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/saski/arnesto/building-data-appsnpx skills add saski/arnesto --skill building-data-appsgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/building-data-apps)<a href="https://agentmods.dev/skills/saski/arnesto/building-data-apps"><img src="https://agentmods.dev/badge/skills/saski/arnesto/building-data-apps.svg" alt="Measured on agentmods" 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 | $0.00218 | $0.01347 |
| Opus 5 | $0.00109 | $0.00674 |
| Sonnet 5 | $0.00044 | $0.00269 |
| Haiku 4.5 | $0.00022 | $0.00135 |
Grade A, and why
building-data-apps 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.
This is a copy
94% identical to building-data-apps — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building Data Applications
Architect high-quality data dashboards and interactive reports. You MUST select the appropriate framework before implementation.
Step 0: Framework Selection
You MUST select the framework based on the user's maintenance requirements and data ecosystem.
Choice: Streamlit
- User Profile: Data Scientists / Python users.
- Logic Complexity: High Python dependency (Pandas, NumPy, local data processing).
- Deployment: Single-file Python script.
- Customization: Standard layout (fast boilerplate).
Choice: React + Vite
- User Profile: Web Developers / Full-stack teams.
- Logic Complexity: High UI and Interactivity requirements (e.g., drag-and-drop, interactive maps).
- Deployment: Standalone Frontend + Backend API.
- Customization: Infinite (Custom CSS, specialized JS libraries).
Guidance:
- Check for existing stack first: ALWAYS prefer the framework the user is
already using in their project (e.g., if you see a
package.jsonwith React dependencies, use React; if you see existing Streamlit files, use Streamlit). - Default to React + Vite for production-grade applications that require complex client-side state, custom branding, or integration into a larger web ecosystem.
- Default to Streamlit if the user specifically mentions "Python dashboard", needs to iterate on complex local Python data processing, or requires a single-script deployment.
Step 1: Implementation Plan
You MUST propose a plan to the user that specifies the chosen framework and justifies the choice based on the criteria above.
Shared Design Standards
Regardless of framework, you MUST follow the principles in
resources/shared_design_system.md.
- Visual Style: Minimal chrome, zinc color palette, and card-based layouts.
- Typography:
DM Sansfor content,JetBrains Monofor data.
What ships with it
7 files 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.
- 3d ago First seen · 158 lines · 218 tokens per session scan A 7036b861cba7
building-data-apps is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed 8d ago), licensed Unlicense. It adds 218 tokens to every session and 1,347 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to building-data-apps, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
pixir-delegate
Use Pixir as a headless subagent runtime from Claude Code or any harness with skill ! preprocessing (Codex roots and other no-hydration hosts use pixir-delegate-codex instead) — one-shot workers (pixir --json), parallel fan-out to N children (pixir delegate --spec), resumable steering (pixir resume), evidence…
pixir-delegate-codex
Use when a Codex CLI/Desktop root should fan out subagents, delegate to Pixir workers, run parallel workers, or manage a resident delegation daemon via Pixir Delegate; covers Codex preflight, AGENTS.md, approvals/sandbox, dry-run, daemon start/status/attach/cancel, closure evidence, and audited single-run execution…
pixir-diagnostics
Diagnose Pixir and T3 Code Pixir incidents from local canonical evidence. Use when a Pixir run, ACP/T3 thread, subagent/workflow, provider replay, or daily-driver dogfood session appears stuck, inconsistent, missing tool output, or hard to classify.
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.
pixir-delegate-native
Delegate work to subagents from INSIDE a Pixir session using the native Subagent tools (spawnagent, waitagent, closeagent, listagents, sendinput) instead of shelling out to the pixir CLI. Use when you are a Pixir session that needs to fan out parallel workers, steer a child, or run skill-backed workflow templates …
repo-contracts-and-boundaries
Use when turning architecture, layering, ownership, dependency direction, schemas, structural metrics, quality thresholds, baselines, allowlists, or generated quality snapshots into repository checks.