Prompt Budget Guardrails
- 1 installs
- 74 repo stars
- Updated August 4, 2026
- sbroenne/mcp-windows
Testing prompt guidance for usefulness while keeping prompt size and claims in check using paired content and token-budget assertions.
About
Provides patterns to validate MCP prompt templates for correct content plus relative token budgets. A developer uses it when changing prompt templates or prompt-discovery behavior and wants to keep scope honest.
- Pairs content assertions with relative token-budget assertions
- Adds prompt-discovery integration tests
Prompt Budget Guardrails by the numbers
- 1 all-time installs (skills.sh)
- Ranked #1,750 of 2,153 Testing & QA skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/sbroenne/mcp-windows --skill prompt-budget-guardrailsAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| repo stars | ★ 74 |
| Last updated | August 4, 2026 |
| Repository | sbroenne/mcp-windows ↗ |
What it does
Testing prompt guidance for usefulness while keeping prompt size and claims in check using paired content and token-budget assertions.
Files
Context
Use this when changing prompt templates, prompt-facing docs, or MCP prompt discovery behavior. It is especially useful when the product wants to ship new guidance quickly but QA needs to keep scope honest and token usage under control.
Patterns
- Pair content assertions with budget assertions. Verify the prompt says the right thing (for example, "best-effort" or "use metadata before pixels") and also verify it stays smaller than a broader baseline prompt.
- Prefer relative token budgets over fake absolutes for large canonical prompts. A browser-specific prompt should usually be smaller than the generic quickstart, even if the quickstart itself is not tiny.
- Add prompt discovery integration so the server actually exposes the prompt you just tested at unit level.
- For browser-adjacent validation, use the existing Electron/Chromium harness to test ARIA-label and search/navigation patterns safely before claiming real-browser parity.
Examples
tests/Sbroenne.WindowsMcp.Tests/Unit/Prompts/WindowsAutomationPromptsTests.cstests/Sbroenne.WindowsMcp.Tests/Integration/PromptDiscoveryTests.cstests/Sbroenne.WindowsMcp.Tests/Integration/ElectronHarness/UIAutomationElectronTests.cs
Anti-Patterns
- Do not call a prompt "token-efficient" without a budget-oriented assertion.
- Do not upgrade docs from Electron/Chromium confidence to full browser support without real browser coverage.
- Do not use tool-hint-heavy prompt tests; keep them focused on the task and the guidance being shipped.
Related skills
TddFollow test-driven development with a strict red-green-refactor loop when creating reliable features or fixing bugs.544k196k
Test Driven DevelopmentEnforce writing failing tests before any production implementation code.181k264kQaRun conversational QA sessions that turn user-reported bugs into well-written, domain-aware GitHub issues without manual ticket writing.179k196kMigrate To ShoehornAutomatically update TypeScript test files that rely on unsafe `as` type assertions by replacing them with type-safe partial objects from @total-typescript/shoehorn.164k196k
Webapp TestingVerify frontend behavior, debug UI issues, capture screenshots, and inspect logs of a running local web application using Playwright.123k165k
Playwright CliRun browser automation, generate element snapshots, inspect DOM attributes, and execute Playwright tests from the terminal.102k12.3k