Experiential is an open-source model gateway and router, meaning a service that gives agents one API for hosted, user-provided, local, and custom language models. It is for teams that need to choose models, control access and spending, and route production requests according to quality, speed, or cost. The catalogue entries provide agent skills and instructions for operating or configuring the gateway.
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 experientiallabs/experiential --skill video-creategit clone --depth 1 https://github.com/experientiallabs/experientialWrote 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/experientiallabs/experiential/video-create)<a href="https://agentmods.dev/skills/experientiallabs/experiential/video-create"><img src="https://agentmods.dev/badge/skills/experientiallabs/experiential/video-create/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/experientiallabs/experiential/video-create"><img src="https://agentmods.dev/badge/skills/experientiallabs/experiential/video-create.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 | $0.00147 | $0.03725 |
| Opus 5.5 | $0.00059 | $0.01490 |
| Sonnet 5.5 | $0.00029 | $0.00745 |
| Haiku 4.5 | $0.00015 | $0.00373 |
Grade B, and why
video-create scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Read `references/keys.md`. Check what's already available (env vars, `$ROOT/.env`, `~/.config`, `gh auth status`) **before** asking. Then ask once, in a single message, for only the keys that unlock something this film a How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/video-create: from idea to finished film
You are the director, editor, motion designer and sound designer. The output is a finished mp4 with audio, rendered from source that can re-render the whole film with one command. Or, in planner mode, the output is a self-contained brief that another chat can execute.
The core belief behind this skill: everyone has the same model; the context you give it is what makes it look pro. One-prompt videos look mid because the model falls back to its default look: centred text, gradient background, everything fading in. This skill exists to replace defaults with context:
- references give you pacing, type and transitions;
- brand and product assets make the film recognizably this company's;
- the company's real worldview gives it the story;
- measured numbers replace impressions;
- build rules make every frame exact and every fix a one-line edit;
- gates (storyboards → stills → animatic → render) catch problems while fixes are still cheap.
Files in this skill (read them when the phase needs them)
| File | Read it when |
|---|---|
references/interview.md |
Phase 1: the full question bank, defaults and batching rules |
references/keys.md |
Phase 2: which API keys unlock what, where to get them, how to store them, and fallbacks |
references/context-sources.md |
Phase 3: how to learn the company (repo, website, docs, Granola, Slack, Notion) and find brand assets |
references/film-patterns.md |
Phases 4-5: proven structures (manifesto, launch, one-take morph, demo, explainer, social), including measured examples |
references/build-rules.md |
Phase 6: engine, render pipeline, gotchas and pitfalls, verbatim. Non-negotiable. |
references/audio.md |
Phase 6: music, SFX, ElevenLabs VO, mixing and loudness |
references/failure-modes.md |
Every phase. Real problems from past builds, each written as "to avoid X, do Y". Skim the section for the phase you're entering. |
references/remake-mode.md |
Only when the user wants a frame-locked 1:1 remake of a reference |
references/style-match-mode.md |
Whenever the user points at a reference edit and wants "something very similar" with their own subject and footage (sigma, hype and founder edits). Read it before sourcing anything. |
scripts/fa_align.py |
Exact word times by forced alignment, for caption slams and speech cuts. Whisper timestamps drift 0.3–0.8 s. |
scripts/uniq_check.py |
Ship gate: the no-repeat rule over the shot table |
templates/BRIEF.template.md |
Phase 5: the brief you fill in (and hand off, in planner mode) |
examples/style-match-sigma-edit.md |
Phase 5 (style-match mode): a complete, frame-exact brief at the depth expected (every cut, caption, poster and transition measured) |
examples/remake-edge-of-the-world.md |
Phase 5 (remake mode): a complete frame-locked remake prompt at the depth expected |
scripts/analyze_ref.py |
Phase 4: measures a reference video (cuts per 10s, longest takes, loudness arc, silences, BPM, transcript, contact sheet) |
What ships with it
15 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.
- examples/remake-edge-of-the-world.md 9.1 KB
- examples/style-match-sigma-edit.md 12 KB
- references/audio.md 4.6 KB
- references/build-rules.md 12 KB
- references/context-sources.md 4.0 KB
- references/failure-modes.md 19 KB
- references/film-patterns.md 6.8 KB
- references/interview.md 6.8 KB
- references/keys.md 5.1 KB
- references/remake-mode.md 5.5 KB
- references/style-match-mode.md 7.2 KB
- scripts/analyze_ref.py 7.2 KB runs code
- scripts/fa_align.py 2.6 KB runs code
- scripts/uniq_check.py 1.5 KB runs code
- templates/BRIEF.template.md 5.2 KB
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.
- 16d ago First seen · 144 lines · 147 tokens per session scan B d6cb6e9173ad
video-create is a skill published in the GitHub repository experientiallabs/experiential (9,911 stars, last pushed 11d ago), licensed Apache-2.0. It adds 147 tokens to every session and 3,725 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.
Other skills, from other repositories
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…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…