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 d-padmanabhan/agent-engineering-handbook --skill single-file-dashboardgit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/single-file-dashboard)<a href="https://agentmods.dev/skills/d-padmanabhan/agent-engineering-handbook/single-file-dashboard"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/single-file-dashboard/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/d-padmanabhan/agent-engineering-handbook/single-file-dashboard"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/single-file-dashboard.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 | $0.00146 | $0.03830 |
| Opus 5 | $0.00073 | $0.01915 |
| Sonnet 5 | $0.00029 | $0.00766 |
| Haiku 4.5 | $0.00015 | $0.00383 |
Grade A, and why
single-file-dashboard 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 9d 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 — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Single-File Dashboard
How to ship analytical artifacts as single-file, fully self-contained, zero-dependency HTML dashboards that render identically online, offline, on an airgapped laptop, and inside an email client.
Companion rules:
800-markdown.mdc- markdown formatting for prose deliverables810-documentation.mdc- documentation patterns815-reactflow-diagrams.mdc- interactive React Flow canvases (the other dashboard pattern; see contrast below)
When to invoke
Use when the user asks for:
- "Build a dashboard" / "interactive HTML report" / "shareable analysis"
- "Offline dashboard" / "airgap-safe" / "for the client" / "for the regulator"
- "Visualize this workbook" / "turn this CSV into a presentable view"
- An executive-style deliverable for client / leadership / regulator review
- Anything that must render without internet access
Do not use for:
- React applications (use a real frontend stack)
- Embedded analytics inside a webapp (use a charting library and your build pipeline)
- Real-time / streaming dashboards (use Grafana / Datadog / Looker)
- Interactive architecture canvases with custom nodes / edges - use
815-reactflow-diagrams.mdcand the React Flow skill instead
The Six Golden Rules
- One file. Zero dependencies. No CDN, no remote scripts, no web fonts, no images. Inlined CSS, inlined JS, inlined data, inlined SVG.
- Inline vanilla SVG for charts. No D3, Chart.js, ECharts, or React. Vanilla SVG renders everywhere; libraries do not.
- Escape user content. Every string pulled from data must be HTML-escaped. Never bypass.
- Renders identically offline. Test by disabling network; the dashboard must look unchanged.
- Renders identically in email. Open the file in Gmail / Outlook / Apple Mail (as an attachment); layout must hold.
- Re-runnable, not editable. Never edit generated HTML. Edit the generator and re-run.
When to choose this pattern vs alternatives
| Need | Use this skill | Use React Flow | Use real BI tool | Use Markdown |
|---|---|---|---|---|
| Client / executive deliverable; must be emailable | yes | no | no | maybe |
| Airgap / regulated environment | yes | possibly (still SPA) | no | yes |
| Interactive architecture canvas with custom nodes | no | yes | no | no |
| Real-time / streaming data | no | no | yes | no |
| Analytical workbook -> shareable HTML | yes | no | maybe | no |
| Live KPIs across many sources | no | no | yes | no |
| Static narrative document | no | no | no | yes |
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.
- 9d ago First seen · 392 lines · 146 tokens per session scan A 98487cd54f2a
single-file-dashboard is a skill published in the GitHub repository d-padmanabhan/agent-engineering-handbook (17 stars, last pushed today), licensed MIT. It adds 146 tokens to every session and 3,830 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.