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 skills add Volchunovich/gum --skill gum-helpgit clone --depth 1 https://github.com/Volchunovich/gumWrote 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.
[](https://agentmods.dev/skills/volchunovich/gum/gum-help)<a href="https://agentmods.dev/skills/volchunovich/gum/gum-help"><img src="https://agentmods.dev/badge/skills/volchunovich/gum/gum-help/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.
<a href="https://agentmods.dev/skills/volchunovich/gum/gum-help"><img src="https://agentmods.dev/badge/skills/volchunovich/gum/gum-help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00009 | $0.01606 |
| Opus 5 | $0.00005 | $0.00803 |
| Sonnet 5 | $0.00002 | $0.00321 |
| Haiku 4.5 | $0.00001 | $0.00161 |
Grade A, and why
gum-help 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GUM Help
GUM (Globally Unified Modules) -- reusable AI agent behavior bundles that travel with you across projects and runtimes. This is the complete reference for GUM commands, skills, concepts, and workflows.
Quick Start
New to GUM? Here's the 60-second version:
- Install:
npx get-gum@latest - Create your first module:
/gum-createin chat -- the agent walks you through it - Check what's active:
/gum-statusto see your modules and their rules - That's it. Your module is live and enforced immediately.
Core Concepts
Module -- a folder containing rules (for the LLM) and hooks (for the system). One concern per module.
Rules (rules.md) -- judgment-based instructions the agent follows. Compliance is ~70% because the LLM interprets them. Example: "Prefer composition over inheritance."
Hooks (hooks.json) -- mechanical actions the system executes automatically. Compliance is 100% because code enforces them. Example: "Run eslint after every file edit."
The golden rule: If a behavior is mechanical, make it a hook. If it requires judgment, make it a rule. Never leave guaranteed enforcement on the table.
CLI Commands
| Command | Description |
|---|---|
npx get-gum@latest |
Install GUM |
npx get-gum toggle |
Enable/disable modules (interactive) |
npx get-gum toggle --local |
Per-project team overrides (.gum.json) |
npx get-gum toggle --personal |
Per-project personal overrides (.gum.local.json) |
npx get-gum list |
Show all modules and their status |
npx get-gum remove |
Remove a module entirely |
npx get-gum doctor |
Health check -- find broken modules, stale hooks |
npx get-gum doctor --repair |
Auto-fix issues found by doctor |
npx get-gum export <name> |
Export module to shareable .gum.json |
npx get-gum import <file> |
Import module from file or URL |
npx get-gum sync |
Resync all hooks to runtime settings |
npx get-gum update |
Update GUM to latest version |
npx get-gum uninstall |
Remove GUM completely |
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.
- 10d ago First seen · 163 lines · 9 tokens per session scan A 00661db684a3
gum-help is a skill published in the GitHub repository Volchunovich/gum (5 stars, last pushed 7d ago), licensed MIT. It adds 9 tokens to every session and 1,606 once invoked, about $0.0000 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…