paper-cranes: Skill for Claude Code

.claude/skills/fork/SKILL.md

fork is a skill for Claude Code from loqwai/paper-cranes. It costs 34 tokens per session (871 once invoked), scanned A, original, BSD-3-Clause.

A command that saves the current browser shader and its knob settings as a new numbered shader file, with a companion Markdown document. A shader is code that generates visual effects.

In plain words
What is it for?
Use it while experimenting in the shader editor to capture the current code, controls, and settings as a new iteration.
Why use it?
It preserves an experimental visual state as a separate iteration instead of overwriting the current work. This makes it easier to keep and compare versions of a shader.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is loqwai/paper-cranes's own configuration. It tells Claude Code how to work on paper-cranes itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything paper-cranes configures →

Reuse

Borrowing it

Nothing to install: this file belongs to loqwai/paper-cranes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/loqwai/paper-cranes/main/.claude/skills/fork/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/loqwai/paper-cranes

Made for: Claude Code.

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 fork

README.md
[![agentmods](https://agentmods.dev/badge/skills/loqwai/paper-cranes/fork/github.svg)](https://agentmods.dev/skills/loqwai/paper-cranes/fork)
Your own site
<a href="https://agentmods.dev/skills/loqwai/paper-cranes/fork"><img src="https://agentmods.dev/badge/skills/loqwai/paper-cranes/fork/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 fork

Your own site · 80×15
<a href="https://agentmods.dev/skills/loqwai/paper-cranes/fork"><img src="https://agentmods.dev/badge/skills/loqwai/paper-cranes/fork.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 871 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.
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 $0.00034 $0.00871
Opus 5.5 $0.00014 $0.00348
Sonnet 5.5 $0.00007 $0.00174
Haiku 4.5 $0.00003 $0.00087

Measured 5d ago against content hash 4189a1c6b91a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fork 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 5d 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.

.claude/skills/fork/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fork — Save Current State as New Shader Iteration

Capture the current shader code + knob values from the browser and create a new numbered .frag file with the knob values baked into comments and a companion .md doc.

Context

Arguments (optional shader path): !echo "$ARGUMENTS"

Browser tabs: !echo "Use tabs_context_mcp + javascript_tool to read current state"

Steps

1. Find the current shader

If $ARGUMENTS specifies a path, use it. Otherwise:

  1. Check the browser — read window.location.search for ?shader=
  2. Fall back to most recently modified .frag in the worktree

2. Read the current state from the browser

On the jam/editor tab, run:

JSON.stringify({
  shader: new URLSearchParams(window.location.search).get('shader'),
  controller: new URLSearchParams(window.location.search).get('controller'),
  knobs: Object.fromEntries(
    Object.entries(window.cranes.manualFeatures || {})
      .filter(([k]) => /^knob_\d+$/.test(k))
      .filter(([_, v]) => v !== undefined && v !== null)
      .sort(([a],[b]) => parseInt(a.split('_')[1]) - parseInt(b.split('_')[1]))
  )
})

3. Determine the new filename

Look at existing numbered files in the shader directory:

shaders/<path>/the-coat-2.frag
shaders/<path>/the-coat-3.frag
→ next: the-coat-4.frag

If no numbered files exist, use 2.frag as the first fork.

4. Copy the shader

Copy the current .frag to the new filename. Update any internal comments that reference the old name.

  • Copy the controller too. If the shader reads controller uniforms, copy controllers/<name>.js to a frozen snapshot such as controllers/<name>-<N>.js. Otherwise the fork changes whenever the live controller does.
  • Add a preset line right after the leading // @ metadata (and after #version if present). It must carry every query param the fork needs: controller, wavelet=true if wavelets are used, and any knobs that matter. The list page extracts http(s) URLs from comments as presets and applies their params: // preset: https://visuals.beadfamous.com/?shader=<path>&controller=<snapshot>&wavelet=true

Read the full file on GitHub · 99 lines

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. 5d ago Changed · +9 lines 4189a1c6b91a
  2. 11d ago First seen · 90 lines · 34 tokens per session scan A 26a81ad859c1

Subscribe to this mod's changes

fork is a skill published in the GitHub repository loqwai/paper-cranes (7 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 34 tokens to every session and 871 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-02.

Related

Other skills, from other repositories

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

systematic-debugging

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

obra/superpowers · 21 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