MengTo/Skills is a collection of reusable instruction folders that teach coding agents workflows for interface design, games, frontend systems, automations, and agent loops. Designers and developers use the skills to turn references, prompts, and implementation habits into repeatable work. The catalogue contains the project’s skills and supporting instruction.
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 MengTo/Skills --skill paper-cinder-transitiongit clone --depth 1 https://github.com/MengTo/SkillsWrote 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/mengto/skills/paper-cinder-transition)<a href="https://agentmods.dev/skills/mengto/skills/paper-cinder-transition"><img src="https://agentmods.dev/badge/skills/mengto/skills/paper-cinder-transition/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/mengto/skills/paper-cinder-transition"><img src="https://agentmods.dev/badge/skills/mengto/skills/paper-cinder-transition.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 | $0.00167 | $0.03390 |
| Opus 5.5 | $0.00067 | $0.01356 |
| Sonnet 5.5 | $0.00033 | $0.00678 |
| Haiku 4.5 | $0.00017 | $0.00339 |
Grade A, and why
paper-cinder-transition 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 22d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Cinder Transition
A page does not fade into the next one, it is eaten by a line of fire. Reach for
fire-paper-loader when the burn is a ring on a loading screen that must survive a
blocked main thread; reach for this when the burn is the change between two scenes
you own. For text that is written in by a mask rather than burned, use masked-reveal;
for a scroll-scrubbed sequence with no burn, scroll-scrubbed-visual-sequence.
The mechanism
One full-screen pass decides, per pixel, whether it belongs to the frozen old frame (ahead of the line), to the burning zone (the line), or to the live new scene (behind it), from a single signed distance to a noisy front. Everything else is staging. Remove any of the three layers and it stops reading as fire: no frozen frame and the old page keeps moving under the flame, no live scene and the reveal is a still, no pixel-true distance and the edge is a soft blotch.
xc = signed distance to the front in CSS px (+ ahead, - burnt)
reveal = clamp(0.5 - xc/aa, 0, 1) // new frame from the front back, cut to the pixel
col = mix(fromFrozen, toLive, reveal)
col = mix(col, charcoal, bed * pores) // 26 px band of torn, porous char (alpha-masked)
col += flame(xc) + charGlow(xc) // additive: thread, ember zone, tight glow
Staging split
| goes in the skill | staging (yours to change) |
|---|---|
| the composite order, the distance field, the ember ramp, char rules, the noise bake | what the two scenes are, palette of the scenes, typography, page copy |
| the two scene buffers (frozen from, live to) and the scissor | which side the line enters from (see below) |
| timing, easing, DPR, reduced-motion still | control chrome |
Rules, each tied to the failure it prevents
Draw the frozen old frame and the live new scene, never one fading into the other. Snapshot the outgoing scene once into a full-resolution target when the transition starts (clock frozen) and keep rendering the incoming scene live. A cross-fade, or a burn over a still-animating old scene, shows two chapters in one patch of screen and the fire stops being the thing that changes the page.
What ships with it
4 files 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.
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.
- 22d ago First seen · 187 lines · 167 tokens per session scan A 690c85e4b5e2
paper-cinder-transition is a skill published in the GitHub repository MengTo/Skills (6,944 stars, last pushed 4d ago), licensed MIT. It adds 167 tokens to every session and 3,390 once invoked, about $0.0007 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 2026-10-01.
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
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…
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…