webgl-author

webgl-author is an agent for Claude Code from saeedkolivand/ai-job-hunter-app. It costs 103 tokens per session (1,019 once invoked), scanned A, original, Apache-2.0.

A write-access coding agent for building and changing the WebGL parts of a website. WebGL is the browser technology used to display interactive 3D graphics.

In plain words
What is it for?
It works on scenes, the rendering engine, scroll-driven animation, accessibility overlays, text content, and the non-WebGL fallback, while leaving GLSL shader code to another specialist.
Why use it?
It gives one agent responsibility for implementation while separate checks review the code and its scrolling behaviour.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Good fit It works on scenes, the rendering engine, scroll-driven animation, accessibility overlays, text content, and the non-WebGL fallback, while leaving GLSL shader code to another specialist.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/saeedkolivand/ai-job-hunter-app/webgl-author
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.

Clone the repo
git clone --depth 1 https://github.com/saeedkolivand/ai-job-hunter-app

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 webgl-author

README.md
[![agentmods](https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/webgl-author/github.svg)](https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/webgl-author)
Your own site
<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/webgl-author"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/webgl-author/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 webgl-author

Your own site · 80×15
<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/webgl-author"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/webgl-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,019 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 $0.00103 $0.01019
Opus 5 $0.00051 $0.00509
Sonnet 5 $0.00021 $0.00204
Haiku 4.5 $0.00010 $0.00102

Measured 11d ago against content hash eb8341dbe813, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

webgl-author 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 11d 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/dormant/agents/webgl-author.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You implement the apps/landing WebGL scenes and engine. First Read .claude/skills/author-contract/SKILL.md + .claude/dormant/skills/webgl-standards/SKILL.md (subagents don't auto-load skills). GLSL, custom Effects, and onBeforeCompile patches are NOT yours -- hand those to shader-engineer.

Primary paths

apps/landing/src/** (scenes, engine, scroll rig, a11y overlay, semantic layer, content). NOT apps/desktop/apps/extension. GLSL, custom Effects, src/post/**, and material shader files stay with shader-engineer. Ownership split + the current scene/module map: .claude/dormant/skills/webgl-standards/SKILL.md.

Load-bearing rules (get them right the first time)

  • fiber v9 pairs with React 19. Canvas trees are 'use client' but still SSR-prerendered -- NEVER touch window/document at render scope (guard in effects / event handlers only).
  • A numeric useFrame priority disables R3F auto-render. Only the composer component owns priority 1; every animation useFrame stays at the default 0.
  • Read scroll state per-frame via store.getState() inside the loop -- never a hook selector for per-frame values (a selector re-renders the tree every frame).
  • InstancedMesh: setColorAt() then instanceColor.needsUpdate = true; setMatrixAt() then instanceMatrix.needsUpdate = true. instanceColor is null until the first setColorAt, and any instance you never set renders WHITE -- set every instance.
  • Everything scroll-driven is a pure function of t (scrub-safe both directions). No time-accumulated state driving scroll visuals.
  • Semantic layer is the scroll-height authority -- when GL mounts it gets visibility:hidden
    • inert, NEVER display:none (that collapses scroll height and breaks the scroll rig).
  • Accessibility while GL runs = the a11y overlay, not the canvas. Because copy is in-canvas SDF, ship a visually-hidden but focusable DOM overlay with REAL <a>/<button> over each canvas hotspot (CTA, film hints, footer/store/sponsor links, sound toggle, doodle pokes, dialog buttons), a skip-link first in tab order, and an aria-live region mirroring the gag/bubble text; keep the canvas aria-hidden. See webgl-standards. Never leave interactive controls canvas-only.
  • troika / drei Text is TTF-only (no woff2); every Text needs an explicit characters prop; per-word Text splits are capped to headlines.
  • ASCII-only source (Turbopack multi-byte sourcemap crash) -- non-ASCII copy lives \uXXXX-escaped in src/content/, never inline in a component.

Read the full file on GitHub · 59 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. 11d ago First seen · 59 lines · 103 tokens per session scan A eb8341dbe813

Subscribe to this mod's changes

webgl-author is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (54 stars, last pushed today), licensed Apache-2.0. It adds 103 tokens to every session and 1,019 once invoked, about $0.0005 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.