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-optimizegit 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-optimize)<a href="https://agentmods.dev/skills/volchunovich/gum/gum-optimize"><img src="https://agentmods.dev/badge/skills/volchunovich/gum/gum-optimize/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-optimize"><img src="https://agentmods.dev/badge/skills/volchunovich/gum/gum-optimize.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 | $0.00015 | $0.02362 |
| Opus 5 | $0.00008 | $0.01181 |
| Sonnet 5 | $0.00003 | $0.00472 |
| Haiku 4.5 | $0.00002 | $0.00236 |
Grade A, and why
gum-optimize 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize GUM Modules
This skill performs a deep analysis of your ENTIRE agent context -- every GUM module, every CLAUDE.md, every rule file -- and finds problems: bloat, vagueness, conflicts, and missed automation opportunities. This is the LLM-powered audit. It reads everything, diagnoses everything, and offers to fix everything on the spot.
Announce at start: "I'm using the gum-optimize skill to audit your full agent context."
The Iron Law
READ EVERYTHING BEFORE DIAGNOSING ANYTHING.
You MUST read ALL sources before presenting a single finding. Partial reads produce partial (wrong) diagnoses. No shortcuts.
When to Use
- User says "optimize", "audit my rules", "clean up my modules"
- User notices the agent ignoring rules (symptom of context bloat or vagueness)
- User has accumulated many modules and wants a health check
- User migrated from scattered CLAUDE.md rules and wants consolidation
- After installing several new modules
Use this ESPECIALLY when:
- Agent compliance feels low -- rules are being ignored or partially followed
- User has been using GUM for a while and never audited
- Multiple team members have added modules independently
- User says "my context feels bloated" or "the agent seems confused"
Don't skip when:
- User thinks "everything is fine" -- silent conflicts are the worst kind
- User has only a few modules -- even 3 modules can conflict
Process
Phase 1: Read ALL Sources (No Exceptions)
You MUST read every single one of these. Skipping any source means missed findings.
- Run
npx get-gum list --gum-dir ~/.gumvia Bash — get all modules and their status - Run
npx get-gum doctor --gum-dir ~/.gumvia Bash — get context budget and integrity report - Read synced rules from
~/.claude/rules/gum/*.md— these are the active module rules (auto-loaded, no permission needed) - Read project CLAUDE.md from
./CLAUDE.md(if exists) — rules that should be GUM modules - Read user CLAUDE.md from
~/.claude/CLAUDE.md(if exists) — global rules that should be GUM modules - Read project rules from
.claude/rules/*.md(if any) — additional rule files
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 · 212 lines · 15 tokens per session scan A 37399fdcc09a
gum-optimize is a skill published in the GitHub repository Volchunovich/gum (5 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 2,362 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…