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.
npx skills add blitzreels/agent-skills --skill blitzreels-x-videogit clone --depth 1 https://github.com/blitzreels/agent-skillsWrote 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.
[](https://agentmods.dev/skills/blitzreels/agent-skills/blitzreels-x-video)<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.
<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>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 | $0.00067 | $0.00567 |
| Opus 5 | $0.00034 | $0.00283 |
| Sonnet 5 | $0.00013 | $0.00113 |
| Haiku 4.5 | $0.00007 | $0.00057 |
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.
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
- Open the supplied X links or use the host's X search capability when available.
- Preserve the source URLs, author attribution, and publication time. Separate quoted claims from verified facts.
- 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.
- Native X video to clips: use the X post URL with
- 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
- Call
clips_createonce with the X URL and a caller-generated idempotency key. - Follow
batch.pollingwithclips_get; do not create a second batch while the first is active. - Present completed clips before items needing review. Include verified titles, download URLs, and the studio URL.
- 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
- Build a short brief with the hook, verified context, narration, visual direction, target duration, and aspect ratio.
- Cite the X sources in the reviewable brief. Do not present an X claim as independent confirmation.
- Follow
blitzreels-generationfor planning, cost review, asset generation, visual QA, and export. - 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.
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.
- 11d ago First seen · 47 lines · 67 tokens per session scan A 3e451dc4cc24
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.
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.
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.
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.
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.
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.
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.