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 agentmods add skills/microsoft/flint-chart/flint-theme-authornpx skills add microsoft/flint-chart --skill flint-theme-authorgit clone --depth 1 https://github.com/microsoft/flint-chartWhat 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 | $0.00064 | $0.02139 |
| Opus 5 | $0.00032 | $0.01069 |
| Sonnet 5 | $0.00013 | $0.00428 |
| Haiku 4.5 | $0.00006 | $0.00214 |
Grade A, and why
flint-theme-author 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 3d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flint ThemeSpec authoring
Create a reusable visual system for Flint charts. Translate the user's reference
materials into one valid ThemeSpec that can be pasted directly into Theme Lab.
Authoritative references
Read these before authoring. When prose and source disagree, the TypeScript contract is authoritative.
- Theme guide: https://github.com/microsoft/flint-chart/blob/main/docs/theme-spec.md
- Exhaustive ThemeSpec types and allowed values: https://github.com/microsoft/flint-chart/blob/main/packages/flint-js/src/core/theme/types.ts
- Real preset implementations: https://github.com/microsoft/flint-chart/tree/main/packages/flint-js/src/core/theme/presets
- Theme Lab: https://microsoft.github.io/flint-chart/#/theme-lab
Do not invent keys. If a requested decision cannot be represented by
ThemeSpec, omit it and briefly identify the unsupported decision outside the
JSON only when the user asked for an explanation.
Output contract
Unless the user asks for commentary, return exactly one valid JSON object:
- Return the bare
ThemeSpec, not{ "theme_spec": ... }and not a completeChartAssemblyInput. - Do not wrap JSON in a Markdown fence.
- Do not include comments, placeholders, ellipses, or trailing commas.
- Include a stable kebab-case
idand a human-readablelabel. - Include only supported fields and only decisions justified by the references.
- Omit unspecified optional fields rather than guessing.
The top-level output schema is:
{
"extends": "optional-preset-id",
"id": "theme-id",
"label": "Theme label",
"ink": {},
"type": {},
"structure": {},
"marks": {},
"labels": {},
"legend": {},
"dataLabels": {},
"annotation": {},
"furniture": [],
"facets": {},
"layout": {},
"chartDefaults": {},
"compileDefaults": {},
"interaction": {},
"variants": []
}
Every block except id and label may be omitted. The skeleton shows the
shape, not a requirement to emit empty blocks.
Theme boundary
A theme controls presentation and compiler behavior across many charts. It may decide color, typography, surfaces, grids, axes, mark geometry, labels, legends, annotations, density, spacing, facets, and reusable chart defaults.
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.
- 3d ago First seen · 203 lines · 64 tokens per session scan A e1d84f72850f
flint-theme-author is a skill published in the GitHub repository microsoft/flint-chart (4,094 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 2,139 once invoked, about $0.0003 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
build-power-bi-report
Use when the user wants to build, design, or scaffold a Power BI report or dashboard. Triggers on phrases like "build a Power BI report", "create a dashboard", "make a sales report", "design a Power BI page", "add a page to my report", "I need a report for X". Covers requirements elicitation — what to ask the user…
wireframe-power-bi-page
Use when planning the layout of a Power BI report page. Triggers on phrases like "wireframe a page", "layout for a dashboard", "where should I put the visuals", "design the page layout", "how should I arrange these visuals". Covers canvas geometry (1280x720), 5 validated layouts, the pbirlayoutgrid tool, spacing math.
design-power-bi-report
Use when polishing or theming a Power BI report — typography, colors, KPI cards, slicer placement, formatting taste decisions. Triggers on phrases like "make my report look better", "improve the design", "what colors should I use", "format this dashboard", "report doesn't look professional".
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.…
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…