What is cutting-a-deliverable?

A workflow guide for turning a source video into a finished file with splicedeck. It defines the required sequence: inspect the source, draft a cut sheet, splice segments, verify the result, and deliver it.

Use it to inspect, cut, trim, caption, verify, or render videos with splicedeck, including when working from a cut sheet or delivery profile.

It explains the dependencies between video-editing steps and the handles, files, and folders each step requires. This prevents commands from being run in an order that cannot work.

How ihuzaifashoukat/splicedeck configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ihuzaifashoukat/splicedeck. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ihuzaifashoukat/splicedeck/main/.claude/skills/cutting-a-deliverable/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ihuzaifashoukat/splicedeck

Made for: Claude Code.

Or install splicedeck, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ihuzaifashoukat/splicedeck/cutting-a-deliverable/github.svg)](https://agentmods.dev/skills/ihuzaifashoukat/splicedeck/cutting-a-deliverable)

Your own site

<a href="https://agentmods.dev/skills/ihuzaifashoukat/splicedeck/cutting-a-deliverable"><img src="https://agentmods.dev/badge/skills/ihuzaifashoukat/splicedeck/cutting-a-deliverable/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ihuzaifashoukat/splicedeck/cutting-a-deliverable"><img src="https://agentmods.dev/badge/skills/ihuzaifashoukat/splicedeck/cutting-a-deliverable.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,738 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00094	$0.01738
Opus 5	$0.00047	$0.00869
Sonnet 5	$0.00019	$0.00348
Haiku 4.5	$0.00009	$0.00174

Measured 10d ago against content hash 2effe6867b27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cutting-a-deliverable 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 10d 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.

.claude/skills/cutting-a-deliverable/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cutting a deliverable

splicedeck's tool list tells you what each verb takes. It cannot tell you the order, or what each verb needs the previous one to have done. That is this file.

Parameters and envelopes are owned by docs/agent-surface.md §4. Do not learn them from here — run spd <verb> --help, or read that document. The verb table with cost and surface columns is in references/verb-table.md, generated from the code.

The order

inspect → draft → splice → verify → deliver

Each arrow is a real dependency, not a convention.

inspect --path <file> reads the source and mints a source handle (s1). Nothing downstream works without one. The path is workspace-relative; an absolute path refuses PATH_OUTSIDE_WORKSPACE.
draft starts a cut sheet from a source handle, a bookmark and a delivery profile, and mints a sheet handle (c1). It needs casebook/parties/<party>/ to exist as a directory. A party is created by a human, by hand. In a directory that is not yet a workspace, spd init writes bookmarks/, profiles/, elements/ and casebook/ first. It never overwrites.
splice adds a segment to the sheet's body lane. A sheet with an empty body lane cannot be delivered.
verify runs every gate and records a state_hash.
deliver encodes and muxes. It compares the sheet against the hash verify recorded, so any change to the sheet after verify requires another verify. That is what SHEET_NOT_VERIFIED means.

preview substitutes for deliver when you want a bounded span at a lower rung. It has the same preconditions.

The trap that costs everyone a turn

draft and splice both take a parameter called source, and they mean different things.

Verb	`source` is	Example
`draft`	a source handle, minted by `inspect`	`s1`
`splice`	a source key from the sheet's `sources[]`	`a`

Passing s1 to splice refuses UNKNOWN_HANDLE with an empty retry_with. Read the key out of the sheet:

Read the full file on GitHub · 155 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/verb-table.md 4.8 KB

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.

10d ago First seen · 155 lines · 94 tokens per session scan A 2effe6867b27

Subscribe to this mod's changes

cutting-a-deliverable is a skill published in the GitHub repository ihuzaifashoukat/splicedeck (3 stars, last pushed 23d ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,738 once invoked, about $0.0005 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.

Claude Code Creative and media agentic-ai ai-agent automation captions cli

brainstorming

A structured idea-generation and selection workflow. It uses methods such as SCAMPER, “How Might We” questions, Crazy 8s, ICE scoring, and voting to move from many ideas to a short list.

Insajin/autopus-adk · 16 tokens

atmos-cast

Atmos cast recording and rendering: atmos cast play/render, output-format inference (gif/mp4/html/ascii/png/jpg/jpeg), the --cast/ATMOSCAST auto-recording flag, workflow type: cast (steps/session modes) and type: simulate step types, and committed .cast screengrabs.

cloudposse/atmos · 66 tokens

splicedeck: Skill for Claude Code