splicedeck AGENTS.md

splicedeck AGENTS.md is an instructions file for Codex, OpenCode from ihuzaifashoukat/splicedeck. It costs 1,765 tokens per session, scanned A, original, Apache-2.0.

The main repository contract for splicedeck, a local video editor driven by AI agents. It defines how bookmarks, party-specific editing preferences, locked behavior records, video processing, and other project rules work.

In plain words
What is it for?
Read it before changing any part of splicedeck, especially editing behavior, dependencies, speech recognition, project memory, or files governed by its ownership rules.
Why use it?
It gives agents the authoritative rules for making safe, reproducible changes and explains how the project records behavior so changes can be reviewed or reverted.

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

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 splicedeck AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ihuzaifashoukat/splicedeck/agents-md.svg)](https://agentmods.dev/instructions/ihuzaifashoukat/splicedeck/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ihuzaifashoukat/splicedeck/agents-md"><img src="https://agentmods.dev/badge/instructions/ihuzaifashoukat/splicedeck/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,765 This file is loaded in full into every session.
When invoked 1,765 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 $0.01765 $0.01765
Opus 5 $0.00882 $0.00882
Sonnet 5 $0.00353 $0.00353
Haiku 4.5 $0.00177 $0.00177

Measured 5d ago against content hash befa1e9296b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

splicedeck 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 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.

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 · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

splicedeck — agent contract

Read by Codex, Claude Code, Cursor, Gemini CLI and any agent that honours AGENTS.md. Read this before touching anything.

A local-first video editor that an AI agent drives. One pass over a source produces both a cleaned long-form master and vertical clips. It remembers how each party likes to be cut.

The governing idea

A bookmark is the base. The casebook is the delta. findings.lock.txt is the receipt.

A style bookmark supplies opening settings. Per-party memory overrides individual fields where a human shipped something different and kept it. The resolver writes its answer to a committed lock file, so git diff reads as a behaviour changelog and git revert is a real behavioural rollback.

Hard rules

  1. Pure-Python dependencies only. No compiled extension on any default path, ever, including transitively. On a clean Windows box with no Microsoft Visual C++ redistributable, ctranslate2 and onnxruntime both fail to load their DLLs. Speech recognition runs as a subprocess against an external binary, never as an imported wheel. A pull request that adds a wheel with a binary artifact on the default path is rejected regardless of what it does.
  2. Local-complete, cloud-optional. A fresh clone with no API keys and no cloud account must render a finished, delivered file. Cloud tiers are opt-in accelerators behind the same interface. Nothing may become required.
  3. ffmpeg is a child process. Never linked, never vendored, never bundled. Every filter-embedded path is escaped or made relative, because a Windows drive letter breaks filter parsing: : is the filter option separator.
  4. Capability is proven by trial, never by feature list. ffmpeg -encoders lists encoders the hardware cannot run. On the reference machine h264_nvenc is listed and fails at runtime because the GPU has no encoder silicon, while h264_qsv succeeds. Detect by test-encoding.
  5. weld/ is pure. It builds argv lists and filtergraph strings and returns them. No subprocess, no disk, no network, no clock. This is what makes the whole decision layer testable in CI with no ffmpeg and no GPU. Do not put I/O in it "just this once".
  6. All time is an integer tick. No float ever enters the time domain. Ranges are in / out / at, never origin-plus-extent, so moving a cut is one number changing.
  7. Nothing durable is authored by the model. Every memory tool argument is an identifier the pipeline minted — never a value, a string, or a path. A case records something a human did; the pipeline writes every field from its own ledger.
  8. The server may write only casebook/pending/. It may read casebook/parties/, casebook/schema/, bookmarks/ and ledger/. Skills, prompts and executables are unreachable because nothing can reach them, not because something refuses.
  9. A cut never lands inside a word. Snap to word boundaries from the index.
  10. Describe the look, never the source. No preset, bookmark, axis value, element, directory, file, party identifier, commit message or documentation line may be named after — or documented as targeting — any real person living or dead, or any third-party brand, product, channel, publication or trade dress. This binds the casebook write gate too.
  11. Media never enters git. Sources are content-addressed; the repository holds pointers. The hash is authoritative, the path is advisory.
  12. Every failure is typed, and every refusal carries its correction as data — a list of ready-to-send calls, not prose the caller must parse.

Read the full file on GitHub · 137 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 · 137 lines · 1,765 tokens per session scan A befa1e9296b5

Subscribe to this mod's changes

splicedeck AGENTS.md is an instructions file published in the GitHub repository ihuzaifashoukat/splicedeck (3 stars, last pushed 17d ago), licensed Apache-2.0. It adds 1,765 tokens to every session, about $0.0088 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.