Compare variants
Compare tailtest variants: Claude Code, Cursor, Codex CLI, and Cline
Same rule layer. Same adversarial test mode. Different host integration. Pick the right tailtest for your editor.
| Feature | Claude Code 3.14.0 · 491 tests
| Cursor 1.6.0 · 181 tests
| Codex CLI 4.7.0 · 380 tests
| Cline 1.0.0 · 162 tests
|
|---|---|---|---|---|
| R1-R15 rule layer Same rule layer ports across all variants. Consistent test generation behavior. | yes | yes | yes | yes |
| 9 language baselines Python, TypeScript, JavaScript, Go, Ruby, Java, Kotlin, C#, PHP, Rust. | yes | yes | yes | yes |
| 7+ framework templates Flask, FastAPI, Django, NestJS, Spring Boot, Kotlin / Kotest, C# / xUnit. | yes | yes | yes | yes |
| R12 failure classification Real bug / environment / test bug. Cline returns structured arrays via MCP tool; others classify via rule reasoning. | rule-based | rule-based | rule-based | structured (MCP) |
| Adversarial mode (V13) Same R15 rule + 8 scenario categories everywhere. | yes | yes | yes | yes |
| Auto-fire on every edit The honest delta: Cline has no host hook. The .clinerules baseline tells the agent to fire after every edit; Cline's auto-approve makes it hands-off. | yes (PostToolUse hook) | yes (afterFileEdit hook) | yes (Stop hook) | instruction + auto-approve |
| Plan-before-write enforced Cline's Plan / Act toggle enforces the SCENARIO PLAN review step at the UX level. Other variants enforce via rule. | rule-based | rule-based | rule-based | UX-native (Plan mode) |
| Persistent project profile Cline integrates with Cline's Memory Bank pattern for cross-session context. | .tailtest/ | .tailtest/ | .tailtest/ | .tailtest/ + Memory Bank |
| Test count (own dogfood suite) | 491 | 181 | 380 | 162 |
| Latest version | 3.14.0 | 1.6.0 | 4.7.0 | 1.0.0 |
| IDE coverage Cline's host coverage means one tailtest-cline install reaches VS Code, Cursor, JetBrains, Antigravity, Zed, Neovim, VSCodium, Windsurf, plus the Cline CLI. | Claude Code | Cursor | Codex CLI | 9+ editors via Cline |
Which tailtest should you install?
Pick by the editor you actually use. The rule layer and adversarial test mode are identical across all four; the differences are in how each plugin hooks into your editor.
Use the Claude Code variant if...
3.14.0Claude Code users; most precise hook-fired auto experience and the largest dogfood test surface.
IDE coverage: Claude Code
Use the Cursor variant if...
1.6.0Cursor users wanting the deepest native integration. Lighter weight than running Cline inside Cursor.
IDE coverage: Cursor
Search for "Tailtest" in the Cursor plugin marketplace and click Install.
Use the Codex CLI variant if...
4.7.0Codex CLI users wanting hook-driven Stop event integration.
IDE coverage: Codex CLI
Use the Cline variant if...
1.0.0Anyone whose editor is not Claude Code, Cursor, or Codex CLI directly. One plugin reaches 8+ editors. Pairs with Cline's Plan / Act mode for explicit human review gates.
IDE coverage: 9+ editors
Open Cline's Extensions panel inside your IDE. Search for tailtest. Click install. Cline clones the repo, installs deps, registers the server in cline_mcp_settings.json automatically.
Honest delta: Cline auto-fire is instruction-driven
Tailtest-cline is the only variant where auto-fire-on-edit depends on agent compliance with a .clinerules/ instruction plus Cline's auto-approve setting, rather than a host runtime hook. The structured MCP tool layer compensates by making R12 classification, scenario planning, and framework template lookup deterministic regardless of rule recall. Net: high reliability on what matters (the analysis), one explicit configuration step on the trigger.
If you use Claude Code, Cursor, or Codex CLI directly, prefer the matching variant for the tightest hook integration. If your editor is anything else (VS Code, JetBrains, Zed, Neovim, etc.), tailtest-cline is the way -- one plugin, eight-plus editors.
Cursor vs Claude Code: testing edition
The honest answer: tailtest works in both. The Cursor and Claude Code variants of tailtest hook into each editor's native event model -- afterFileEdit for Cursor, PostToolUse for Claude Code -- and use the same R1-R15 rule layer so generated tests look the same regardless of which agent you're running.
You only need to pick a variant if you use one editor exclusively. If you switch between Claude Code and Cursor, install both (they don't conflict). If you use Cursor through Cline, install just the Cline variant.
MCP test server for Cline
Tailtest-cline is an MCP server. It exposes 5 structured tools (tailtest_setup, tailtest_scenario_plan, tailtest_classify_failures, tailtest_pick_template, tailtest_ping) plus a 451-line .clinerules/ rule pack and a Memory Bank integration. The structured I/O is the difference: instead of asking the agent to remember "always include 2 adversarial scenarios at standard depth," the agent calls a tool that always returns the right number.
One Cline install reaches VS Code, Cursor, JetBrains IDEs, Antigravity, Zed, Neovim, VSCodium, Windsurf, and the Cline CLI -- the same MCP server runs in all of them.
Get started
Same MIT license. Same rule layer. Pick by editor.
All four variants are MIT-licensed, no telemetry, no analytics. Switch any time -- they all read the same .tailtest/ config.