blitzreels-x-video

blitzreels-x-video is a skill for Claude Code from blitzreels/agent-skills. It costs 67 tokens per session (567 once invoked), scanned A, original, MIT.

Instructions for turning an X post, video, thread, conversation, or current trend into a short video with BlitzReels. X, formerly Twitter, is a social network where these posts are published.

In plain words
What is it for?
For clipping native X videos, or making sourced short-form videos from X text, threads, or trends.
Why use it?
They help keep the source, author, timing, and verified facts separate before production begins.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the blitzreels plugin — 5 skills, 1 MCP server shipped together

Good fit For clipping native X videos, or making sourced short-form videos from X text, threads, or trends.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blitzreels/agent-skills/blitzreels-x-video
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 blitzreels/agent-skills --skill blitzreels-x-video
Clone the repo
git clone --depth 1 https://github.com/blitzreels/agent-skills

Made for: Claude Code.

Or install blitzreels, the plugin that ships this one along with the rest of its 5 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.

agentmods badge for blitzreels-x-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/blitzreels/agent-skills/blitzreels-x-video/github.svg)](https://agentmods.dev/skills/blitzreels/agent-skills/blitzreels-x-video)
Your own site
<a href="https://agentmods.dev/skills/blitzreels/agent-skills/blitzreels-x-video"><img src="https://agentmods.dev/badge/skills/blitzreels/agent-skills/blitzreels-x-video/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 blitzreels-x-video

Your own site · 80×15
<a href="https://agentmods.dev/skills/blitzreels/agent-skills/blitzreels-x-video"><img src="https://agentmods.dev/badge/skills/blitzreels/agent-skills/blitzreels-x-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 567 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 $0.00067 $0.00567
Opus 5 $0.00034 $0.00283
Sonnet 5 $0.00013 $0.00113
Haiku 4.5 $0.00007 $0.00057

Measured 11d ago against content hash 3e451dc4cc24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

blitzreels-x-video 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 11d 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/blitzreels-x-video/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BlitzReels X-to-video

Combine current X evidence with the BlitzReels MCP tools. Do not treat popularity, sentiment, or a post's text as verified unless the host can read the live source.

Resolve the source

  1. Open the supplied X links or use the host's X search capability when available.
  2. Preserve the source URLs, author attribution, and publication time. Separate quoted claims from verified facts.
  3. Choose one branch:
    • Native X video to clips: use the X post URL with clips_create.
    • Existing BlitzReels media: use its asset ID with clips_create.
    • Text post, thread, or trend to a new video: prepare a sourced brief, then follow blitzreels-generation.
  4. Ask for the intended angle only when the source supports several materially different stories.

Completion: a reachable source, a clear video angle, and one selected production branch.

Clip native X video

  1. Call clips_create once with the X URL and a caller-generated idempotency key.
  2. Follow batch.polling with clips_get; do not create a second batch while the first is active.
  3. Present completed clips before items needing review. Include verified titles, download URLs, and the studio URL.
  4. Start or retry a paid export only after approval when the returned state requires it.

Completion: a terminal batch or a bounded active status with its batch ID and studio URL.

Create a video from an X discussion

  1. Build a short brief with the hook, verified context, narration, visual direction, target duration, and aspect ratio.
  2. Cite the X sources in the reviewable brief. Do not present an X claim as independent confirmation.
  3. Follow blitzreels-generation for planning, cost review, asset generation, visual QA, and export.
  4. Keep paid generation and export behind separate approval unless the user has already approved the disclosed cost.

Completion: a verified downloadable video plus the source list and any unresolved factual caveats.

Boundaries

  • Do not imitate a real person's voice or likeness without rights and explicit user intent.
  • Do not download private, access-controlled, or deleted X media.
  • Do not claim that BlitzReels publishes to X. Return a verified asset; use a separate authorized X tool for posting.
  • Require approval immediately before publishing, deleting, purchasing, or spending credits.

Read the full file on GitHub · 47 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. 11d ago First seen · 47 lines · 67 tokens per session scan A 3e451dc4cc24

Subscribe to this mod's changes

blitzreels-x-video is a skill published in the GitHub repository blitzreels/agent-skills (3 stars, last pushed 11d ago), licensed MIT. It adds 67 tokens to every session and 567 once invoked, about $0.0003 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

authoring-video-templates

Use when creating or editing a video template JSON (the template descriptor), adding or changing sections/filters/maps/variables/transitions/looks/motion/audio/layers, or debugging template validation errors in ffmpeg-video-composer.

heristop/leclap · 51 tokens

core-architecture-patterns

Use when adding a segment type, platform adapter, editor manager, core service, or descriptor effect (look/grade/motion/section-audio field) in packages/ffmpeg-video-composer, or when wiring new dependencies into the tsyringe container.

heristop/leclap · 58 tokens

ondevice-ffmpeg-engine

Use when building, modifying, or consuming the on-device FFmpeg engine — the Rust crate packages/ffmpeg-engine, the leclap-ffmpeg Expo native module, the run/probe/version/cancel API, the uniffi bindings, build-engine.sh, or the FFmpeg-from-source toolchain in scripts/ffmpeg.

heristop/leclap · 75 tokens

cross-platform-ffmpeg

Use when working with FFmpeg across Node/Static/WASM, the PlatformBridge, the FFmpeg detection/fallback chain, or browser/React Native runtime constraints in ffmpeg-video-composer.

heristop/leclap · 45 tokens

kling-studio

Full-featured Kling 3.0 Omni video generation skill. Covers text-to-video, image-to-video, video editing (base mode), video reference (feature mode), multi-shot generation, and audio-synced video. Includes validated API constraint rules and prompt engineering guide.

wells1137/media-skills · 60 tokens

seedance-prompt

This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.

Emily2040/seedance-2.0 · 68 tokens