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.
curl -O https://raw.githubusercontent.com/loqwai/paper-cranes/main/.claude/skills/show/SKILL.mdgit clone --depth 1 https://github.com/loqwai/paper-cranesWrote 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/loqwai/paper-cranes/show)<a href="https://agentmods.dev/skills/loqwai/paper-cranes/show"><img src="https://agentmods.dev/badge/skills/loqwai/paper-cranes/show/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/loqwai/paper-cranes/show"><img src="https://agentmods.dev/badge/skills/loqwai/paper-cranes/show.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 | $0.00092 | $0.02191 |
| Opus 5.5 | $0.00037 | $0.00876 |
| Sonnet 5.5 | $0.00018 | $0.00438 |
| Haiku 4.5 | $0.00009 | $0.00219 |
Grade B, and why
show scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
tail -n 0 -F .claude/vj-signals.jsonl | grep -E --line-buffered '"type":"(clip|too-dark|shiver|boot)"|"type":"flicker","flicker":([2-9]|[1-9][0-9])' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w '%{http_code}\n' "http://localhost:$P/" How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
show: show-day launcher
This skill gets the wall up correctly and quickly. The runbook, knob map, story table, fork library and failure fixes live in docs/show-playbook.md. Read it once, and use it for anything this skill doesn't cover. Brief every agent you start with docs/vj-preferences.md.
Arguments
- No args: the live line,
shader=claude/wip/black-sun/sun-1+controller=black-sun. <shader-path>: for a fork,sun/Npairs withcontroller=sun-N, andsun/1pairs withcontroller=sun. For any other shader, add&controller=only if a matchingcontrollers/*.jsexists.audio=<label>: appends&audio_device=<label>. Without it, the page uses the OS default input, which should be BlackHole 2ch. Don't passaudio_deviceotherwise.check: run step 1 only, then stop.panic <fork>: run the Panic section only.
1. Preflight: run these, then print a ✅/❌ table
P=$(./scripts/dev-port); echo "port $P"
curl -s -o /dev/null -w '%{http_code}\n' "http://localhost:$P/"
lsof -a -p "$(lsof -nP -iTCP:$P -sTCP:LISTEN -t | head -1)" -d cwd -Fn | tail -1 # which checkout serves the wall
git branch --show-current; git fetch -q origin && git status -sb | head -1
grep -n "'\*\*/controllers/\*\*'" vite.config.js && grep -n "chokidar.watch('controllers'" vite-plugins/editor-sync-plugin.js
node scripts/vj/show.js displays
system_profiler SPAudioDataType | grep -i -A2 'BlackHole'
| Check | ✅ when |
|---|---|
| Dev server | HTTP 200. If not, start npm run dev in a background Bash, then recheck. |
| Server checkout | The cwd is the checkout you'll edit. Edits in any other checkout never reach the wall (2026-10-09: the server ran from the main checkout while edits went to peter-show). |
| Branch | peter-show and not behind. If behind, ask before running git pull --ff-only. |
| No-reload controller fix (PR #144) | Both greps hit: vite.config.js ignores **/controllers/**, and editor-sync-plugin.js runs its own chokidar.watch('controllers') |
| Projector | displays lists more than the built-in panel. launch uses the last display, so confirm with the user if there's only one. |
| BlackHole present | It appears in the audio device list. It's verified as the active input after launch in step 3. |
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.
- 2d ago Changed · +21 lines ddf20ea785bc
- 5d ago First seen · 129 lines · 92 tokens per session scan B 81fd0e8b085f
show is a skill published in the GitHub repository loqwai/paper-cranes (7 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 92 tokens to every session and 2,191 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts with the existing agent-browser CLI, including screenshots and keyboard or interaction checks. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser automation.