agentmods.dev

instagram-reel-director

instagram-reel-director is a skill for Claude Code, Codex from 4nw3rprod/spoooler. It costs 145 tokens per session (4,302 once invoked), scanned A, original, MIT.

A production workflow for creating a finished Instagram Reel as a vertical 1080×1920 MP4 using the instagram-reel-tool server.

In plain words
What is it for?
Writing on-screen text and voiceover, choosing scene types, reviewing product media, generating audio, aligning speech, and rendering the Reel.
Why use it?
It provides an end-to-end process for turning a product or topic into a ready-to-post short video, including script, media selection, narration, timing, and rendering.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

not rated 2repo 4mo ago A scan 145 tokens original MIT

Good fit Writing on-screen text and voiceover, choosing scene types, reviewing product media, generating audio, aligning speech, and rendering the Reel.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/4nw3rprod/spoooler/spoooler
View source ↗ 4nw3rprod/spoooler spoooler.vercel.app
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.

Any agent
npx skills add 4nw3rprod/spoooler --skill spoooler
Clone the repo
git clone --depth 1 https://github.com/4nw3rprod/spoooler

Made for: Claude Code, Codex.

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 instagram-reel-director

README.md
[![agentmods](https://agentmods.dev/badge/skills/4nw3rprod/spoooler/spoooler/github.svg)](https://agentmods.dev/skills/4nw3rprod/spoooler/spoooler)
Your own site
<a href="https://agentmods.dev/skills/4nw3rprod/spoooler/spoooler"><img src="https://agentmods.dev/badge/skills/4nw3rprod/spoooler/spoooler/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.

agentmods 80×15 button for instagram-reel-director

Your own site · 80×15
<a href="https://agentmods.dev/skills/4nw3rprod/spoooler/spoooler"><img src="https://agentmods.dev/badge/skills/4nw3rprod/spoooler/spoooler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,302 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00145 $0.04302
Opus 5.5 $0.00058 $0.01721
Sonnet 5.5 $0.00029 $0.00860
Haiku 4.5 $0.00015 $0.00430

Measured 2mo ago against content hash 90fbc0d3478e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

instagram-reel-director 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 2mo ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/fetch-emoji.sh, scripts/scrape-entities.py, scripts/scrape-media.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instagram Reel Director

You produce a finished Instagram reel by orchestrating the instagram-reel-tool MCP server. The server is the crew (scraping, stock, TTS, whisper alignment, Remotion render — all local). You are the director. Your judgment — the script, the archetype per scene, which media looks good — is the product. There is no separate scriptwriting model; do not look for one.

Everything runs on the user's machine and writes to runs/<slug>/*.json and public/instagram-reel-tool/<slug>/. State persists between calls, so a session is resumable via get_run_state.

Core principles

  1. You write everything. On-screen copy = complete short sentences (6–16 words, never fragments). Voiceover = natural spoken English, one clear idea per sentence. Do not echo a transcript verbatim — rewrite it as a reel.
  2. You choose the archetype per scene. Vary them. A reel that is five statement slides is a failure. Mix hook → (problem / proof / stat / checklist / comparison / graph) → cta.
  3. You judge media with your own eyes. After scraping, call review_media to SEE the thumbnails, then rank_media to commit your scores. Only fall back to vision_filter_media (an external API) if you genuinely cannot view images.
  4. Every scene gets a background; product media goes in frames. Stock video = full-bleed background (one per scene). Scraped product imagery = frame (browser-chrome card), distributed across scenes, concentrated on proof.
  5. Confirm before you render. Call get_run_state and check that script, media, pattern, and voice are all present. Rendering is the slow, expensive step.
  6. Narrate what you are doing. These tools stream live progress; tell the user which stage is running and what came back.

The 12 scene archetypes (you pick one per scene)

type Use it for layoutData required
hook Scene 1. The scroll-stopper. none
problem Name the pain / costly status quo. none
stat One dominant number is the whole point. {value, label}
statement A punchy editorial declaration, no data. none
proof Show the actual product / a concrete step. Hosts scraped media. none
checklist 3–5 steps, features, or requirements. {title?, items:[{text, brand?}], checked?}
comparison Before/after, old vs new, A vs B. {leftTitle, rightTitle, leftItems[], rightItems[], leftBrand?, rightBrand?}
bar-graph Compare magnitudes across 2–5 named things. {title?, unit?, bars:[{label, value, brand?}]}
pie-chart Composition / share of a whole (≤5 slices). {title?, slices:[{label, value, brand?}]}
progress-graph A trend / growth over 3–6 points. {title?, unit?, points:[{label, value}]}
motion-graphic A process/flow of connected nodes. {title?, nodes:[{label, brand?}], flow:"linear"|"cycle"|"hub"}
github-card The script names a specific GitHub repo. {owner, repo, description?, language?, stars?, forks?, visibility?, url?} — the scraper auto-fills stars/forks/language from the repo URL
cta Last scene. The call to action. none

Read the full file on GitHub · 301 lines

Files

What ships with it

6 files 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.

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. 2mo ago First seen · 301 lines · 145 tokens per session scan A 90fbc0d3478e

Subscribe to this mod's changes

instagram-reel-director is a skill published in the GitHub repository 4nw3rprod/spoooler (2 stars, last pushed 4mo ago), licensed MIT. It adds 145 tokens to every session and 4,302 once invoked, about $0.0006 per session on Opus 5.5. 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.

Creative and mediaMarketing and SEOcloned voiceinstagram reelproduct reelreel generatorremotion rendershort-form-videovertical videovoiceover reel
Related

instagram-reel-director compared with skills from other repositories

instagram-reel-director next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
instagram-reel-director4nw3rprod/spooolerSkill24mo agoMITA145Claude Code, Codex
viralityOotto-AI/claude-content-skillsSkill408yesterdayMITA95Claude Code
content-factoryOotto-AI/claude-content-skillsSkill408yesterdayMITA155Claude Code
agent-reachOotto-AI/claude-content-skillsSkill408yesterdayMITA334Claude Code
reel-builderOotto-AI/claude-content-skillsSkill408yesterdayMITA111Claude Code
ai-brainOotto-AI/claude-content-skillsSkill408yesterdayMITA95Claude Code
hook-miningOotto-AI/claude-content-skillsSkill408yesterdayMITA111Claude Code