Vizro is an open-source Python toolkit for assembling data visualization applications from low-code configuration. It helps developers create dashboards and multi-page apps from charts, tables, controls, layouts, navigation, and interactions, with optional high-code customization. Catalogue add-ons support working with Vizro projects.
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 mckinsey/vizro --skill wiring-vizro-actionsgit clone --depth 1 https://github.com/mckinsey/vizroWrote 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/mckinsey/vizro/wiring-vizro-actions)<a href="https://agentmods.dev/skills/mckinsey/vizro/wiring-vizro-actions"><img src="https://agentmods.dev/badge/skills/mckinsey/vizro/wiring-vizro-actions/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/mckinsey/vizro/wiring-vizro-actions"><img src="https://agentmods.dev/badge/skills/mckinsey/vizro/wiring-vizro-actions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00086 | $0.01996 |
| Opus 5.5 | $0.00034 | $0.00798 |
| Sonnet 5.5 | $0.00017 | $0.00399 |
| Haiku 4.5 | $0.00009 | $0.00200 |
Grade A, and why
wiring-vizro-actions 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 21d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiring Vizro Actions
Core concept: Source → Control → Target
All advanced interactions follow the same shape:
- A source component triggers
va.set_controlswhen the user clicks it. Practical sources arevm.Graphandvm.Table— they carry click-data (column values from the clicked point/cell) that can drive a dynamic filter. (vm.Figure/vm.Button/vm.Cardtechnically supportset_controlstoo, but only with a hardcoded literalvalue, so they are not useful for cross-filtering.) set_controlswrites a value into an intermediate control (vm.Filterorvm.Parameter) with an explicitid.- The control updates target components. Filter/Parameter targets are data-bearing components:
vm.Graph,vm.Table,vm.Figure,vm.Table.
The control is always explicit — you do not connect components directly. This makes interactions composable (you can wire multiple sources to the same control, or one source to multiple controls).
Built-in actions
| Action | Purpose | Trigger |
|---|---|---|
va.export_data() |
Download all on-page data as CSV (respects filters) | vm.Button |
va.set_controls(controls=..., value=...) |
Set the value of a Filter or Parameter | vm.Graph or vm.Table |
import vizro.actions as va. Built-in actions are passed directly into actions= — wrapping them in vm.Action raises an error (deliberate: built-ins have their own predefined inputs/outputs and would conflict with vm.Action's).
# Correct
vm.Button(text="Export data", actions=va.export_data())
vm.Graph(actions=va.set_controls(controls="region_filter", value="y"))
# Wrong — raises an exception
vm.Graph(actions=[vm.Action(function=va.set_controls(...))])
Named interaction patterns
Match data shape + user need to a pattern. Full details (when-to-use, wireframes, spec entries, code) in actions-reference.md.
| # | Pattern | When to use | Key mechanic |
|---|---|---|---|
| 1 | Hierarchical Drill-Down (cross-page) | 2–3 level hierarchy where detail needs a dedicated page | cross-filter + show_in_url=True + back button + export |
| 2 | Single-Page Drill-Down (container) | 2-level hierarchy where detail fits in a container | cross-filter into a container |
| 3 | Comparison Spotlight (cross-highlight) | Compare one entity against many without removing context | custom chart with highlight_X + invisible Parameter |
| 4 | Multi-Dimensional Slice | 2+ categorical dimensions (e.g. day × time heatmap) | actions chain → multiple Filters |
| 5 | Data Export | Analyst persona needs the filtered data downloaded | vm.Button + va.export_data() |
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.
- 21d ago Changed c1b7282076a3
- 2mo ago First seen · 168 lines · 86 tokens per session scan A 6fdcf7b25045
wiring-vizro-actions is a skill published in the GitHub repository mckinsey/vizro (3,817 stars, last pushed today), licensed Apache-2.0. It adds 86 tokens to every session and 1,996 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
developing-with-streamlit
Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit apps. Also custom components, st.components.v2, HTML/JS/CSS work. Discovers and loads version-matched reference docs from the user's installed Streamlit (>=1.57). Triggers: streamlit, st.…
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), workspaces, structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, attach a workspace, defer capability…
marimo-pair
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.
pydantic-ai-harness
Extend Pydantic AI agents with capabilities from pydantic-ai-harness -- the Coder coding agent, file and shell tools in local or sandboxed workspaces (Modal, E2B, Sprites, Daytona, boxd, smolvm, BoxLite), Code Mode, sub-agents and planning, memory and skills, context compaction, guardrails and spend limits, web…
fill-model-descriptions
Curate descriptions and provider-specific reasoning options and token limits in packages/llm-info/data/models.yml using models.dev, OpenRouter, and provider documentation. Use when the user asks to populate model descriptions, enrich the model catalog, or curate descriptions after running pnpm sync-models.
migrating-langchain-to-pydantic-ai
Migrate Python LangChain, LangGraph, or Deep Agents applications to Pydantic AI and, when the source uses harness features, Pydantic AI Harness. Use for LangChain agents, chains, LCEL, direct LangGraph graphs, persistence, interrupts, streaming, and createdeepagent projects with planning, filesystem or sandbox…