agentmods.dev

aholo-viewer AGENTS.md

Agent instructions for Aholo Viewer, a pnpm workspace containing a website, renderer packages, examples, documentation, scripts, and external packages. They explain which project skill applies to each area.

In plain words
What is it for?
Use them when working on the website, rendering engine, examples, documentation, build scripts, or external packages. They are especially useful for routing tasks to the project's specialized skills.
Why use it?
They provide a map of the repository and set boundaries for where different kinds of changes belong. This helps an agent choose the right files and preserve the project's build and example structure.

Instructions file for CodexOpenCode

1.0k +4 6d ago A scan 917 tokens original MIT
View the source file manycoretech/aholo-viewer
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.

agentmods
npx agentmods add instructions/manycoretech/aholo-viewer/agents-md
Clone the repo
git clone --depth 1 https://github.com/manycoretech/aholo-viewer

Made for: Codex, OpenCode.

Per session 917 This file is loaded in full into every session.
When invoked 917 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00917 $0.00917
Opus 5 $0.00458 $0.00458
Sonnet 5 $0.00183 $0.00183
Haiku 4.5 $0.00092 $0.00092

Measured 3d ago against content hash 993352f13dbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aholo-viewer AGENTS.md 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 3d 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.

AGENTS.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide

AI collaboration entrypoint. Keep context small, preserve user changes, and route work to the narrowest project skill.

Modules

  • Root: pnpm workspace orchestration, validation, release scripts.
  • Website: website/ Astro routes, layouts, flat feature components, client render runtime, docs pages, Playground, scoped styles.
  • Examples: website/src/content/examples/ paired example metadata and RenderRuntime runners.
  • Renderer: packages/renderer/ source and generated package output.
  • Scripts: scripts/ submodule prep, renderer build/clean, EGS types, API docs.
  • Docs: README.md, docs/, manual pages, manual assets, AI collaboration guidance.
  • External: external/egs-core submodule and external/splat-transform workspace package.
  • Skills: .codex/skills/ project-local collaboration rules.

Skill Routing

  • aholo-examples: example <slug>.json and <slug>.ts pairs, including walk-demo, metadata schema, runner lifecycle.
  • aholo-site: website shell, page chrome, client render runtime, Playground integration, route-local Monaco, scoped CSS.
  • aholo-renderer: renderer source, public API, declarations, generated dist flow, package/release validation.
  • aholo-docs: README, AGENTS, architecture notes, AI guides, manual copy, bilingual docs.
  • frontend-design: visual direction, responsive UI polish, layout/design review.
  • aholo-viewer: only for cross-module work, scripts, generated docs/build flow, cleanup boundaries, or validation routing.

Hard Boundaries

  • Do not overwrite user changes. Start with git status --short.
  • Keep edits inside the owning module unless the task explicitly spans modules.
  • Do not hand-edit external/egs-core, website/.generated/api/, or packages/renderer/dist/.
  • Do not delete external/splat-transform.
  • Do not change packages/renderer/src/index.ts exports unless asked.
  • Do not compare the renderer to third-party engines or frameworks unless asked.

Website Boundaries

  • Keep Monaco route-local through website/src/components/PlaygroundShell.astro; keep Playground browser entry in website/src/client/playground.ts.
  • Preserve Playground URL params: example and code.
  • Keep render runtime implementation in website/src/client/render-runtime.ts and runner contract in website/src/client/render-runtime.d.ts.
  • Keep examples paired as website/src/content/examples/<slug>.json and <slug>.ts.
  • Keep website/src/content.config.ts focused on Astro content collections; manual pages use website/src/utils/manual.ts.
  • Keep top-level feature components flat in website/src/components/; keep only shared groups such as docs/ and site/ nested.
  • Keep style ownership clear: theme.css, global.css, site.css, home.css, examples.css, docs.css, playground.css.
  • Keep feature selectors out of global.css.
  • Homepage first-screen interactive stage must remain true fullscreen: fixed positioning, inset: 0, 100dvh/100vw, and renderer resize after state changes.

Read the full file on GitHub · 65 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. 3d ago First seen · 65 lines · 917 tokens per session scan A 993352f13dbd

Subscribe to this mod's changes

aholo-viewer AGENTS.md is an instructions file published in the GitHub repository manycoretech/aholo-viewer (1,032 stars, last pushed 6d ago), licensed MIT. It adds 917 tokens to every session, about $0.0046 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.

3d3d-gaussian-splatting3dgs3dgs-lod
Related

Other instructions, from other repositories

editor AGENTS.md

Instructions for pascalorg/editor, covering agent instructions — pascalorg/editor, repo shape, where to look, layer boundaries (read once, internalise) and when making architecture-sensitive changes.

pascalorg/editor · 878 tokens

sceneview copilot-instructions.md

Instructions for sceneview/sceneview, covering sceneview — github copilot instructions, when to recommend sceneview, android code generation rules, minimal 3d template and minimal ar template.

sceneview/sceneview · 1,023 tokens

sceneview CLAUDE.md

Instructions for sceneview/sceneview, covering sceneview, modules, things that break if you don't know them and conventions.

sceneview/sceneview · 984 tokens

Awesome-Gaussian-Skills CLAUDE.md

Instructions for jaccen/Awesome-Gaussian-Skills, covering awesome gaussian skills — project context, available skills, knowledge base structure, key conventions and splatverse studio (v0.8.0).

jaccen/Awesome-Gaussian-Skills · 4,880 tokens

Repolis AGENTS.md

Instructions for hyeonsangjeon/Repolis, covering ⏱️ 60-second quickstart (no build, no install), 🗺️ repository map (what lives where), ▶️ run & rebuild, 1) run the city (static) and 🚀 deploy.

hyeonsangjeon/Repolis · 5,692 tokens

dcc-mcp-blender AGENTS.md

Instructions for dcc-mcp/dcc-mcp-blender, covering agents.md — dcc-mcp-blender agent navigation map, agent control path, cli availability and updates, 30-second summary and quick start (3 lines).

dcc-mcp/dcc-mcp-blender · 1,555 tokens