Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/malloydata/publishernpx agentmods add skills/malloydata/publisher/malloy-dashboardsWrote 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/malloydata/publisher/malloy-dashboards)<a href="https://agentmods.dev/skills/malloydata/publisher/malloy-dashboards"><img src="https://agentmods.dev/badge/skills/malloydata/publisher/malloy-dashboards/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/malloydata/publisher/malloy-dashboards"><img src="https://agentmods.dev/badge/skills/malloydata/publisher/malloy-dashboards.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 179 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00073 | $0.06872 |
| Opus 5 | $0.00036 | $0.03436 |
| Sonnet 5 | $0.00015 | $0.01374 |
| Haiku 4.5 | $0.00007 | $0.00687 |
Grade A, and why
malloy-dashboards 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 yesterday.
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 — 476 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publisher Dashboards
A
dashboards/*.malloyfile is a dashboard. It imports the model, either declares one query and applies its own filtering or names views that already do, and tags the layout. Publisher discovers it at package load, renders the filter controls from the givens it references, offers# drillclick-through between pages, and serves it at/<env>/<pkg>/dashboards/<name>. No code, no build step.
When this is the right tool
| The user wants | Use |
|---|---|
| A recurring, at-a-glance view behind shared filters | this skill (a dashboard) |
| A narrative, with prose between the numbers | a notebook (skill:malloy-notebooks) |
| Custom design, branding, or interactions beyond tags | an HTML data app (skill:malloy-html-data-apps) |
| The model itself: sources, measures, joins | skill:malloy-modeling |
Notebooks and dashboards run the same engine, so interactivity is not the axis: both get filter
controls, URL-addressable state, Apply batching, and # drill. Pick on the shape of the document.
Scanned at a glance is a dashboard; read top to bottom is a notebook.
Build sequence
- READ THE MODEL FIRST. Get the real source, view, dimension, and given names from the package:
get_contextif you have it, otherwise the REST model endpoint or the.malloyfiles. Never guess a name. A guessed field in a query fails the whole package load, not just that one dashboard; a guessed tile or suggest source is quieter, and only shows up in the package warnings. - PICK THE VIEWS TO SHOW. A dashboard is
## artifact { tiles=[…] }naming existing views, so this is the design step: which views, how wide each sits, what each is called. There is one form, so there is no form to choose. - DECLARE THE GIVENS the dashboard will filter by, in the model (usually
givens.malloy), with their control tags: see "Filter controls" below for the syntax and what each tag renders as. Skip if they already exist, since a given is a model concern and dashboards share them. - COMPOSE THE FILE for
dashboards/, following the template below, but do not save it yet. Import every given it filters by, and every source or query any of those givens names in asuggest. Both are per-file, and getting the suggest wrong does not error: the control still looks like a picker but has no options, and says so underneath, "Could not load the options for this control". The package warnings name it too. Asuggestnaming aquery=needs that query's own source imported as well, because an import is not transitive: the query resolves by name, so the file compiles and the package loads, but running the picker fails withUndefined source '<name>'. The package warnings name this one too, saying which source to import. Import the source that suggest query reads, not just the query. - COMPILE IT with
compile_model(orPOST …/models/<path>/compile), against the source text, before you save, at the path the file will have. Editing one that already exists needs"scope": "file", which compiles your source AS that file; the default appends it instead, so every imported name and the query name collide with the saved copy and you get a wall of already-defined errors that reads as broken Malloy rather than a wrong scope. Editing a shared include wants"scope": "package", which recompiles every file as saved:fileonly checks the one you are editing, so renaming a source in_shared.malloypasses it while breaking every dashboard that imports it. A clean compile is not a working dashboard: some tag mistakes surface at step 6, and some only when you look at the page in step 7. (The third scope,append, is the default and is what a not-yet-saved file gets.) - SAVE IT, RELOAD, AND READ THE MANIFEST AND THE WARNINGS.
reload_package, orGET …/packages/<pkg>?reload=true. Check the status the reload returns as well as the warnings: a 424 means the package did not load and your edit is not live. Thewarningskey is absent when there are none, so an empty response is the pass, not a sign you are reading the wrong field. Then readGET …/packages/<pkg>/dashboards/<name>: itsgivensare exactly the controls that will render, which catches a given you imported but never referenced before you open the page, and itsqueryis the name to run in step 7. See "Read the lint" below. - OPEN IT AND LOOK. Not optional; see "What 'done' means".
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.
- yesterday Changed a12f4a41cc35
- 10d ago First seen · 476 lines · 73 tokens per session scan A 95cd2663d41b
malloy-dashboards is a skill published in the GitHub repository malloydata/publisher (100 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 6,872 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
reimagine-it-extract
Emit the content signals reimagine-it reads from an HTML file — title, anchors, proper nouns, dates, numbers, emails, links, source hex colors, and the derived palette — as JSON without generating a redesign. Use when the user says /reimagine-it extract, "what does the engine see in this page", "extract the palette"…
reusable-visualization
Build ONE reusable chart visualization component that receives its data and its settings from the host application instead of fetching them, and declares the fields and config options the host exposes to viewers. Use this whenever a single chart component is reused across many different queries rather than built for…
lightdash-agent-slack-messaging
Use this skill when writing, designing, or generating Slack messages for Lightdash's in-app analytics agent. Triggers when someone asks to create agent update messages, Slack digests, agent notifications, weekly summaries, daily summaries, or any Slack copy for the Lightdash project agent. Also use when asked to vary…
developing-in-lightdash
Use when reading, creating, and editing Lightdash dashboards and charts as JSON, including dashboard layout and chart-type-specific configuration.
upgrade-preflight
Checks whether a self-hosted Lightdash upgrade is safe to run, and reads the tooling's answer without over-reading it. Use when upgrading a self-hosted instance, planning a maintenance window, answering "is this upgrade safe", or recovering a failed, hung, parked or lock-stuck migration — covers lightdash…
developing-data-apps-locally
Use when editing a locally created or downloaded Lightdash data app — how local editing, building, and uploading work, and what is read-only.