{
  "markdown": "# tailtest -- AI software testing for Claude Code\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-emerald.svg)](https://opensource.org/licenses/MIT)\n[![Tests](https://img.shields.io/badge/tests-491_passing-emerald)](https://github.com/avansaber/tailtest)\n[![Version](https://img.shields.io/badge/version-3.14.0-blue)](https://github.com/avansaber/tailtest/releases/latest)\n[![Platform](https://img.shields.io/badge/platform-macOS_%7C_Linux-lightgrey)](https://tailtest.com/platform/agent-edits/)\n\n> You build. Claude builds. tailtest makes sure it works.\n\n**tailtest** is the open-source AI software testing layer for [Claude Code](https://www.anthropic.com/claude-code). It runs inside the build loop: every time Claude edits a file, tailtest queues the file, generates production-shaped scenarios using the R1-R15 rule layer, runs them with your existing test runner (pytest, jest, go test, etc.), and surfaces failures back to Claude within the same turn. Hook-based. Deterministic. No prompting required.\n\nOpen source (MIT), no telemetry, no SaaS account. Includes adversarial mode (R15) that biases scenario generation toward 8 breakage categories -- the mode we've used to find 16 real bugs across 47 open-source Python repositories.\n\n**[Read more on tailtest.com](https://www.tailtest.com/) · [Platform overview](https://www.tailtest.com/platform/) · [Agent-edit testing deep dive](https://www.tailtest.com/platform/agent-edits/) · [Full docs](https://www.tailtest.com/docs/)**\n\n---\n\n## Install\n\n```bash\nclaude plugin marketplace add avansaber/tailtest\nclaude plugin install tailtest@avansaber-tailtest\n```\n\nRestart Claude Code after install. No other setup required.\n\n## Update\n\n```bash\nclaude plugin marketplace update avansaber-tailtest\nclaude plugin update tailtest@avansaber-tailtest\n```\n\n## Uninstall\n\n```bash\nclaude plugin remove tailtest@avansaber-tailtest\n```\n\n---\n\n## How it works\n\nAfter any Claude-written file lands in your project:\n\n1. tailtest generates scenarios that describe real business behavior -- not function signatures\n2. It runs them using your existing test runner (pytest, vitest, jest, go test, and more)\n3. Pass: `tailtest: N scenarios -- all passed.` Fail: one line surfaced, \"want me to fix this?\"\n\n---\n\n## Supported languages\n\nPython, TypeScript, JavaScript, Go, Ruby, PHP, Java, Kotlin, C#, Rust\n\nRunners are auto-detected from `pyproject.toml`, `package.json`, `go.mod`, `build.gradle.kts`, `*.csproj`, `*.sln`, and other standard manifests.\n\n---\n\n## Quick config\n\nCreate `.tailtest/config.json` in your project root to control depth:\n\n```json\n{ \"depth\": \"standard\" }\n```\n\nOptions: `simple` (2-3 scenarios), `standard` (5-8, default), `thorough` (10-15).\n\nSee [tailtest.com/docs/config](https://tailtest.com/docs/config) for all options.\n\n---\n\n## Other tailtest variants\n\nSame R1-R15 rule layer, same adversarial test mode, different host integration. **This repo is the Claude Code variant.**\n\n- **[tailtest](https://github.com/avansaber/tailtest)** -- Claude Code plugin (hook-driven; this repo)\n- **[tailtest-cursor](https://github.com/avansaber/tailtest-cursor)** -- Cursor plugin (hook-driven)\n- **[tailtest-codex](https://github.com/avansaber/tailtest-codex)** -- Codex CLI plugin (hook-driven)\n- **[tailtest-cline](https://github.com/avansaber/tailtest-cline)** -- Cline plugin (MCP-driven; reaches 8+ editors via Cline's host coverage)\n\nSee [tailtest.com/demo/claude-code](https://tailtest.com/demo/claude-code) for a live walkthrough of this variant, or [tailtest.com/comparison](https://tailtest.com/comparison) for a feature matrix across all four.\n\n---\n\n## License\n\nMIT\n",
  "bytes": 3633,
  "sha": "4d85d6cc35149f342512f974e9ae2c7988e0d08c493b78c91a920a0e8a68b629",
  "repo_slug": "avansaber/tailtest",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_avansaber_tailtest_tailtest_e35ef3fb/readme"
}