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 santoshkanthety/powerbi-agent --skill powerbi-modifying-theme-jsongit clone --depth 1 https://github.com/santoshkanthety/powerbi-agentWrote 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/santoshkanthety/powerbi-agent/powerbi-modifying-theme-json)<a href="https://agentmods.dev/skills/santoshkanthety/powerbi-agent/powerbi-modifying-theme-json"><img src="https://agentmods.dev/badge/skills/santoshkanthety/powerbi-agent/powerbi-modifying-theme-json/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/santoshkanthety/powerbi-agent/powerbi-modifying-theme-json"><img src="https://agentmods.dev/badge/skills/santoshkanthety/powerbi-agent/powerbi-modifying-theme-json.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 | $0.00180 | $0.04241 |
| Opus 5 | $0.00090 | $0.02121 |
| Sonnet 5 | $0.00036 | $0.00848 |
| Haiku 4.5 | $0.00018 | $0.00424 |
Grade A, and why
powerbi-modifying-theme-json 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 12d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power BI Report Themes
Why Themes Matter
A report without a well-designed theme accumulates formatting debt. Every visual ends up with its own bespoke title size, shadow toggle, border style, and hardcoded colors in visual.json. This creates three problems:
- Inconsistency. Visuals drift apart as authors format each one individually. One card has 14pt titles, another has 12pt; one chart has shadows, another doesn't. The report looks unfinished.
- Fragility. Rebranding or updating the visual style means touching every visual.json individually. A report with 40 visuals across 8 pages means 40 files to edit. With a theme, it's one file.
- Bloated visual JSON. Each bespoke override adds lines to visual.json, making reports harder to diff, review, and maintain. A clean visual.json should contain field bindings, position, and conditional formatting; everything else should come from the theme.
Reports using the default Power BI theme or a minimal custom theme (just dataColors and a name) are leaving most formatting to Power BI's built-in defaults, which change between Desktop releases. A well-designed theme locks in the intended appearance.
Signs a theme needs attention:
- Many visuals have
objectsorvisualContainerObjectswith redundant formatting - Visuals of the same type look inconsistent (different title fonts, shadows on some but not others)
- The theme JSON has few or no
visualStylesentries - The report uses a built-in theme like "Default" or "Classic" without customization
Tooling preference: Use
pbirCLI when available (pbir theme colors,pbir visuals clear-formatting). Fall back to directjqmodification when unavailable. Always validate after every write.
Tip: Theme JSON files can be 75KB+ and 2000+ lines. Do not read the full monolithic file. Use
pbir theme serializeto split into small editable files (see Author/Modify workflow below), or usejqto extract only specific keys. Serialized fragments from the serialize/build workflow are small and safe to read directly.
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.
- 12d ago First seen · 310 lines · 180 tokens per session scan A 5d6143384983
powerbi-modifying-theme-json is a skill published in the GitHub repository santoshkanthety/powerbi-agent (2 stars, last pushed 12d ago), licensed MIT. It adds 180 tokens to every session and 4,241 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
dashboard_composer
Skill "dashboard_composer" from G-Schumacher44/strata-oss, covering skill: dashboardcomposer, trigger, inputs, allowed tools and forbidden.
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
sxo
Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…
journey-mapping
Build customer journey maps and service blueprints that visualize the end-to-end user experience including touchpoints, emotions, friction, and underlying systems. Use this skill whenever the user wants to map a customer journey, build a service blueprint, identify friction across an experience, align teams on the…
shiny-bslib
Build modern Shiny dashboards and applications using bslib (Bootstrap 5). Use when creating new Shiny apps, modernizing legacy apps (fluidPage, fluidRow/column, tabsetPanel, wellPanel, shinythemes), or working with bslib page layouts, grid systems, cards, value boxes, navigation, sidebars, filling layouts, theming…