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-creategit 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-create)<a href="https://agentmods.dev/skills/volchunovich/gum/gum-create"><img src="https://agentmods.dev/badge/skills/volchunovich/gum/gum-create/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-create"><img src="https://agentmods.dev/badge/skills/volchunovich/gum/gum-create.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 | $0.00014 | $0.02747 |
| Opus 5 | $0.00007 | $0.01373 |
| Sonnet 5 | $0.00003 | $0.00549 |
| Haiku 4.5 | $0.00001 | $0.00275 |
Grade A, and why
gum-create 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 9d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create GUM Module
This skill creates a new GUM module from scratch. You guide the user through naming, describing, and defining behaviors -- then you generate all files, register the module, and sync hooks. When you finish, the module is live and enforced immediately.
Announce at start: "I'm using the gum-create skill to build a new GUM module."
Checklist
IMMEDIATELY on skill load — before asking ANY question or producing ANY output other than the announcement — create a TaskCreate for EACH of these items:
- Ask module name — one question, wait for answer
- Ask description — one-line summary of what the module does
- Gather behaviors — ask user to describe all rules/behaviors they want
- Classify each behavior — mechanical (→ hook) or judgment-based (→ rule)
- Confirm classification — present the split to user, get approval
- Generate module files — module.yaml, rules.md, hooks.json
- Sync — run
npx get-gum syncvia Bash to register module and sync rules/hooks - Confirm active — show the user their module is live
Mark each task as completed as you finish it. Do NOT batch — mark done immediately.
The Iron Law
HOOKS OVER RULES FOR MECHANICAL TASKS. ALWAYS.
Rules depend on LLM compliance (~70%). Hooks are system-enforced (100%). If a behavior can be a hook, it MUST be a hook. Never leave guaranteed enforcement on the table.
When to Use
- User says "create a module", "add a GUM module", "new gum rule"
- User wants to codify a recurring instruction into something portable
- User describes behaviors they want enforced across projects
- User wants to automate a pre/post action (lint, format, strip lines)
Use this ESPECIALLY when:
- User keeps repeating the same instruction every session
- User describes something mechanical ("always run X after Y")
- User wants team-wide behavior enforcement
Don't skip when:
- User says "just add it to CLAUDE.md" -- GUM modules are portable, CLAUDE.md is not
- User thinks it's "too small for a module" -- small, focused modules are ideal
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.
- 9d ago First seen · 264 lines · 14 tokens per session scan A d3325f3256e7
gum-create is a skill published in the GitHub repository Volchunovich/gum (5 stars, last pushed 6d ago), licensed MIT. It adds 14 tokens to every session and 2,747 once invoked, about $0.0001 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…