Borrowing it
Nothing to install: this file belongs to day-ai/day-ai-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/day-ai/day-ai-sdk/master/.claude/commands/app.mdgit clone --depth 1 https://github.com/day-ai/day-ai-sdkWrote 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/commands/day-ai/day-ai-sdk/app)<a href="https://agentmods.dev/commands/day-ai/day-ai-sdk/app"><img src="https://agentmods.dev/badge/commands/day-ai/day-ai-sdk/app/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/commands/day-ai/day-ai-sdk/app"><img src="https://agentmods.dev/badge/commands/day-ai/day-ai-sdk/app.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 | $0.00000 | $0.01939 |
| Opus 5.5 | $0.00000 | $0.00776 |
| Sonnet 5.5 | $0.00000 | $0.00388 |
| Haiku 4.5 | $0.00000 | $0.00194 |
Grade A, and why
app 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 29d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/app - Guide User Through Building a New App
When the user runs /app, help them create a new application integrated with Day AI. Guide them through the planning and implementation process.
Step 1: Understand Their Goal
Ask clarifying questions to understand what they want to build:
Questions to Ask:
- What problem are you trying to solve?
- What will users do with this app?
- What data will it work with? (notes, tasks, bugs, opportunities, etc.)
- Where will it run? (desktop, web, CLI, mobile, serverless)
- Will it be interactive (chat interface) or automated (cron job, background task)?
Step 2: Choose a Template
Based on their answers, recommend one of our example apps as a starting point:
Desktop Apps (Electron + React)
Use examples/desktop/ when:
- User wants a native desktop application
- Needs a rich UI with multiple panels/views
- Wants real-time interaction with an AI agent
- Working with local data that needs persistence
- Example use cases: bug tracker, note-taking, CRM dashboard, project manager
Template provides:
- Electron main/renderer architecture with IPC
- React + TypeScript + Tailwind UI
- Claude AI chat with streaming
- Day AI OAuth + MCP integration
- Native tools (CRUD operations on local data)
- Glass-morphism dark theme
Agent with no UI (Claude Agent SDK)
Use the Agent SDK pattern from the README ("Build an agent") when:
- The job is "ask Claude to do something with Day AI data" with no custom UI
- Scripts, Slack bots, scheduled reports that need judgment
- Connect Day AI with
mcpServersandallowedTools: ['mcp__day-ai__*']; no tool code needed
Serverless Automation (Vercel/Next.js)
Use examples/vercel-weather-cron/ when:
- User wants scheduled automation (cron jobs)
- Needs to enrich Day AI CRM with external data
- Building a notification/digest system
- No heavy UI required (simple dashboard for testing)
- Example use cases: daily digests, data sync, monitoring alerts, scheduled reports
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.
- 29d ago Changed · +9 lines b259ea596326
- 2mo ago First seen · 219 lines · 0 tokens per session scan A 5e83467f709a
app is a command published in the GitHub repository day-ai/day-ai-sdk (24 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,939 tokens. 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.
app compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| appday-ai/day-ai-sdk | Command | 24 | yesterday | MIT | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |