glyphloop AGENTS.md

Een agentgids voor Glyphloop, een programma dat herhalende ASCII-animaties maakt voor websites. ASCII-animaties zijn beelden die met tekens zoals letters en symbolen worden opgebouwd.

In plain words
What is it for?
Voor het renderen van animaties via de opdrachtregel of MCP-server en het maken van webinsluitingen, terminalspelers of losse animatieframes.
Why use it?
De gids legt uit hoe je zonder browser een animatiepresetsbestand maakt, rendert en in een website plaatst.

Instructions file for CodexOpenCode

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/ideoshi/glyphloop/agents-md
Clone the repo
git clone --depth 1 https://github.com/ideoshi/glyphloop

Made for: Codex, OpenCode.

Per session 2,770 This file is loaded in full into every session.
When invoked 2,770 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 $0.02770 $0.02770
Opus 5 $0.01385 $0.01385
Sonnet 5 $0.00554 $0.00554
Haiku 4.5 $0.00277 $0.00277

Measured yesterday against content hash 7794606951ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

glyphloop 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 yesterday.

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 · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Glyphloop - Agent Guide

This repo generates loop-perfect generative ASCII animations for websites. As an AI agent you can create one without a browser: author a small JSON preset, run one command (or use the MCP server), and drop the output files into a site.

Quick start (CLI)

npx glyphloop@beta render --preset flowfield-hero --out out/hero
npx glyphloop@beta render --json '{"sourceId":"waves","mapper":{"fg":"#00ff88"}}' --out out/waves

From a source checkout:

npm run render -- --preset flowfield-hero --out out/hero
npm run render -- --json '{"sourceId":"waves","mapper":{"fg":"#00ff88"}}' --out out/waves

Output (--format embed, the default):

File Purpose
frames.json RLE-compressed character frames + style metadata
player.js Dependency-free player (~2 kB, honors prefers-reduced-motion)
index.html Working demo page

Other formats: --format terminal (ANSI frames.ans + play.sh), --format frames (frames.json only). The command prints a JSON summary on success and a descriptive error: line on bad input - errors list the valid options, so read them and retry.

MCP server (use from any project)

npx glyphloop@beta mcp

From this repository, run npm run mcp. To register the installed command in Claude Code:

claude mcp add --scope user glyphloop -- npx -y glyphloop@beta mcp

Tools: list_sources (call first - full schema + params), preview_frame (render one frame as text to check the look before committing), and render_animation (write embed/terminal/frames files to a directory). Iterate: preview → tweak preset → preview → render.

Embedding in a website

<div data-ascii-player></div>
<script>window.ASCII_DATA = /* contents of frames.json */;</script>
<script src="player.js"></script>

Or call AsciiPlayer(element, data) yourself. The player renders into a <pre>; size with CSS font-size. Keep embeds modest: ~140 cols × 8–12 s × 24 fps is commonly 0.5–2.5 MB of frames.json depending on motion and RLE compression, and per-cell source color can be larger. Preview the actual export before shipping it on a performance-sensitive page.

Read the full file on GitHub · 203 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. yesterday First seen · 203 lines · 2,770 tokens per session scan A 7794606951ff

Subscribe to this mod's changes

glyphloop AGENTS.md is an instructions file published in the GitHub repository ideoshi/glyphloop (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,770 tokens to every session, about $0.0138 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 2026-08-31.