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 CryptoLibertus/myvideogift-mcp --skill create-video-giftgit clone --depth 1 https://github.com/CryptoLibertus/myvideogift-mcpWrote 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/cryptolibertus/myvideogift-mcp/create-video-gift)<a href="https://agentmods.dev/skills/cryptolibertus/myvideogift-mcp/create-video-gift"><img src="https://agentmods.dev/badge/skills/cryptolibertus/myvideogift-mcp/create-video-gift/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/cryptolibertus/myvideogift-mcp/create-video-gift"><img src="https://agentmods.dev/badge/skills/cryptolibertus/myvideogift-mcp/create-video-gift.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 | $0.00053 | $0.00550 |
| Opus 5.5 | $0.00021 | $0.00220 |
| Sonnet 5.5 | $0.00011 | $0.00110 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
create-video-gift 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.
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.
What it actually says
Create a video gift
Workflow for the myvideogift MCP server bundled with this plugin. A finished
gift is an original song plus a cinematic photo-montage film, delivered at a
shareable URL.
-
Check the account first — call
check_account. Rendering spends one prepaid credit; if the balance is empty, stop and send the user to https://developers.myvideogift.com to top up. Don't gather inputs they can't spend. -
Pick the occasion — call
list_occasionsand choose the id that fits (it drives the song's lyrics and tone). If more than one plausibly fits, ask the user rather than guessing. -
Gather the inputs for
create_gift:recipient_nameandrelationshipare required.memory(a sentence or two) and up to 6feeling_wordsnoticeably improve the song — ask for them instead of leaving them blank.photo_urls: up to 30 publicly fetchable image URLs of the recipient. Required to render. If the user's photos aren't hosted anywhere public, they must upload them somewhere fetchable first — the API pulls by URL.
-
Consent is a hard gate — rendering requires
consent=true, an attestation that the user holds the rights to the photos and the recipient's depiction. Ask the user explicitly and only pass it after they confirm. Never set it on your own. -
Draft costs nothing —
create_giftwithrender=falsecreates a free draft you can show the user for approval. To render, callcreate_giftagain with the same inputs plusrender=trueandconsent=true(this creates the billable gift; the draft stays a draft). -
Poll for the film — a render takes a few minutes and returns a
poll_after_sechint. Callget_giftwith the returnedgift_iduntil status isdelivered, then give the user thefilm_urland the shareablegift_url.
If any tool returns an error about the key or balance, surface it verbatim — the messages are written for end users.
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.
- 2mo ago First seen · 45 lines · 53 tokens per session scan A 2d83e12a6933
create-video-gift is a skill published in the GitHub repository CryptoLibertus/myvideogift-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 550 once invoked, about $0.0002 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.
Other skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…
qmclaw-workbench
A local simulator for superconducting quantum-bit experiments, including measurements used to study and tune a qubit. It produces bounded synthetic results without connecting to laboratory hardware or quantum cloud services.
quantum-fermi-hubbard-vqe
A variational quantum simulation of the open-boundary Fermi–Hubbard chain, a model of particles hopping between sites and interacting when they occupy the same system. It maps the model to qubits with the Jordan–Wigner transformation and searches for a low-energy state.
quantum-grover
A Qiskit implementation of Grover's algorithm, a quantum search method that increases the chance of finding a marked item. It can explain the method, build an explicit quantum circuit, or run it with chosen inputs.
guppy-programs
A compiler and simulator for structured quantum programs with measurements, qubit reset, and gates chosen by earlier measurement results. It uses Guppy and Selene to model these dynamic circuits locally.