metamedium

metamedium is a skill for Claude Code from team-attention/plugins-for-claude-natives. It costs 136 tokens per session (1,292 once invoked), scanned A, original, MIT.

A planning lens that separates the content of a project from its form—the way the work or message is structured and delivered.

In plain words
What is it for?
Planning projects, reconsidering stuck approaches, comparing manual work with tools, and exploring new formats for creating or delivering results.
Why use it?
It helps when improving the current output is producing smaller gains, by prompting you to consider changing the process or format instead.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the clarify plugin — 3 skills shipped together

Good fit Planning projects, reconsidering stuck approaches, comparing manual work with tools, and exploring new formats for creating or delivering results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/team-attention/plugins-for-claude-natives/metamedium
Install

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.

Any agent
npx skills add team-attention/plugins-for-claude-natives --skill metamedium
Clone the repo
git clone --depth 1 https://github.com/team-attention/plugins-for-claude-natives

Made for: Claude Code.

Or install clarify, the plugin that ships this one along with the rest of its 3 skills.

Wrote 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.

agentmods badge for metamedium

README.md
[![agentmods](https://agentmods.dev/badge/skills/team-attention/plugins-for-claude-natives/metamedium/github.svg)](https://agentmods.dev/skills/team-attention/plugins-for-claude-natives/metamedium)
Your own site
<a href="https://agentmods.dev/skills/team-attention/plugins-for-claude-natives/metamedium"><img src="https://agentmods.dev/badge/skills/team-attention/plugins-for-claude-natives/metamedium/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.

agentmods 80×15 button for metamedium

Your own site · 80×15
<a href="https://agentmods.dev/skills/team-attention/plugins-for-claude-natives/metamedium"><img src="https://agentmods.dev/badge/skills/team-attention/plugins-for-claude-natives/metamedium.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,292 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00136 $0.01292
Opus 5 $0.00068 $0.00646
Sonnet 5 $0.00027 $0.00258
Haiku 4.5 $0.00014 $0.00129

Measured 12d ago against content hash 6bbee094d9ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

metamedium 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 12d 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.

plugins/clarify/skills/metamedium/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Metamedium: Content vs Form Lens

Distinguish content (what is being said/built) from form (the medium/structure it's delivered through) to surface whether the real leverage is in optimizing content or inventing a new form. Based on Alan Kay's metamedium concept.

"A change of perspective is worth 80 IQ points." — Alan Kay

Core Concept

Most people only change content — what they say, write, or build. The real leverage comes from changing form — the medium, format, or structure itself.

Content (what) Form (how/medium)
Example Writing a LinkedIn post Building a tool that generates posts from client work
Example Writing unit tests manually Building a test generator from type signatures
Example Giving a workshop Inventing a format where attendees co-create artifacts
Leverage Linear — each piece is one output Exponential — each new form enables infinite content

When to Use

  • Planning a project and unsure whether to optimize the output or the process
  • Stuck optimizing content with diminishing returns
  • Building something and want to check if form-level change would yield more leverage
  • Evaluating whether "more of the same" or "something structurally different" is the right move

For requirement clarification, use the vague skill. For strategy blind spot analysis, use the unknown skill.

Protocol

ALWAYS use the AskUserQuestion tool for the fork question in Phase 2 — never ask content/form choices in plain text.

Phase 1: Identify and Label

Read the user's current work, plan, or task. Classify each component as content or form:

[CONTENT] Writing a blog post about AI consulting
[FORM]    Building a pipeline that turns consulting retros into blog posts
[CONTENT] Deploying a new API endpoint
[FORM]    Building a codegen that auto-generates endpoints from schemas
[CONTENT] Fixing a flaky test
[FORM]    Building a test infrastructure that prevents flaky tests by design

Read the full file on GitHub · 134 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 12d ago First seen · 134 lines · 136 tokens per session scan A 6bbee094d9ae

Subscribe to this mod's changes

metamedium is a skill published in the GitHub repository team-attention/plugins-for-claude-natives (824 stars, last pushed 4mo ago), licensed MIT. It adds 136 tokens to every session and 1,292 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens