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 TJC-LP/sanzaru --skill sanzaru-mcpgit clone --depth 1 https://github.com/TJC-LP/sanzaruWrote 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/tjc-lp/sanzaru/sanzaru-mcp)<a href="https://agentmods.dev/skills/tjc-lp/sanzaru/sanzaru-mcp"><img src="https://agentmods.dev/badge/skills/tjc-lp/sanzaru/sanzaru-mcp/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/tjc-lp/sanzaru/sanzaru-mcp"><img src="https://agentmods.dev/badge/skills/tjc-lp/sanzaru/sanzaru-mcp.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 | $0.00126 | $0.03312 |
| Opus 5.5 | $0.00050 | $0.01325 |
| Sonnet 5.5 | $0.00025 | $0.00662 |
| Haiku 4.5 | $0.00013 | $0.00331 |
Grade A, and why
sanzaru-mcp scanned grade A 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 19d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
the file into a code sandbox, no asking for a token or a URL to curl. The viewer already How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sanzaru MCP tools
How to drive the sanzaru MCP server. This skill is about the tool surface: which tool,
which arguments, how to wait. For prompt craft (what to say to a video or image model) load
prompt-guidance; for the shell CLI load sanzaru-cli.
Tool Quick Reference
| Category | Tool | Pattern | Description |
|---|---|---|---|
| Jobs | wait_for |
blocking | Wait for any mix of hf_*/resp_* ids in ONE call; download=true saves them too. Use this instead of polling get_*_status |
| Video | create_video |
async | Text- or image-to-video on Higgsfield (default Seedance 2.5; returns an hf_* id and the estimated cost — then wait_for it) |
edit_video |
async | Re-render an existing clip (Seedance 2.5); the source is billed too | |
extend_video |
async | Continue an existing clip by N seconds; the source is billed too | |
get_video_status |
one-off | Single status check; prefer wait_for for waiting |
|
download_video |
sync | Save a completed job's output (usually done by wait_for(download=true)) |
|
cancel_video |
sync | Cancel a job that is still queued (refunded) | |
list_local_videos |
sync | List downloaded video files | |
| Image | generate_image |
sync | Images API — returns the finished image (RECOMMENDED for one-shots) |
edit_image |
sync | Edit/compose images (up to 16 inputs, optional mask) | |
create_image |
async | Responses API — refinement chains (previous_response_id) and parallel batches; model picks the mainline model (gpt-6-astra default, gpt-5.6-sol/terra/luna) |
|
get_image_status |
one-off | Single status check; prefer wait_for for waiting |
|
download_image |
sync | Download completed image | |
| Inspect | inspect_image |
sync | See an image yourself — returns it as visual content; region zooms in to read small text |
inspect_video_frame |
sync | See frames from a video — the only way to check what a render actually shows (needs ffmpeg) | |
| Reference | list_reference_images |
sync | List start frames / edit inputs in the reference directory |
prepare_reference_image |
sync | Crop/pad an image to a video aspect ratio (aspect_ratio=) or exact size |
|
| Audio | create_audio |
sync | Text-to-speech — OpenAI (named voices) or ElevenLabs (voice id) |
transcribe_audio |
sync | Transcription (long files are windowed automatically) | |
chat_with_audio |
sync | Audio understanding / Q&A over a file | |
list_audio_files |
sync | List and filter audio files (substring or glob pattern, not regex) |
|
| Podcast | generate_podcast |
sync | The way to make a podcast — from a script, or from a topic (write the script yourself first). Recommended: ElevenLabs eleven_v4, render_mode: "dialogue", verify: true |
simulate_podcast |
sync | Experimental. Unscripted — realtime or gpt-live-1 agents converse from a rundown. Most expensive tool, variable results; only when an unscripted conversation is explicitly wanted. dry_run: true first, set max_cost_usd |
|
| Viewer | view_media |
sync | Opens a video/audio/image inline (MCP App), with a Download button where the host supports it |
What ships with it
1 file 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.
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.
- 19d ago Changed · +12 lines · +5 tokens per session 98b36264980e
- 20d ago Changed · +58 lines 32ed3ecbb537
- 1mo ago Changed · +12 lines acd5a080f766
- 1mo ago First seen · 108 lines · 121 tokens per session scan A 85c00f6e012c
sanzaru-mcp is a skill published in the GitHub repository TJC-LP/sanzaru (6 stars, last pushed 9d ago), licensed MIT. It adds 126 tokens to every session and 3,312 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-17.
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…