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 agentmods add instructions/plokdalberb-byte/cutible/agents-mdgit clone --depth 1 https://github.com/plokdalberb-byte/cutibleWrote 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/instructions/plokdalberb-byte/cutible/agents-md)<a href="https://agentmods.dev/instructions/plokdalberb-byte/cutible/agents-md"><img src="https://agentmods.dev/badge/instructions/plokdalberb-byte/cutible/agents-md.svg" alt="Measured on agentmods" 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 | $0.00889 | $0.00889 |
| Opus 5 | $0.00445 | $0.00445 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
cutible 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.
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.
Repository Guidelines
Project Structure & Module Organization
Cutible is a headless video-editing engine with 5 architectural layers:
| Layer | Modules | Role |
|---|---|---|
| L1 Core | schema.py, verbs.py |
Timeline-as-Data (Pydantic) + 14 low-level verb primitives |
| L2 Render | compiler.py, qc.py |
Deterministic FFmpeg render + probe-based QC |
| L3 Capabilities | verbs_high.py, ingest/, index/, perception/, render_farm/, remotion/, otio_bridge/ |
Composite verbs, media ingest, semantic search, VLM review, distributed render, OTIO interop |
| L4 Agents | agents/ |
Multi-agent swarm: Planner → Editor → Sound → QC → Orchestrator |
| L5 Interfaces | cli.py, mcp_server.py, api/app.py, sdk/client.py, sdk_ts/ |
CLI, MCP (35 tools), REST API, Python SDK, TypeScript SDK |
The primary agent interface is the MCP server (mcp_server.py): 35 JSON-RPC 2.0 tools over stdio. The REST API and SDKs are secondary.
Key pattern: every verb returns a Diff, errors return VerbError(hint, context). The Project (Pydantic model) is the single source of truth — JSON, diffable, auditable.
Build, Test, and Development Commands
# Install (from repo root)
pip install -e ".[all,dev]" # full install + dev tools
pip install -e "." # core only
pip install -e ".[api]" # REST API only
# Lint & type-check
ruff check cutible/ # lint (E, F, W, I, N, UP, B, SIM rules)
ruff format --check cutible/ # format check
mypy cutible/ --ignore-missing-imports
# Run tests
pytest # all tests
pytest tests/test_core.py # core tests only
pytest -k "test_undo" # specific test by name
# TypeScript SDK (cd sdk_ts/)
npm test # jest tests
npx tsc --noEmit # type-check (strict mode)
# Docker
docker-compose up app # REST API on :8000
docker-compose --profile distributed up worker # render farm worker
# CLI entry points
cutible # main CLI (12 commands)
cutible-mcp # MCP stdio server
cutible-api --host 0.0.0.0 --port 8000
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.
- 3d ago First seen · 65 lines · 889 tokens per session scan A c493bc61ab9d
cutible AGENTS.md is an instructions file published in the GitHub repository plokdalberb-byte/cutible (0 stars, last pushed 2mo ago), licensed MIT. It adds 889 tokens to every session, about $0.0044 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.
Other instructions, from other repositories
leclap AGENTS.md
Instructions for heristop/leclap, covering agents.md, project overview, repository layout, setup and commands.
leclap CLAUDE.md
Instructions for heristop/leclap: This repository's agent guidance lives in AGENTS.md — read it first; it is the single source of truth for structure, commands, and conventions.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.
dshcode CLAUDE.md
Claude Code instructions for whitelonng/dshcode, a project described as: Community desktop companion for DeepSeek Harness — one-click Electron app for macOS and Windows.