# Test Runner > Run tests in Fast/Full modes using repo-defined entrypoints (PROJECT.md/scripts) and report minimal, actionable results. Use when this capability is needed. - Skill: `tomevault-io/test-runner-9` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/test-runner-9` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/test-runner-9/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/test-runner-9 --- # test-runner Purpose: Execute tests with minimal friction and report results clearly. ## Inputs - PROJECT.md (how to run / quality gates) - Repo scripts/entrypoints (Makefile/Taskfile/package scripts/CI) - Optional: TASK-xxx Verification lines (if available) ## Modes - Fast (default): run tests only, smallest set that gives quick feedback. - Full: run the full suite as defined by the repo (may include integration/e2e). ## Command selection (prefer repo entrypoints) Pick commands in this order: 1) PROJECT.md 2) Repo entrypoints: make/task/just/package scripts 3) Fallback by stack if no entrypoint exists (ask before running if unsure) ## Output - Mode: Fast/Full - Commands executed + exit code - Short failure excerpt + pointer when --- > Converted and distributed by [TomeVault](https://tomevault.io/claim/jpiedrafita) — claim your Tome and manage your conversions.