@aibridge/cli 0.2.0 → 0.4.0

package/README.md

@@ -28,7 +28,7 @@ npx skills add ycmjason/aibridge
 That's it. The skill runs the CLI on demand via `npx -y @aibridge/cli` — nothing else to install. Ask your agent to "use aibridge", or try it yourself:
 
 ```bash
-npx -y @aibridge/cli subagent "summarize the architecture of this repo"
+npx -y @aibridge/cli subagent --model xai-grok/grok-4.5 "summarize the architecture of this repo"
 ```
 
 <sup>Want the `aibridge` command on your PATH for manual use? `npm i -g @aibridge/cli` (optional).</sup>
@@ -37,21 +37,22 @@ npx -y @aibridge/cli subagent "summarize the architecture of this repo"
 
 | Command | Use when |
 |---|---|
-| `aibridge plan "<task>"` | You want a delegate model to study the repo and expand a task into a detailed, reviewable **plan file** before any code is written |
-| `aibridge implement <plan.md>` | You have an approved plan file and want it executed in place — with your project's **real typecheck and tests** run until green |
-| `aibridge review [--plan <plan.md>]` | You want a **different model** to pressure-test the working-tree diff against the plan contract (over-reach is a finding) — or to review the plan itself before implementing |
-| `aibridge subagent "<task>"` | A self-contained task deserves a concurrent delegate, a cross-model second opinion, or a red-team pass |
-| `aibridge image-gen "<prompt>" --out out.png` | You need a real raster image — on a Codex (default), Antigravity, or Grok seat, with render verification |
+| `aibridge plan --model xai-grok/grok-4.5 --out plan.md "<task>"` | You want a delegate model to study the repo and expand a task into a detailed, reviewable **plan file** before any code is written |
+| `aibridge implement --model google-antigravity/gemini-3.6-flash <plan.md>` | You have an approved plan file and want it executed in place — with your project's **real typecheck and tests** run until green |
+| `aibridge review --model xai-grok/grok-4.5 --out review.md [--plan <plan.md>]` | You want a **different model** to pressure-test the working-tree diff against the plan contract (over-reach is a finding) — or to review the plan itself before implementing |
+| `aibridge subagent --model xai-grok/grok-4.5 "<task>"` | A self-contained task deserves a concurrent delegate, a cross-model second opinion, or a red-team pass |
+| `aibridge image-gen --model openai-codex/gpt-5.6-sol --out out.png "<prompt>"` | You need a real raster image — on a Codex, Antigravity, or Grok seat, with render verification |
+| `aibridge models [--json]` | You need the exact facts for every registered model seat (accepted efforts, image format, pinned model ID) |
 | `aibridge quota` | Two-second check of every backend's remaining quota before you pipeline work |
 | `aibridge runs` | Inspect or watch past delegation runs (`~/.aibridge/runs`) |
 
 The three verbs compose into an orchestrator-driven loop your agent stays in charge of:
 
 ```
-aibridge plan "add rate limiting to the API"   # delegate writes plan.md
+aibridge plan --model xai-grok/grok-4.5 --out plan.md "add rate limiting to the API"   # delegate writes plan.md
 # → your agent reads, edits, approves the plan
-aibridge implement plan.md                     # another model executes it, runs your gates
-aibridge review --plan plan.md                 # a third seat cross-checks the diff
+aibridge implement --model google-antigravity/gemini-3.6-flash plan.md                 # another model executes it, runs your gates
+aibridge review --model xai-grok/grok-4.5 --out review.md --plan plan.md               # a third seat cross-checks the diff
 ```
 
 Plan files — not their contents — travel between stages, so the loop is nearly free on your agent's context.
@@ -63,6 +64,36 @@ Plan files — not their contents — travel between stages, so the loop is near
 - **No API keys.** Delegation runs on the backing CLIs' existing logins, each spending its own quota. (The skill treats a backend that shares your agent's own quota pool as a last resort.)
 - **Models are canonical slugs**: `<vendor>-<cli>/<model>[-<effort>]` — e.g. `xai-grok/grok-4.5`, `google-antigravity/gemini-3.6-flash`, `openai-codex/gpt-5.6-sol-high`, `anthropic-claude/opus-5`. No aliases — not short ones, and not moving vendor aliases like `opus`: every seat pins an exact model version. `aibridge <command> --help` lists every seat.
 
+## Tell your agent when to reach for it
+
+aibridge doesn't decide when to delegate — your agent does, and left alone it will
+mostly keep the work for itself. Put the routing rule in whatever instructions file
+your agent already reads at the start of every session (`AGENTS.md`, `CLAUDE.md`,
+`.cursorrules`, …). Something like:
+
+```markdown
+## Delegation gate — decide before you implement
+
+The moment a task becomes implementation you could fully specify, say the call out
+loud — **solo** or **aibridge** — plus one line of why. Delegating is the default.
+Stay solo only when the edit is smaller than the spec would be, or the work needs
+live judgment, your own session's tools, or tight back-and-forth. Never default to
+solo silently.
+
+Route by size and risk:
+
+- tiny → solo
+- clearly specified and self-contained → `aibridge subagent`
+- large or risky → `aibridge plan` → read and approve the plan file →
+  `aibridge implement` → `aibridge review`
+
+Delegated work is yours to verify: re-run the real gates before trusting a diff.
+Prefer a reviewer from a different model family than whoever implemented.
+```
+
+Tune the seats and thresholds to your own quotas. The value is that the decision is
+explicit and made *before* the work starts, rather than rationalised afterwards.
+
 ## Requirements
 
 - **Node ≥ 24.11**

package/dist/cli.mjs

@@ -1,5 +1,5 @@
 #!/usr/bin/env node
-import { r as runCli, t as buildContext } from "./context-DQxvMUd2.mjs";
+import { r as runCli, t as buildContext } from "./context-v_ns4n_W.mjs";
 //#region src/cli.ts
 await runCli(buildContext(process), process.argv.slice(2));
 //#endregion

package/dist/{context-DQxvMUd2.mjs → context-v_ns4n_W.mjs}

@@ -10,6 +10,7 @@ import { fetchClaudeQuota } from "@aibridge/driver-claude";
 import * as codex from "@aibridge/driver-codex";
 import { fetchCodexQuota } from "@aibridge/driver-codex";
 import * as grok from "@aibridge/driver-grok";
+import { fetchGrokQuota } from "@aibridge/driver-grok";
 import { runCaptured } from "@aibridge/proc";
 import { randomBytes } from "node:crypto";
 //#region src/models.ts
@@ -23,7 +24,7 @@ const MODELS = {
 			"medium",
 			"high"
 		],
-		brief: "xAI Grok 4.5 via grok CLI — default for plan & review; own xAI login"
+		brief: "xAI Grok 4.5 via grok CLI — own xAI login; ~30 req/min, ~1k msgs/day, single-flight"
 	},
 	"google-antigravity/gemini-3.6-flash": {
 		slug: "google-antigravity/gemini-3.6-flash",
@@ -35,7 +36,15 @@ const MODELS = {
 			"high"
 		],
 		defaultEffort: "high",
-		brief: "Google Gemini 3.6 Flash via agy — default for implement, also image-gen; own Antigravity login"
+		brief: "Google Gemini 3.6 Flash via agy — own Antigravity login; quota shared across all Gemini tiers"
+	},
+	"google-antigravity/gemini-3.1-pro": {
+		slug: "google-antigravity/gemini-3.1-pro",
+		backend: "agy",
+		efforts: ["low", "high"],
+		backendModel: "gemini-3.1-pro",
+		defaultEffort: "high",
+		brief: "Google Gemini 3.1 Pro via agy — own Antigravity login; quota shared across all Gemini tiers"
 	},
 	"google-antigravity/claude-sonnet-4-6": {
 		slug: "google-antigravity/claude-sonnet-4-6",
@@ -68,12 +77,36 @@ const MODELS = {
 			"high",
 			"xhigh"
 		],
-		brief: "OpenAI Codex gpt-5.6-sol via codex CLI"
+		brief: "OpenAI gpt-5.6-sol via codex CLI — frontier agentic coding; own ChatGPT login"
 	},
-	"anthropic-claude/sonnet-5": {
-		slug: "anthropic-claude/sonnet-5",
+	"openai-codex/gpt-5.6-terra": {
+		slug: "openai-codex/gpt-5.6-terra",
+		backend: "codex",
+		backendModel: "gpt-5.6-terra",
+		efforts: [
+			"low",
+			"medium",
+			"high",
+			"xhigh"
+		],
+		brief: "OpenAI gpt-5.6-terra via codex CLI — balanced, everyday coding; own ChatGPT login"
+	},
+	"openai-codex/gpt-5.6-luna": {
+		slug: "openai-codex/gpt-5.6-luna",
+		backend: "codex",
+		backendModel: "gpt-5.6-luna",
+		efforts: [
+			"low",
+			"medium",
+			"high",
+			"xhigh"
+		],
+		brief: "OpenAI gpt-5.6-luna via codex CLI — fast and affordable coding; own ChatGPT login"
+	},
+	"anthropic-claude/fable-5": {
+		slug: "anthropic-claude/fable-5",
 		backend: "claude",
-		backendModel: "claude-sonnet-5",
+		backendModel: "claude-fable-5",
 		efforts: [
 			"low",
 			"medium",
@@ -81,12 +114,13 @@ const MODELS = {
 			"xhigh",
 			"max"
 		],
-		brief: "Claude Sonnet 5 via claude CLI — bills your Claude subscription"
+		defaultEffort: "high",
+		brief: "Claude Fable 5 via claude CLI — hardest, longest-running work; bills the claude CLI subscription"
 	},
 	"anthropic-claude/opus-5": {
 		slug: "anthropic-claude/opus-5",
 		backend: "claude",
-		backendModel: "claude-opus-5",
+		backendModel: "claude-opus-5[1m]",
 		efforts: [
 			"low",
 			"medium",
@@ -95,12 +129,12 @@ const MODELS = {
 			"max"
 		],
 		defaultEffort: "high",
-		brief: "Claude Opus 5 via claude CLI (default effort: high) — bills subscription"
+		brief: "Claude Opus 5, 1M context via claude CLI — everyday complex work; bills the claude CLI subscription"
 	},
-	"anthropic-claude/opus-5-1m": {
-		slug: "anthropic-claude/opus-5-1m",
+	"anthropic-claude/sonnet-5": {
+		slug: "anthropic-claude/sonnet-5",
 		backend: "claude",
-		backendModel: "claude-opus-5[1m]",
+		backendModel: "claude-sonnet-5",
 		efforts: [
 			"low",
 			"medium",
@@ -108,13 +142,22 @@ const MODELS = {
 			"xhigh",
 			"max"
 		],
-		defaultEffort: "high",
-		brief: "Claude Opus 5, 1M context via claude CLI — long-context work; bills subscription"
+		brief: "Claude Sonnet 5 via claude CLI — routine work; bills the claude CLI subscription"
+	},
+	"anthropic-claude/haiku-4-5": {
+		slug: "anthropic-claude/haiku-4-5",
+		backend: "claude",
+		backendModel: "claude-haiku-4-5-20251001",
+		efforts: [
+			"low",
+			"medium",
+			"high",
+			"xhigh",
+			"max"
+		],
+		brief: "Claude Haiku 4.5 via claude CLI — quick answers; bills the claude CLI subscription"
 	}
 };
-const DEFAULT_MODEL = "xai-grok/grok-4.5";
-const DEFAULT_IMPLEMENTER = "google-antigravity/gemini-3.6-flash";
-const DEFAULT_IMAGE_GEN = "openai-codex/gpt-5.6-sol";
 const IMAGE_GEN_FORMATS = /* @__PURE__ */ new Map([
 	["agy", "jpg"],
 	["codex", "png"],
@@ -212,6 +255,7 @@ const DRIVERS = {
 	grok: {
 		probe: () => grok.probe(),
 		run: (task) => grok.run(task),
+		quota: () => grok.fetchGrokQuota(),
 		generateImage: (req) => grok.generateImage(req)
 	},
 	codex: {
@@ -240,11 +284,11 @@ async function imageGen$1(flags, prompt) {
 		this.process.stderr.write(`aibridge image-gen: ${msg}\n`);
 		this.process.exitCode = 1;
 	};
-	const inputSlug = flags.model ?? "openai-codex/gpt-5.6-sol";
+	const inputSlug = flags.model;
 	const model = resolveModel(inputSlug);
 	if (!model) return fail(formatUnknownModelError(inputSlug));
 	if (!supportsImageGen(model)) return fail(formatImageGenModelError(inputSlug, model));
-	if (model.spec.backend === "codex" && model.effort) return fail(`effort "-${model.effort}" has no effect on image-gen (the image tool renders, not the seat model); use ${DEFAULT_IMAGE_GEN}.`);
+	if (model.spec.backend === "codex" && model.effort) return fail(`effort "-${model.effort}" has no effect on image-gen (the image tool renders, not the seat model); pass the un-suffixed slug "${model.spec.slug}" instead.`);
 	const expected = imageFormatFor(model);
 	if (expected === void 0) return fail(formatImageGenModelError(inputSlug, model));
 	const label = expected === "png" ? "PNG" : "JPEG";
@@ -378,7 +422,7 @@ const fullDescription$6 = [
 	"",
 	"Image-gen seats (canonical slug):",
 	...listModelHelpLines({ imageOnly: true }),
-	`Default: ${DEFAULT_IMAGE_GEN}.`
+	"Recommended seat: openai-codex/gpt-5.6-sol."
 ].join("\n");
 const imageGen = buildCommand({
 	func: imageGen$1,
@@ -387,8 +431,7 @@ const imageGen = buildCommand({
 			model: {
 				kind: "parsed",
 				parse: String,
-				optional: true,
-				brief: `Model slug (default: ${DEFAULT_IMAGE_GEN})`
+				brief: "Model slug (required) — see the seat list above"
 			},
 			out: {
 				kind: "parsed",
@@ -492,8 +535,17 @@ function evaluateCodexPreflight(snapshot) {
 	};
 	return { ok: true };
 }
+function evaluateGrokPreflight(snapshot) {
+	if (snapshot.usedPercent !== void 0 && snapshot.usedPercent >= 100) return {
+		ok: false,
+		message: "grok credit quota exhausted",
+		resetAt: snapshot.periodEnd
+	};
+	return { ok: true };
+}
 async function preflightModel(resolved) {
 	if (resolved.spec.backend === "codex") return preflightCodex();
+	if (resolved.spec.backend === "grok") return preflightGrok();
 	if (resolved.spec.backend !== "agy") return { ok: true };
 	try {
 		return evaluateAgyPreflight(await fetchAgyQuota(), backendModelId(resolved));
@@ -514,6 +566,16 @@ async function preflightCodex() {
 		};
 	}
 }
+async function preflightGrok() {
+	try {
+		return evaluateGrokPreflight(await fetchGrokQuota());
+	} catch (err) {
+		return {
+			ok: true,
+			warning: `quota preflight failed (${err.message}); proceeding`
+		};
+	}
+}
 function formatReset$1(resetTime) {
 	if (!resetTime) return "-";
 	const ms = new Date(resetTime).getTime() - Date.now();
@@ -649,7 +711,7 @@ function readRunLogs(id) {
 //#endregion
 //#region src/commands/implement/impl.ts
 async function implement$1(flags, planFile) {
-	const inputSlug = flags.model ?? "google-antigravity/gemini-3.6-flash";
+	const inputSlug = flags.model;
 	const model = resolveModel(inputSlug);
 	if (!model) {
 		this.process.stderr.write(`${formatUnknownModelError(inputSlug)}\n`);
@@ -719,8 +781,7 @@ const implement = buildCommand({
 			model: {
 				kind: "parsed",
 				parse: String,
-				optional: true,
-				brief: `Model slug (default: ${DEFAULT_IMPLEMENTER})`
+				brief: "Model slug (required) — see the seat list above"
 			},
 			timeout: {
 				kind: "parsed",
@@ -749,6 +810,70 @@ const implement = buildCommand({
 	}
 });
 //#endregion
+//#region src/commands/models/impl.ts
+const BACKEND_DISPLAY_NAMES = {
+	grok: "grok (Grok CLI)",
+	agy: "agy (Antigravity)",
+	codex: "codex (Codex CLI)",
+	claude: "claude (Claude Code CLI)"
+};
+function modelsImpl(flags) {
+	const specs = Object.values(MODELS);
+	if (flags.json) {
+		const jsonOutput = specs.map((spec) => ({
+			slug: spec.slug,
+			backend: spec.backend,
+			backendModel: spec.backendModel,
+			efforts: spec.efforts ? [...spec.efforts] : [],
+			defaultEffort: spec.defaultEffort ?? null,
+			image: imageFormatFor({
+				spec,
+				effort: void 0
+			}) ?? null,
+			brief: spec.brief
+		}));
+		this.process.stdout.write(`${JSON.stringify(jsonOutput)}\n`);
+		return;
+	}
+	const backends = [];
+	for (const spec of specs) if (!backends.includes(spec.backend)) backends.push(spec.backend);
+	let firstBackend = true;
+	for (const backend of backends) {
+		if (!firstBackend) this.process.stdout.write("\n");
+		firstBackend = false;
+		this.process.stdout.write(`=== ${BACKEND_DISPLAY_NAMES[backend]} ===\n`);
+		const backendSpecs = specs.filter((spec) => spec.backend === backend);
+		for (const spec of backendSpecs) {
+			this.process.stdout.write(`  ${spec.slug}\n`);
+			const segments = [];
+			if (spec.efforts) {
+				const formattedEfforts = spec.efforts.map((e) => e === spec.defaultEffort ? `${e}*` : e).join(" | ");
+				segments.push(`efforts: ${formattedEfforts}`);
+			}
+			const img = imageFormatFor({
+				spec,
+				effort: void 0
+			});
+			segments.push(`image: ${img ?? "—"}`);
+			segments.push(`id: ${spec.backendModel}`);
+			this.process.stdout.write(`    ${segments.join(" · ")}\n`);
+			this.process.stdout.write(`    ${spec.brief}\n`);
+		}
+	}
+	if (specs.some((spec) => spec.defaultEffort !== void 0)) this.process.stdout.write("\n* = effort used when the slug has no -<effort> suffix\n");
+}
+//#endregion
+//#region src/commands/models/command.ts
+const models = buildCommand({
+	func: modelsImpl,
+	parameters: { flags: { json: {
+		kind: "boolean",
+		withNegated: false,
+		brief: "Emit the registry as JSON"
+	} } },
+	docs: { brief: "List every model seat in the registry (slug, efforts, image format)" }
+});
+//#endregion
 //#region src/commands/plan/impl.ts
 function countOpenQuestions(markdown) {
 	const headingIdx = markdown.search(/^## Open questions[ \t]*$/m);
@@ -781,7 +906,7 @@ function extractPathFromPorcelainLine(line) {
 	return content;
 }
 async function plan$1(flags, taskPrompt) {
-	const inputSlug = flags.model ?? "xai-grok/grok-4.5";
+	const inputSlug = flags.model;
 	const model = resolveModel(inputSlug);
 	if (!model) {
 		this.process.stderr.write(`${formatUnknownModelError(inputSlug)}\n`);
@@ -801,7 +926,7 @@ async function plan$1(flags, taskPrompt) {
 	const cwd = this.process.cwd();
 	const promptSnippet = taskPrompt.replace(/\r?\n/g, " ").slice(0, 80);
 	const run = startRun("plan", `${model.spec.slug}: ${promptSnippet}`);
-	const absOutPath = flags.out ? isAbsolute(flags.out) ? flags.out : resolve(cwd, flags.out) : resolve(run.dir, "plan.md");
+	const absOutPath = isAbsolute(flags.out) ? flags.out : resolve(cwd, flags.out);
 	const beforePorcelain = await getPorcelainStatus(cwd);
 	const outcome = await delegate({
 		model,
@@ -866,14 +991,12 @@ const plan = buildCommand({
 			model: {
 				kind: "parsed",
 				parse: String,
-				optional: true,
-				brief: `Model slug (default: ${DEFAULT_MODEL})`
+				brief: "Model slug (required) — see the seat list above"
 			},
 			out: {
 				kind: "parsed",
 				parse: String,
-				optional: true,
-				brief: "Where to write the plan (default: <run.dir>/plan.md)"
+				brief: "Where to write the plan file (required)"
 			},
 			timeout: {
 				kind: "parsed",
@@ -912,6 +1035,17 @@ function formatReset(resetTime) {
 	const rel = mins < 60 ? `${mins}m` : `${Math.floor(mins / 60)}h${mins % 60}m`;
 	return `${new Date(resetTime).toLocaleTimeString()} (in ${rel})`;
 }
+function renderGrok(ctx, snapshot) {
+	ctx.process.stdout.write("=== grok (xAI) — used this period ===\n");
+	ctx.process.stdout.write(`${"PERIOD".padEnd(10)} ${"USED".padEnd(10)} RESET\n`);
+	const usedPctStr = snapshot.usedPercent !== void 0 ? `${snapshot.usedPercent}%` : "?";
+	const periodStr = snapshot.periodType ?? "-";
+	ctx.process.stdout.write(`${periodStr.padEnd(10)} ${usedPctStr.padEnd(10)} ${formatReset(snapshot.periodEnd)}\n`);
+	if (snapshot.products.length > 0) {
+		const prods = snapshot.products.map((p) => `${p.product} ${p.usedPercent}%`).join(" · ");
+		ctx.process.stdout.write(`  ${prods}\n`);
+	}
+}
 function renderAgy(ctx, snapshot) {
 	ctx.process.stdout.write("=== agy (Antigravity) — remaining per model group ===\n");
 	for (const group of snapshot.groups) {
@@ -941,14 +1075,16 @@ function renderSection(ctx, result, title, render) {
 	else ctx.process.stdout.write(`=== ${title} ===\nunavailable: ${result.reason.message}\n`);
 }
 async function quotaImpl(flags) {
-	const [agy, codex, claude] = await Promise.allSettled([
+	const [grok, agy, codex, claude] = await Promise.allSettled([
+		fetchGrokQuota(),
 		fetchAgyQuota(),
 		fetchCodexQuota(),
 		fetchClaudeQuota()
 	]);
-	const allFailed = agy.status === "rejected" && codex.status === "rejected" && claude.status === "rejected";
+	const allFailed = grok.status === "rejected" && agy.status === "rejected" && codex.status === "rejected" && claude.status === "rejected";
 	if (flags.json) {
 		this.process.stdout.write(`${JSON.stringify({
+			grok: grok.status === "fulfilled" ? grok.value : { error: String(grok.reason) },
 			agy: agy.status === "fulfilled" ? agy.value : { error: String(agy.reason) },
 			codex: codex.status === "fulfilled" ? codex.value : { error: String(codex.reason) },
 			claude: claude.status === "fulfilled" ? claude.value : { error: String(claude.reason) }
@@ -956,6 +1092,8 @@ async function quotaImpl(flags) {
 		if (allFailed) this.process.exitCode = 1;
 		return;
 	}
+	renderSection(this, grok, "grok (xAI)", renderGrok);
+	this.process.stdout.write("\n");
 	renderSection(this, agy, "agy (Antigravity)", renderAgy);
 	this.process.stdout.write("\n");
 	renderSection(this, codex, "codex (ChatGPT)", renderCodex);
@@ -971,8 +1109,10 @@ const quota = buildCommand({
 		brief: "Emit the raw snapshot as JSON"
 	} } },
 	docs: {
-		brief: "Show agy / codex / claude quota with reset times",
+		brief: "Show grok / agy / codex / claude quota with reset times",
 		fullDescription: [
+			"grok: reads ~/.grok/auth.json and asks the xAI billing endpoint for the",
+			"weekly credit usage percentage and per-product split.",
 			"agy: reads its cached OAuth token (~/.gemini/antigravity-cli/) and asks the",
 			"Cloud Code API for per-model remaining quota. EXHAUSTED means agy turns on",
 			"that model fail with an empty answer until the reset time.",
@@ -1032,7 +1172,7 @@ function parseReviewVerdict(response) {
 	};
 }
 async function review$1(flags) {
-	const inputSlug = flags.model ?? "xai-grok/grok-4.5";
+	const inputSlug = flags.model;
 	const model = resolveModel(inputSlug);
 	if (!model) {
 		this.process.stderr.write(`${formatUnknownModelError(inputSlug)}\n`);
@@ -1082,7 +1222,7 @@ async function review$1(flags) {
 	const timeoutSec = flags.timeout ?? 1200;
 	const modeDetail = isDirty ? absPlanPath ? `diff + plan (${absPlanPath})` : `diff (${baseRef})` : `plan-only (${absPlanPath})`;
 	const run = startRun("review", `${model.spec.slug}: ${modeDetail}`);
-	const absOutPath = flags.out ? isAbsolute(flags.out) ? flags.out : resolve(cwd, flags.out) : resolve(run.dir, "review.md");
+	const absOutPath = isAbsolute(flags.out) ? flags.out : resolve(cwd, flags.out);
 	let reviewPrompt;
 	if (isDirty) reviewPrompt = `You are an expert code reviewer. Inspect the working tree diff against base '${baseRef}' and untracked files at ${cwd}.\n` + (absPlanPath ? `Compare the implementation against the plan contract at ${absPlanPath}. Any file modified or feature added outside the plan contract counts as over-reach (severity: major unless harmful, then critical).\n` : "") + `Write your detailed review report to the file ${absOutPath}. For each finding, include file:line, severity (critical|major|minor), and rationale.\nYour final answer (last message) must consist of EXACTLY ONE VERDICT LINE:\nEither: "PASS"\nOr: "FINDINGS: <c> critical, <m> major, <n> minor"`;
 	else reviewPrompt = `You are an expert architecture reviewer. Inspect the plan contract file at ${absPlanPath}.\nReview the plan for soundness, missing edge cases, safety, and feasibility.\nWrite your detailed review report to the file ${absOutPath}. For each finding, include severity (critical|major|minor) and rationale.\nYour final answer (last message) must consist of EXACTLY ONE VERDICT LINE:\nEither: "PASS"\nOr: "FINDINGS: <c> critical, <m> major, <n> minor"`;
@@ -1134,8 +1274,7 @@ const review = buildCommand({
 		model: {
 			kind: "parsed",
 			parse: String,
-			optional: true,
-			brief: `Model slug (default: ${DEFAULT_MODEL})`
+			brief: "Model slug (required) — see the seat list above"
 		},
 		plan: {
 			kind: "parsed",
@@ -1152,8 +1291,7 @@ const review = buildCommand({
 		out: {
 			kind: "parsed",
 			parse: String,
-			optional: true,
-			brief: "Where to write the review report (default: <run.dir>/review.md)"
+			brief: "Where to write the review report (required)"
 		},
 		timeout: {
 			kind: "parsed",
@@ -1345,7 +1483,7 @@ const runs = buildCommand({
 //#endregion
 //#region src/commands/subagent/impl.ts
 async function subagent$1(flags, prompt) {
-	const inputSlug = flags.model ?? "xai-grok/grok-4.5";
+	const inputSlug = flags.model;
 	const model = resolveModel(inputSlug);
 	if (!model) {
 		this.process.stderr.write(`${formatUnknownModelError(inputSlug)}\n`);
@@ -1399,8 +1537,8 @@ const fullDescription = [
 	"",
 	"Available models (canonical slug):",
 	...listModelHelpLines(),
-	`Default: ${DEFAULT_MODEL} (off-budget). The claude-backend slugs are FALLBACKS for`,
-	"when the off-budget CLIs are quota-exhausted — they bill your Claude subscription."
+	"Recommended first choice: xai-grok/grok-4.5. Whichever seat runs on the same provider as the",
+	"agent you orchestrate from is your last resort — it spends the pool you are already burning."
 ].join("\n");
 const subagent = buildCommand({
 	func: subagent$1,
@@ -1409,8 +1547,7 @@ const subagent = buildCommand({
 			model: {
 				kind: "parsed",
 				parse: String,
-				optional: true,
-				brief: `Model slug to delegate to (default: ${DEFAULT_MODEL})`
+				brief: "Model slug (required) — see the seat list above"
 			},
 			timeout: {
 				kind: "parsed",
@@ -1475,9 +1612,10 @@ const app = buildApplication(buildRouteMap({
 		subagent,
 		"image-gen": imageGen,
 		runs,
-		quota
+		quota,
+		models
 	},
-	docs: { brief: "Bridge tasks to non-Claude AI CLIs — a plan → implement → review workflow, task delegation, and image generation (codex / agy / grok seats)." }
+	docs: { brief: "Bridge tasks to the other AI CLIs on this machine — a plan → implement → review workflow, task delegation, and image generation (codex / agy / grok seats)." }
 }), {
 	name: "aibridge",
 	versionInfo: { currentVersion: version },
@@ -1494,4 +1632,4 @@ function buildContext(process) {
 	return { process };
 }
 //#endregion
-export { listModelHelpLines as C, formatUnknownModelError as S, supportsImageGen as T, DEFAULT_IMPLEMENTER as _, readRunLogs as a, backendModelId as b, evaluateCodexPreflight as c, renderPreflightRefusal as d, delegate as f, DEFAULT_IMAGE_GEN as g, positiveIntSeconds as h, listRuns as i, preflightCodex as l, nonEmptyPrompt as m, app as n, startRun as o, getDriver as p, runCli as r, evaluateAgyPreflight as s, buildContext as t, preflightModel as u, DEFAULT_MODEL as v, resolveModel as w, formatImageGenModelError as x, MODELS as y };
+export { supportsImageGen as S, backendModelId as _, readRunLogs as a, listModelHelpLines as b, evaluateCodexPreflight as c, renderPreflightRefusal as d, delegate as f, MODELS as g, positiveIntSeconds as h, listRuns as i, preflightCodex as l, nonEmptyPrompt as m, app as n, startRun as o, getDriver as p, runCli as r, evaluateAgyPreflight as s, buildContext as t, preflightModel as u, formatImageGenModelError as v, resolveModel as x, formatUnknownModelError as y };

package/dist/index.d.mts

@@ -2,6 +2,7 @@ import { CommandContext } from "@stricli/core";
 import { AgyQuotaSnapshot } from "@aibridge/driver-agy";
 import { ClaudeQuotaSnapshot } from "@aibridge/driver-claude";
 import { CodexQuotaSnapshot } from "@aibridge/driver-codex";
+import { GrokQuotaSnapshot } from "@aibridge/driver-grok";
 //#region src/context.d.ts
 interface LocalContext extends CommandContext {
   /** Full Node process — satisfies stricli WritableStreams + exitCode/env/cwd used by impls. */
@@ -21,7 +22,7 @@ declare function runCli(ctx: LocalContext, argv: readonly string[]): Promise<voi
  * Models are registered by canonical, provider-qualified slug —
  * `<vendor>-<cli>/<model>[-<effort>]`, e.g. `openai-codex/gpt-5.6-sol-high`.
  * Canonical slugs only — no short aliases, by design. That holds on both sides:
- * `backendModel` is a pinned model id (`claude-opus-5`), never a moving vendor
+ * `backendModel` is a pinned model id (`claude-sonnet-5`), never a moving vendor
  * alias (`opus`), so a seat never silently changes model under you.
  */
 type Backend = 'agy' | 'claude' | 'codex' | 'grok';
@@ -39,9 +40,6 @@ interface ResolvedModel {
   readonly effort: Effort | undefined;
 }
 declare const MODELS: Record<string, ModelSpec>;
-declare const DEFAULT_MODEL = "xai-grok/grok-4.5";
-declare const DEFAULT_IMPLEMENTER = "google-antigravity/gemini-3.6-flash";
-declare const DEFAULT_IMAGE_GEN = "openai-codex/gpt-5.6-sol";
 declare function supportsImageGen(resolved: ResolvedModel): boolean;
 declare function resolveModel(input: string): ResolvedModel | undefined;
 declare function backendModelId(resolved: ResolvedModel): string;
@@ -80,7 +78,7 @@ type DelegationResult = {
   readonly message: string;
   readonly exitCode: number | null;
 };
-type QuotaSnapshot = AgyQuotaSnapshot | CodexQuotaSnapshot | ClaudeQuotaSnapshot;
+type QuotaSnapshot = AgyQuotaSnapshot | CodexQuotaSnapshot | ClaudeQuotaSnapshot | GrokQuotaSnapshot;
 interface ImageGenRequest {
   readonly prompt: string;
   readonly workDir: string;
@@ -179,4 +177,4 @@ declare function renderPreflightRefusal(cmd: string, verdict: {
   resetAt: string | undefined;
 }): string;
 //#endregion
-export { type AgentCliDriver, type Backend, DEFAULT_IMAGE_GEN, DEFAULT_IMPLEMENTER, DEFAULT_MODEL, type DelegateOptions, type DelegateOutcome, type DelegationResult, type DelegationTask, type Effort, type LocalContext, MODELS, type ModelSpec, type PreflightVerdict, type ResolvedModel, type RunLog, type RunMeta, app, backendModelId, buildContext, delegate, evaluateAgyPreflight, evaluateCodexPreflight, formatImageGenModelError, formatUnknownModelError, getDriver, listModelHelpLines, listRuns, nonEmptyPrompt, positiveIntSeconds, preflightCodex, preflightModel, readRunLogs, renderPreflightRefusal, resolveModel, runCli, startRun, supportsImageGen };
+export { type AgentCliDriver, type Backend, type DelegateOptions, type DelegateOutcome, type DelegationResult, type DelegationTask, type Effort, type LocalContext, MODELS, type ModelSpec, type PreflightVerdict, type ResolvedModel, type RunLog, type RunMeta, app, backendModelId, buildContext, delegate, evaluateAgyPreflight, evaluateCodexPreflight, formatImageGenModelError, formatUnknownModelError, getDriver, listModelHelpLines, listRuns, nonEmptyPrompt, positiveIntSeconds, preflightCodex, preflightModel, readRunLogs, renderPreflightRefusal, resolveModel, runCli, startRun, supportsImageGen };

package/dist/index.mjs

@@ -1,2 +1,2 @@
-import { C as listModelHelpLines, S as formatUnknownModelError, T as supportsImageGen, _ as DEFAULT_IMPLEMENTER, a as readRunLogs, b as backendModelId, c as evaluateCodexPreflight, d as renderPreflightRefusal, f as delegate, g as DEFAULT_IMAGE_GEN, h as positiveIntSeconds, i as listRuns, l as preflightCodex, m as nonEmptyPrompt, n as app, o as startRun, p as getDriver, r as runCli, s as evaluateAgyPreflight, t as buildContext, u as preflightModel, v as DEFAULT_MODEL, w as resolveModel, x as formatImageGenModelError, y as MODELS } from "./context-DQxvMUd2.mjs";
-export { DEFAULT_IMAGE_GEN, DEFAULT_IMPLEMENTER, DEFAULT_MODEL, MODELS, app, backendModelId, buildContext, delegate, evaluateAgyPreflight, evaluateCodexPreflight, formatImageGenModelError, formatUnknownModelError, getDriver, listModelHelpLines, listRuns, nonEmptyPrompt, positiveIntSeconds, preflightCodex, preflightModel, readRunLogs, renderPreflightRefusal, resolveModel, runCli, startRun, supportsImageGen };
+import { S as supportsImageGen, _ as backendModelId, a as readRunLogs, b as listModelHelpLines, c as evaluateCodexPreflight, d as renderPreflightRefusal, f as delegate, g as MODELS, h as positiveIntSeconds, i as listRuns, l as preflightCodex, m as nonEmptyPrompt, n as app, o as startRun, p as getDriver, r as runCli, s as evaluateAgyPreflight, t as buildContext, u as preflightModel, v as formatImageGenModelError, x as resolveModel, y as formatUnknownModelError } from "./context-v_ns4n_W.mjs";
+export { MODELS, app, backendModelId, buildContext, delegate, evaluateAgyPreflight, evaluateCodexPreflight, formatImageGenModelError, formatUnknownModelError, getDriver, listModelHelpLines, listRuns, nonEmptyPrompt, positiveIntSeconds, preflightCodex, preflightModel, readRunLogs, renderPreflightRefusal, resolveModel, runCli, startRun, supportsImageGen };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aibridge/cli",
-  "version": "0.2.0",
+  "version": "0.4.0",
   "description": "CLI that bridges tasks to AI CLIs on your machine (plan / implement / review / subagent / image-gen)",
   "type": "module",
   "license": "MIT",
@@ -35,11 +35,11 @@
   ],
   "dependencies": {
     "@stricli/core": "1.3.0",
-    "@aibridge/proc": "0.2.0",
-    "@aibridge/driver-codex": "0.2.0",
-    "@aibridge/driver-grok": "0.2.0",
-    "@aibridge/driver-claude": "0.2.0",
-    "@aibridge/driver-agy": "0.2.0"
+    "@aibridge/proc": "0.4.0",
+    "@aibridge/driver-grok": "0.4.0",
+    "@aibridge/driver-agy": "0.4.0",
+    "@aibridge/driver-codex": "0.4.0",
+    "@aibridge/driver-claude": "0.4.0"
   },
   "devDependencies": {
     "tsdown": "0.22.14"

package/src/app.ts

@@ -2,6 +2,7 @@ import { createRequire } from 'node:module';
 import { buildApplication, buildRouteMap, run } from '@stricli/core';
 import { imageGen } from './commands/image-gen/command.ts';
 import { implement } from './commands/implement/command.ts';
+import { models } from './commands/models/command.ts';
 import { plan } from './commands/plan/command.ts';
 import { quota } from './commands/quota/command.ts';
 import { review } from './commands/review/command.ts';
@@ -14,7 +15,7 @@ const require = createRequire(import.meta.url);
 const { version } = require('../package.json') as { version: string };
 
 const BRIEF =
-  'Bridge tasks to non-Claude AI CLIs — a plan → implement → review workflow, task delegation, and image generation (codex / agy / grok seats).';
+  'Bridge tasks to the other AI CLIs on this machine — a plan → implement → review workflow, task delegation, and image generation (codex / agy / grok seats).';
 
 const routes = buildRouteMap({
   routes: {
@@ -25,6 +26,7 @@ const routes = buildRouteMap({
     'image-gen': imageGen,
     runs,
     quota,
+    models,
   },
   docs: {
     brief: BRIEF,