agentic-edit

agentic-edit is a skill for Claude Code, Codex from danielrosehill/Claude-Video-Editor-Plugin. It costs 111 tokens per session (1,416 once invoked), scanned A, original, MIT.

A video-editing tool that uses an AI agent to find useful sections in a long video and produce a shorter cut. It can inspect footage conversationally or use a research-focused analysis backend, then create a timestamped cut list.

In plain words
What is it for?
Use it to make highlight reels, remove uninteresting parts of lectures or streams, identify strong moments, and optionally render the selected cut.
Why use it?
It helps turn long recordings into highlights without watching and selecting every segment manually.

Skill for Claude CodeCodex

Part of the video-editing plugin — 40 skills shipped together

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 skills/danielrosehill/claude-video-editor-plugin/agentic-edit
Any agent
npx skills add danielrosehill/Claude-Video-Editor-Plugin --skill agentic-edit
Clone the repo
git clone --depth 1 https://github.com/danielrosehill/Claude-Video-Editor-Plugin

Made for: Claude Code, Codex.

Or install video-editing, the plugin that ships this one along with the rest of its 40 skills.

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 agentic-edit

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielrosehill/claude-video-editor-plugin/agentic-edit.svg)](https://agentmods.dev/skills/danielrosehill/claude-video-editor-plugin/agentic-edit)
Your own site
<a href="https://agentmods.dev/skills/danielrosehill/claude-video-editor-plugin/agentic-edit"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-video-editor-plugin/agentic-edit.svg" alt="Measured on agentmods" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,416 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00111 $0.01416
Opus 5 $0.00056 $0.00708
Sonnet 5 $0.00022 $0.00283
Haiku 4.5 $0.00011 $0.00142

Measured 5d ago against content hash 2d1e0842e86d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agentic-edit 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.

skills/agentic-edit/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Edit

Drive an LLM-based agent over a long video to produce a shorter cut. The agent watches the video (or samples it), proposes timestamped segments worth keeping, and emits a cut-list. The skill optionally renders the cut.

Procedure

1. Resolve backend

Two backends, picked by user preference (or by what's installed):

Backend Best for Source
video-use conversational queries over a video, fast iteration pip install git+https://github.com/browser-use/video-use
VideoAgent research-grade multi-agent reasoning over long video git clone https://github.com/HKUDS/VideoAgent
DATA_DIR="${CLAUDE_USER_DATA:-${XDG_DATA_HOME:-$HOME/.local/share}/claude-plugins}/video-editing"
PREFS="$DATA_DIR/preferences.json"
VENV=$(jq -r '.python_venv // empty' "$PREFS" 2>/dev/null)
PYBIN="$VENV/bin/python"
test -x "$PYBIN" || { echo "No plugin venv. Run deps-setup first."; exit 1; }

# default backend = video-use if installed
if "$PYBIN" -c 'import video_use' 2>/dev/null; then
  BACKEND="video-use"
elif [ -d "$DATA_DIR/tools/VideoAgent" ]; then
  BACKEND="VideoAgent"
else
  echo "Neither video-use nor VideoAgent is installed. Run deps-setup."; exit 1
fi

2. Inputs

Field Default
Source video required
Goal / prompt required ("60-second highlight reel", "remove the audience-Q&A sections", etc.)
Target duration optional — only used as a hint to the agent
Mode cut-list-only (default) or cut-list-and-render
Backend auto (preferences.preferred_video_agent_backend)

3. Drive the backend

3a. video-use — uses its own conversational loop. Send the prompt + video path; capture the structured cut list.

"$PYBIN" - <<PY
from video_use import VideoAgent  # API may differ — check installed version
agent = VideoAgent(video_path="$SRC")
result = agent.ask("$GOAL — return JSON list of {start, end, reason}")
import json; print(json.dumps(result, indent=2))
PY

Read the full file on GitHub · 124 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 · 124 lines · 111 tokens per session scan A 2d1e0842e86d

Subscribe to this mod's changes

agentic-edit is a skill published in the GitHub repository danielrosehill/Claude-Video-Editor-Plugin (5 stars, last pushed 4mo ago), licensed MIT. It adds 111 tokens to every session and 1,416 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens