Back to directory
avansaber avatar
avansaber / tailtest

tailtest

tailtest auto-generates and runs tests for every file your AI agent edits in Claude Code. R1-R15 rule layer + adversarial test mode (V13).

9

Stars

0

Forks

0

Watchers

MIT

License

tailtest -- AI software testing for Claude Code

License: MIT Tests Version Platform

You build. Claude builds. tailtest makes sure it works.

tailtest is the open-source AI software testing layer for 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.

Open 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.

Read more on tailtest.com · Platform overview · Agent-edit testing deep dive · Full docs


Install

claude plugin marketplace add avansaber/tailtest
claude plugin install tailtest@avansaber-tailtest

Restart Claude Code after install. No other setup required.

Update

claude plugin marketplace update avansaber-tailtest
claude plugin update tailtest@avansaber-tailtest

Uninstall

claude plugin remove tailtest@avansaber-tailtest

How it works

After any Claude-written file lands in your project:

  1. tailtest generates scenarios that describe real business behavior -- not function signatures
  2. It runs them using your existing test runner (pytest, vitest, jest, go test, and more)
  3. Pass: tailtest: N scenarios -- all passed. Fail: one line surfaced, "want me to fix this?"

Supported languages

Python, TypeScript, JavaScript, Go, Ruby, PHP, Java, Kotlin, C#, Rust

Runners are auto-detected from pyproject.toml, package.json, go.mod, build.gradle.kts, *.csproj, *.sln, and other standard manifests.


Quick config

Create .tailtest/config.json in your project root to control depth:

{ "depth": "standard" }

Options: simple (2-3 scenarios), standard (5-8, default), thorough (10-15).

See tailtest.com/docs/config for all options.


Other tailtest variants

Same R1-R15 rule layer, same adversarial test mode, different host integration. This repo is the Claude Code variant.

See tailtest.com/demo/claude-code for a live walkthrough of this variant, or tailtest.com/comparison for a feature matrix across all four.


License

MIT

Releases

Platform freshness (V17 Wave A). 518 tests. New hook: SubagentStop -- tailtest now fires after a subagent finishes its work, not just after direct Claude edits. Files queued in pending_files during a...

Apr 26, 2026

v3.14.0 -- 2026-04-25

Download .zip

Adversarial test mode (V13). 491 tests. New depth tier adversarial: alongside simple / standard / thorough, set "depth": "adversarial" in .tailtest/config.json to bias scenario generation toward adver...

Apr 26, 2026

v3.8.0 -- 2026-04-16

Download .zip

Compatibility update for Claude Opus 4.7. Opus 4.7 follows instructions more literally and uses fewer tool calls by default than Opus 4.6. Two changes to the hook's context note address this: (1) when...

Apr 26, 2026

v3.7.1 -- 2026-04-15

Download .zip

Fixes a bug where Python, TypeScript, and JavaScript files were silently skipped when no runner was detected at session start (e.g., a project without a pyproject.toml or package.json). These language...

Apr 26, 2026

v3.7.0 -- 2026-04-15

Download .zip

First-install ramp-up scan. When tailtest starts on a project for the very first time, it now automatically queues the most important existing files for an initial coverage pass -- no manual /t comman...

Contributors

2 contributors by commits. Profile dekhne ke liye kisi bhi developer par click karein.