FableCut AGENTS.md

Repository instructions for FableCut, a browser video editor whose timeline is controlled by coding agents through project files or an MCP server.

In plain words
What is it for?
Updating the video schema, editor code, API, or MCP tools while checking JavaScript syntax and keeping documentation synchronized.
Why use it?
They set project constraints that keep preview and exported video consistent and prevent changes from breaking the documented interface or dependency-free design.

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/ronak-create/fablecut/agents-md
Clone the repo
git clone --depth 1 https://github.com/ronak-create/FableCut

Made for: Codex, OpenCode.

Per session 256 This file is loaded in full into every session.
When invoked 256 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 $0.00256 $0.00256
Opus 5 $0.00128 $0.00128
Sonnet 5 $0.00051 $0.00051
Haiku 4.5 $0.00026 $0.00026

Measured 2d ago against content hash 85506972106a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

FableCut 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 2d 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 · 22 lines

What it actually says

Working with FableCut

The complete agent manual is in CLAUDE.md. Read it before changing the project schema, using the MCP tools, or editing the timeline. This file exists so agents that look for the cross-tool AGENTS.md convention, including OpenCode and Codex, find the same source of truth without duplicating it.

Project constraints

  • Keep FableCut zero-runtime-dependency and standard-library only.
  • Keep preview and export on the same compositor path.
  • Prefer small, focused changes and preserve the existing terse browser-native style.
  • If a schema, prop, text animation, API, or MCP surface changes, update CLAUDE.md and the English README.md in the same change.
  • Run node --check server.js && node --check app.js && node --check mcp-server.js before opening a PR.

MCP entry point

The local MCP server is mcp-server.js. It can be started by any stdio-capable MCP client:

node /absolute/path/to/FableCut/mcp-server.js

Use the existing CLAUDE.md recipes and tool descriptions rather than inventing a second protocol or schema.

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. 2d ago First seen · 22 lines · 256 tokens per session scan A 85506972106a

Subscribe to this mod's changes

FableCut AGENTS.md is an instructions file published in the GitHub repository ronak-create/FableCut (643 stars, last pushed 4d ago), licensed MIT. It adds 256 tokens to every session, about $0.0013 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.