess once via the supervisor to act as a passive canary. A spawn failure re-quarantines the plugin.
- gum plugin remove - Remove a plugin by ID
- gum plugin run - Call a tool on a running plugin
- gum plugin setup - Reads the plugin's credential_descriptors from its manifest, prompts for
- gum plugin transfer-namespace - Updates the namespace_owner binding for in the active profile's
- gum plugin unquarantine - Resets quarantined, retry_count, backoff_step, and next_retry_at in plugin-state.json so the plugin can be invoked on the next call. Use when the operator has independently verified the plugin is healthy and wants to bypass the exponential-backoff window.
Flags
| Flag | Type | Default | Help |
|---|---|---|---|
--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 · 42 lines · 0 tokens per session scan A fbc5b0673189
gum-plugin 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 475 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.
Other commands, from other repositories
claude-flow-swarm
Coordinate multi-agent swarms for complex tasks.
bootstrap
PACT session-start ritual — identify the session team (platform-provisioned), secretary spawn, paused-state surface, bootstrap marker.
ox-session-review
Command "ox-session-review" from sageox/ox, covering failure-mode watch-list (read first), from the ledger root. should print 0, phase 1 — scan & score (read-only), quality buckets (first match wins) and removal candidates.
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
handoff
Package current state for the next agent.
drive
Drive a goal to completion over the deterministic firewall — the autonomous goal-driven loop.