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 earlyaidopters/marks-pi-harness --skill immersive-webgit clone --depth 1 https://github.com/earlyaidopters/marks-pi-harnessWrote 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/earlyaidopters/marks-pi-harness/immersive-web)<a href="https://agentmods.dev/skills/earlyaidopters/marks-pi-harness/immersive-web"><img src="https://agentmods.dev/badge/skills/earlyaidopters/marks-pi-harness/immersive-web/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/earlyaidopters/marks-pi-harness/immersive-web"><img src="https://agentmods.dev/badge/skills/earlyaidopters/marks-pi-harness/immersive-web.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 | $0.00083 | $0.02203 |
| Opus 5.5 | $0.00033 | $0.00881 |
| Sonnet 5.5 | $0.00017 | $0.00441 |
| Haiku 4.5 | $0.00008 | $0.00220 |
Grade A, and why
immersive-web 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 2mo 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Immersive websites
Build sites at the level that wins design awards: continuous 3D worlds, hybrid DOM/WebGL showcases, browser game worlds, and video-driven illusions. Four sites of this class were reverse-engineered from their shipped bundles; the distilled patterns live in references/ and a verified working starter lives in assets/template/.
Step 1 — Pick the archetype (ask the user if ambiguous)
| Path | When | Reference |
|---|---|---|
| A. WebGL scroll-narrative | Scene must react to cursor/scroll continuously; abstract/product 3D hero | references/three-scene.md, scroll-choreography.md, shaders.md |
| B. Video-driven (no WebGL) | Wow moments can be rendered offline (atmosphere, flyovers, turntables); simpler + faster; pairs with the user's video tooling | references/video-driven.md |
| B2. Scroll-scrubbed video | the user supplies ONE video to become the site's spine: scroll drives the playhead, viewer flies through it, text beats overlay. ONE-SHOT pipeline below | references/scrub-video.md |
| C. Game world | Walkable 3D world, character, input-driven camera — big build, confirm scope first | references/archetypes.md (archetype 3) |
Hybrid A+B is common: video sections + one interactive WebGL hero. Read references/archetypes.md for the full anatomy of each archetype before committing.
Path B2 one-shot pipeline (video -> finished site)
The full experience is pre-built and verified (cinemagraph idle, brand title card, alternating beats, altitude HUD, letterbox, velocity zoom, wind ambience, marquee, landing sections). Do NOT rebuild any of it. Run:
~/.pi/agent/skills/immersive-web/scripts/setup-scrub.sh <video.mp4> ./site "BRANDNAME" "TAGLINE" \
"#e3b505" "ALT" 3842 1204 "M" # optional: accent hex, HUD label/start/end/unit
Pick the accent FROM THE FOOTAGE (sample a dominant glow/highlight color) and a HUD metaphor that matches the journey: altitude for aerial descents, DEPTH counting down for dives/vaults, LAYER 01-07 for interiors, KM for drives.
What ships with it
23 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.
- assets/template-scrub/index.html 4.9 KB
- assets/template-scrub/package.json 333 B
- assets/template-scrub/src/main.js 1.7 KB runs code
- assets/template-scrub/src/style.css 10.0 KB
- assets/template-scrub/src/video-scroll.js 8.2 KB runs code
- assets/template/index.html 1.4 KB
- assets/template/package.json 333 B
- assets/template/README.md 1.6 KB
- assets/template/src/main.js 1.6 KB runs code
- assets/template/src/scene.js 3.5 KB runs code
- assets/template/src/scroll.js 1.3 KB runs code
- assets/template/src/shaders/hero.js 2.7 KB runs code
- assets/template/src/style.css 2.1 KB
- references/archetypes.md 6.8 KB
- references/asset-pipeline.md 2.5 KB
- references/scroll-choreography.md 3.1 KB
- references/scrub-video.md 8.2 KB
- references/shaders.md 3.5 KB
- references/three-scene.md 3.1 KB
- references/variation.md 4.9 KB
- references/video-driven.md 3.2 KB
- scripts/enhance-video.sh 2.4 KB runs code
- scripts/setup-scrub.sh 2.4 KB runs code
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.
- 2mo ago First seen · 107 lines · 83 tokens per session scan A 925f0f929129
immersive-web is a skill published in the GitHub repository earlyaidopters/marks-pi-harness (16 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 2,203 once invoked, about $0.0003 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 2026-08-31.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.