kinocut AGENTS.md

kinocut AGENTS.md is an instructions file for Codex, OpenCode from KyaniteLabs/kinocut. It costs 1,121 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Kinocut, a project for guarded video inspection, editing, reuse, and review workflows using FFmpeg, a tool for processing video.

In plain words
What is it for?
Use them when adding or changing video-processing code, public MCP tools, FFmpeg filters, validation, limits, or release checks.
Why use it?
They help prevent duplicated utilities, broken public tool interfaces, unsafe handling of user-supplied video values, and weak error handling.

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/kyanitelabs/kinocut/agents-md
Clone the repo
git clone --depth 1 https://github.com/KyaniteLabs/kinocut

Made for: Codex, OpenCode.

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 kinocut AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kyanitelabs/kinocut/agents-md.svg)](https://agentmods.dev/instructions/kyanitelabs/kinocut/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kyanitelabs/kinocut/agents-md"><img src="https://agentmods.dev/badge/instructions/kyanitelabs/kinocut/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,121 This file is loaded in full into every session.
When invoked 1,121 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01121 $0.01121
Opus 5 $0.00561 $0.00561
Sonnet 5 $0.00224 $0.00224
Haiku 4.5 $0.00112 $0.00112

Measured 5d ago against content hash d1020a0c311a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kinocut AGENTS.md scanned grade A with 1 finding 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 5d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

9. **ALL `subprocess.run()` and `subprocess.Popen()` calls MUST have a `timeout` parameter.** Use `DEFAULT_FFMPEG_TIMEOUT` from `defaults.py`.
AGENTS.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kinocut - Project Rules

Public Agent Skill

  • skills/kinocut/SKILL.md is the canonical public skill for this repo.
  • Invoke $kinocut in compatible agent hosts for guarded video inspection, editing, Hyperframes, repurposing, release checkpoints, and human-review workflows.
  • skills/mcp-video/SKILL.md is a compatibility entry point only. Keep it thin and direct new work to $kinocut.
  • Keep the skill aligned with docs/CLI_REFERENCE.md, docs/TOOLS.md, the Python client, and public MCP tool names when those surfaces change.

Before Writing Any Code

  1. Check if it already exists. Search ffmpeg_helpers.py, validation.py, limits.py, and defaults.py before writing any utility function. Import, don't duplicate.
  2. Check the public API. Functions registered as MCP tools in server.py are the public surface. Internal functions are prefixed with _. Don't break tool signatures.

FFmpeg Security

  1. ALL user-controlled values in FFmpeg filter strings MUST be escaped with _escape_ffmpeg_filter_value() from ffmpeg_helpers.py. This includes: colors, fonts, text, paths, and any string that goes into a -vf or -filter_complex argument.
  2. Gold standard pattern (from effects_engine.py:text_animated):
    safe_text = _escape_ffmpeg_filter_value(text)
    safe_font = _escape_ffmpeg_filter_value(font) if font is not None else font
    safe_color = _escape_ffmpeg_filter_value(color) if color is not None else color
    
  3. Never use f-string interpolation of user values directly into filter strings without escaping.

Error Handling

  1. Always raise custom types from errors.py, never raw ValueError, RuntimeError, or FileNotFoundError.
    • Input file issues → InputFileError
    • FFmpeg processing failures → ProcessingError (auto-truncates stderr to 500 chars)
    • Bad parameters → MCPVideoError with error_type="validation_error"
  2. Never embed result.stderr directly in error messages. Route through ProcessingError which truncates to 500 chars.
  3. Never use bare except Exception: without logging. Always except Exception as e: logger.warning(...).

Read the full file on GitHub · 80 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. 5d ago First seen · 80 lines · 1,121 tokens per session scan A d1020a0c311a

Subscribe to this mod's changes

kinocut AGENTS.md is an instructions file published in the GitHub repository KyaniteLabs/kinocut (136 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,121 tokens to every session, about $0.0056 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

awesome-copilot-id AGENTS.md

AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.

GulajavaMinistudio/awesome-copilot-id · 8,242 tokens

llm-safe-haven CLAUDE.md

Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.

pleasedodisturb/llm-safe-haven · 1,322 tokens

hiveshare CLAUDE.md

Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.

KB-perByte/hiveshare · 1,301 tokens

kleosrules AGENTS.md

Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).

kleosr/kleosrules · 417 tokens

finding-unknowns-skills CLAUDE.md

Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.

Neeeophytee/finding-unknowns-skills · 1,447 tokens

coding-agent-safety-gate AGENTS.md

Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.

ASER-ho/coding-agent-safety-gate · 589 tokens