feat(bench-kit): remove TENX_CLI_EXPERIMENTAL gating — init and update generally available

CHANGELOG.md

@@ -7,6 +7,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Changed
+
+- **`10x bench-kit` is generally available.** The `TENX_CLI_EXPERIMENTAL`
+  opt-in is gone: `init` and `update` are registered unconditionally, appear
+  in `--help`, and are documented in the README. The `experimental_locked`
+  error envelope no longer exists (the gating module has been removed).
+
 ### Added
 
 - **`10x sync` — bulk download & update with change visibility.** One command to

README.md

@@ -62,6 +62,7 @@ Once installed, just tell your agent to **set up 10x-cli** and it will pick up t
 | `10x sync` | Bulk-download / refresh lessons and report what changed upstream |
 | `10x doctor` | Diagnose auth, API connectivity, and local config |
 | `10x bench` | Live top-10 AI model leaderboard from [10xbench.ai](https://10xbench.ai) — no login needed |
+| `10x bench-kit <action>` | Create (`init`) and update (`update`) a company benchmark instance from the [10x-bench-kit](https://github.com/przeprogramowani/10x-bench-kit) template |
 
 ### `10x get` Flags
 
@@ -180,6 +181,40 @@ color-coded score bars in your terminal. Public data, works without logging in.
 The data refreshes whenever new benchmark results are published on 10xbench.ai.
 Colors honor `NO_COLOR` and are disabled automatically when output is piped.
 
+### `10x bench-kit`
+
+Creates and maintains a **company benchmark instance** from the
+[10x-bench-kit](https://github.com/przeprogramowani/10x-bench-kit) template —
+a self-hosted benchmark that scores AI agents on tasks embedded in your own
+repositories. The CLI is a thin installer/updater; tasks, assertions, and
+scoring live in the template and the instance.
+
+| Action | Description |
+|--------|-------------|
+| `init [dir]` | Materialize a fresh instance from the template (no git history, fresh `git init`), register the detected base repo, install runner dependencies |
+| `update [dir]` | Upgrade the instance to a newer template: runtime zone replaced wholesale, skills proposed as a reviewable diff, company content untouched |
+
+| Flag | Description |
+|------|-------------|
+| `--template-version <tag>` | Template tag to install (default: latest) |
+| `--tool <id>` | Agent tool for skill placement (`claude-code`, `cursor`, `copilot`, `codex`, `windsurf`, `gemini`, `generic`) |
+| `--yes` | Run non-interactively, accepting defaults |
+
+```bash
+# Create an instance next to your product repo (run inside it to auto-register)
+10x bench-kit init my-benchmark
+
+# Pin the template version
+10x bench-kit init my-benchmark --template-version v0.8.0
+
+# Upgrade an existing instance to the latest template
+10x bench-kit update
+```
+
+Re-running `init` on an existing instance is a **repair**: missing template
+files are restored, company content is never touched. After `update`, run the
+instance's `bench validate` to confirm the content still matches the new kit.
+
 ### Global Flags
 
 - `--json` — Machine-readable JSON output (auto-detected when piped)

src/commands/bench-kit.ts

@@ -30,7 +30,6 @@ import {
 import { tmpdir } from "node:os";
 import { basename, join, resolve, sep } from "node:path";
 import type { CAC } from "cac";
-import { experimentalEnabled, requireExperimental } from "../lib/experimental";
 import {
   ExitCodes,
   type GlobalFlags,
@@ -121,23 +120,15 @@ export interface BenchKitDeps {
 // bench-kit follows the `auth` precedent: one command dispatching on an
 // action argument.
 export function registerBenchKitCommand(cli: CAC): void {
-  // Experimental commands are all-or-nothing: without the opt-in the
-  // command is not registered at all — absent from help and behaving like
-  // any unknown command — instead of showing up half-locked.
-  if (!experimentalEnabled()) return;
   cli
-    .command(
-      "bench-kit <action> [dir]",
-      "Manage a benchmark instance (actions: init, update; experimental)",
-    )
+    .command("bench-kit <action> [dir]", "Manage a benchmark instance (actions: init, update)")
     .option("--template-version <tag>", "Template tag to install (default: latest)")
     .option("--tool <id>", `Agent tool for skill placement (${Object.keys(PROFILES).join(", ")})`)
     .option("--yes", "Run non-interactively, accepting defaults")
     .example("10x bench-kit init my-benchmark")
     .example("10x bench-kit init my-benchmark --template-version v0.1.0")
     .example("10x bench-kit update")
     .action(async (action: string, dir: string | undefined, options: BenchKitFlags) => {
-      requireExperimental(`bench-kit ${action}`, options);
       const ctx = resolveContext(options);
       if (action === "init") {
         await runBenchKitInit(ctx, dir, options);

tests/bench-kit-command.test.ts

@@ -18,7 +18,6 @@ import {
   runBenchKitUpdate,
   toHttpsUrl,
 } from "../src/commands/bench-kit";
-import { EXPERIMENTAL_ENV, experimentalEnabled } from "../src/lib/experimental";
 import type { OutputContext } from "../src/lib/output";
 
 interface CaptureResult {
@@ -725,58 +724,12 @@ describe("toHttpsUrl", () => {
   });
 });
 
-describe("experimental gate", () => {
-  const savedEnv = process.env[EXPERIMENTAL_ENV];
-
-  afterEach(() => {
-    if (savedEnv === undefined) {
-      delete process.env[EXPERIMENTAL_ENV];
-    } else {
-      process.env[EXPERIMENTAL_ENV] = savedEnv;
-    }
-  });
-
-  it("is off by default and accepts 1 / true", () => {
-    expect(experimentalEnabled({})).toBe(false);
-    expect(experimentalEnabled({ [EXPERIMENTAL_ENV]: "0" })).toBe(false);
-    expect(experimentalEnabled({ [EXPERIMENTAL_ENV]: "1" })).toBe(true);
-    expect(experimentalEnabled({ [EXPERIMENTAL_ENV]: "true" })).toBe(true);
-  });
-
-  it("keeps bench-kit fully hidden without the opt-in", async () => {
-    delete process.env[EXPERIMENTAL_ENV];
-    const cli = cac("10x");
-    registerBenchKitCommand(cli);
-    expect(cli.commands.map((c) => c.name)).not.toContain("bench-kit");
-
-    // Invoking it behaves like any unknown command: no output, no error.
-    const result = await runCli(["bench-kit", "init", "some-dir", "--json"]);
-    expect(result.exitCode).toBeUndefined();
-    expect(result.stdout).toBe("");
-  });
-
-  it("registers bench-kit when the opt-in is set", () => {
-    process.env[EXPERIMENTAL_ENV] = "1";
+describe("10x bench-kit dispatch", () => {
+  it("registers bench-kit unconditionally", () => {
     const cli = cac("10x");
     registerBenchKitCommand(cli);
     expect(cli.commands.map((c) => c.name)).toContain("bench-kit");
   });
-});
-
-describe("10x bench-kit dispatch", () => {
-  const savedEnv = process.env[EXPERIMENTAL_ENV];
-
-  beforeEach(() => {
-    process.env[EXPERIMENTAL_ENV] = "1";
-  });
-
-  afterEach(() => {
-    if (savedEnv === undefined) {
-      delete process.env[EXPERIMENTAL_ENV];
-    } else {
-      process.env[EXPERIMENTAL_ENV] = savedEnv;
-    }
-  });
 
   it("routes 'update' to the real implementation", async () => {
     // A temp dir that is not an instance — proves dispatch reaches update.