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/drvoss/everything-copilot-cli/prototypenpx skills add drvoss/everything-copilot-cli --skill prototypegit clone --depth 1 https://github.com/drvoss/everything-copilot-cliWhat 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 | $0.00039 | $0.01023 |
| Opus 5 | $0.00019 | $0.00511 |
| Sonnet 5 | $0.00008 | $0.00205 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
prototype 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype
A prototype is disposable code that answers a question faster than debate. Keep it close to the real area, make it easy to run, and optimize for learning rather than polish.
When to Use
- The user says "prototype this", "try a few designs", or "let me play with it"
- A state model or workflow is hard to reason about on paper
- You need several UI directions before picking one
- The fastest way to answer the question is to build a small runnable artifact
When NOT to Use
| Instead of prototype | Use |
|---|---|
| You are building production-ready functionality | spec-driven-development |
| The main problem is root-cause analysis of broken code | diagnose |
| You already know the design and need safe cleanup | refactor-clean |
Prerequisites
- A concrete question the prototype should answer
- A place near the target code where throwaway work can live temporarily
- One obvious command the user can run locally
Workflow
1. Choose the branch
Decide which question you are answering:
- Logic / state question — build a tiny runnable terminal or script-based prototype that pushes the state machine through the tricky cases
- UI question — build several clearly different visual variants that can be switched from one route, page, or entry point
If the question is ambiguous and the user is unavailable, match the surrounding code and state the assumption clearly at the top.
2. Mark it as throwaway from day one
Put the prototype near the feature it informs, but name it so nobody confuses it with production code. Follow the project's existing routing or directory conventions instead of inventing a brand-new top-level structure.
3. Make it runnable with one command
Use the project's existing runtime:
npm run prototype:checkoutpython src\feature\prototype.pygo run .\cmd\prototype
The user should not need a multi-step setup just to learn from the prototype.
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 · 128 lines · 39 tokens per session scan A fe732815d8a3
prototype is a skill published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 6d ago), licensed MIT. It adds 39 tokens to every session and 1,023 once invoked, about $0.0002 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
winui-ui-testing
Automated UI testing for Windows desktop apps — generate a batch test script with the winapp ui UI Automation harness, run all tests in one pass, read results. Covers element assertions, interactions, value checking (TextBox, ComboBox, ToggleSwitch), keyboard shortcuts and typing (send-keys), hover, drag-and-drop…
pr-review
Multi-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate on "review my PR / changes / branch", "vet before pushing", "PR review", "is this ready to merge". Fans out parallel sub-agents over skill content, the skill-vs-tool boundary (solution hierarchy), tool correctness…
winui-packaging
MSIX packaging, code signing, and distribution for WinUI 3 apps — build for release, certificate generation (winapp cert generate), certificate trust, code signing (winapp sign), self-contained deployment, CI/CD with GitHub Actions, and Microsoft Store submission. Use when preparing for release, creating MSIX…
winui-session-report
Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.
winui-wpf-migration
Migrate WPF applications to WinUI 3 — namespace replacement (System.Windows → Microsoft.UI.Xaml), control mapping (DataGrid→ListView, WrapPanel→ItemsRepeater, TabControl→TabView), threading (Dispatcher→DispatcherQueue), imaging (System.Drawing→BitmapImage), MVVM conversion to CommunityToolkit.Mvvm, and…
copilotd-e2e-verification
Perform real end-to-end validation of copilotd issue and pull request orchestration using live GitHub artifacts.