claudish 2.2.1 → 2.5.0

package/package.json

@@ -1,31 +1,15 @@
 {
   "name": "claudish",
-  "version": "2.2.1",
+  "version": "2.5.0",
   "description": "CLI tool to run Claude Code with any OpenRouter model (Grok, GPT-5, MiniMax, etc.) via local Anthropic API-compatible proxy",
   "type": "module",
   "main": "./dist/index.js",
   "bin": {
     "claudish": "dist/index.js"
   },
-  "scripts": {
-    "dev": "bun run src/index.ts",
-    "dev:grok": "bun run src/index.ts --interactive --model x-ai/grok-code-fast-1",
-    "dev:grok:debug": "bun run src/index.ts --interactive --debug --log-level info --model x-ai/grok-code-fast-1",
-    "dev:info": "bun run src/index.ts --interactive --monitor",
-    "extract-models": "bun run scripts/extract-models.ts",
-    "build": "bun run extract-models && bun build src/index.ts --outdir dist --target node && chmod +x dist/index.js",
-    "link": "npm link",
-    "unlink": "npm unlink -g claudish",
-    "install-global": "bun run build && npm link",
-    "kill-all": "pkill -f 'bun.*claudish' || pkill -f 'claude.*claudish-settings' || echo 'No claudish processes found'",
-    "test": "bun test ./tests/comprehensive-model-test.ts",
-    "typecheck": "tsc --noEmit",
-    "lint": "biome check .",
-    "format": "biome format --write .",
-    "postinstall": "node scripts/postinstall.cjs"
-  },
   "dependencies": {
     "@hono/node-server": "^1.19.6",
+    "dotenv": "^17.2.3",
     "hono": "^4.10.6"
   },
   "devDependencies": {
@@ -54,5 +38,22 @@
     "ai"
   ],
   "author": "Jack Rudenko <i@madappgang.com>",
-  "license": "MIT"
-}
+  "license": "MIT",
+  "scripts": {
+    "dev": "bun run src/index.ts",
+    "dev:grok": "bun run src/index.ts --interactive --model x-ai/grok-code-fast-1",
+    "dev:grok:debug": "bun run src/index.ts --interactive --debug --log-level info --model x-ai/grok-code-fast-1",
+    "dev:info": "bun run src/index.ts --interactive --monitor",
+    "extract-models": "bun run scripts/extract-models.ts",
+    "build": "bun run extract-models && bun build src/index.ts --outdir dist --target node && chmod +x dist/index.js",
+    "link": "npm link",
+    "unlink": "npm unlink -g claudish",
+    "install-global": "bun run build && npm link",
+    "kill-all": "pkill -f 'bun.*claudish' || pkill -f 'claude.*claudish-settings' || echo 'No claudish processes found'",
+    "test": "bun test ./tests/comprehensive-model-test.ts",
+    "typecheck": "tsc --noEmit",
+    "lint": "biome check .",
+    "format": "biome format --write .",
+    "postinstall": "node scripts/postinstall.cjs"
+  }
+}

package/recommended-models.json

@@ -1,26 +1,26 @@
 {
   "version": "2.1.0",
-  "lastUpdated": "2025-11-20",
+  "lastUpdated": "2025-11-24",
   "source": "https://openrouter.ai/models?categories=programming&fmt=cards&order=top-weekly",
   "models": [
     {
-      "id": "x-ai/grok-code-fast-1",
-      "name": "xAI: Grok Code Fast 1",
-      "description": "Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality work flows.",
-      "provider": "X-ai",
-      "category": "reasoning",
+      "id": "google/gemini-3-pro-preview",
+      "name": "Google: Gemini 3 Pro Preview",
+      "description": "Gemini 3 Pro is Google’s flagship frontier model for high-precision multimodal reasoning, combining strong performance across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks. It delivers state-of-the-art benchmark results in general reasoning, STEM problem solving, factual QA, and multimodal understanding, including leading scores on LMArena, GPQA Diamond, MathArena Apex, MMMU-Pro, and Video-MMMU. Interactions emphasize depth and interpretability: the model is designed to infer intent with minimal prompting and produce direct, insight-focused responses.\n\nBuilt for advanced development and agentic workflows, Gemini 3 Pro provides robust tool-calling, long-horizon planning stability, and strong zero-shot generation for complex UI, visualization, and coding tasks. It excels at agentic coding (SWE-Bench Verified, Terminal-Bench 2.0), multimodal analysis, and structured long-form tasks such as research synthesis, planning, and interactive learning experiences. Suitable applications include autonomous agents, coding assistants, multimodal analytics, scientific reasoning, and high-context information processing.",
+      "provider": "Google",
+      "category": "vision",
       "priority": 1,
       "pricing": {
-        "input": "$0.20/1M",
-        "output": "$1.50/1M",
-        "average": "$0.85/1M"
+        "input": "$2.00/1M",
+        "output": "$12.00/1M",
+        "average": "$7.00/1M"
       },
-      "context": "256K",
-      "maxOutputTokens": 10000,
-      "modality": "text->text",
+      "context": "1048K",
+      "maxOutputTokens": 65536,
+      "modality": "text+image->text",
       "supportsTools": true,
       "supportsReasoning": true,
-      "supportsVision": false,
+      "supportsVision": true,
       "isModerated": false,
       "recommended": true
     },
@@ -46,19 +46,19 @@
       "recommended": true
     },
     {
-      "id": "moonshotai/kimi-k2-thinking",
-      "name": "MoonshotAI: Kimi K2 Thinking",
-      "description": "Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift.\n\nIt sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.",
-      "provider": "Moonshotai",
+      "id": "x-ai/grok-code-fast-1",
+      "name": "xAI: Grok Code Fast 1",
+      "description": "Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality work flows.",
+      "provider": "X-ai",
       "category": "reasoning",
       "priority": 3,
       "pricing": {
-        "input": "$0.50/1M",
-        "output": "$2.50/1M",
-        "average": "$1.50/1M"
+        "input": "$0.20/1M",
+        "output": "$1.50/1M",
+        "average": "$0.85/1M"
       },
-      "context": "262K",
-      "maxOutputTokens": 262144,
+      "context": "256K",
+      "maxOutputTokens": 10000,
       "modality": "text->text",
       "supportsTools": true,
       "supportsReasoning": true,
@@ -66,38 +66,17 @@
       "isModerated": false,
       "recommended": true
     },
-    {
-      "id": "google/gemini-2.5-flash",
-      "name": "Google: Gemini 2.5 Flash",
-      "description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. \n\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).",
-      "provider": "Google",
-      "category": "reasoning",
-      "priority": 4,
-      "pricing": {
-        "input": "$0.30/1M",
-        "output": "$2.50/1M",
-        "average": "$1.40/1M"
-      },
-      "context": "1048K",
-      "maxOutputTokens": 65535,
-      "modality": "text+image->text",
-      "supportsTools": true,
-      "supportsReasoning": true,
-      "supportsVision": true,
-      "isModerated": false,
-      "recommended": true
-    },
     {
       "id": "minimax/minimax-m2",
       "name": "MiniMax: MiniMax M2",
       "description": "MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency.\n\nThe model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors.\n\nBenchmarked by [Artificial Analysis](https://artificialanalysis.ai/models/minimax-m2), MiniMax-M2 ranks among the top open-source models for composite intelligence, spanning mathematics, science, and instruction-following. Its small activation footprint enables fast inference, high concurrency, and improved unit economics, making it well-suited for large-scale agents, developer assistants, and reasoning-driven applications that require responsiveness and cost efficiency.\n\nTo avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our [docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks).",
       "provider": "Minimax",
       "category": "reasoning",
-      "priority": 5,
+      "priority": 4,
       "pricing": {
-        "input": "$0.26/1M",
-        "output": "$1.02/1M",
-        "average": "$0.64/1M"
+        "input": "$0.24/1M",
+        "output": "$0.96/1M",
+        "average": "$0.60/1M"
       },
       "context": "204K",
       "maxOutputTokens": 131072,
@@ -114,7 +93,7 @@
       "description": "Compared with GLM-4.5, this generation brings several key improvements:\n\nLonger context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.\nSuperior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages.\nAdvanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.\nMore capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks.\nRefined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.",
       "provider": "Z-ai",
       "category": "reasoning",
-      "priority": 6,
+      "priority": 5,
       "pricing": {
         "input": "$0.40/1M",
         "output": "$1.75/1M",
@@ -129,55 +108,13 @@
       "isModerated": false,
       "recommended": true
     },
-    {
-      "id": "openai/gpt-5",
-      "name": "OpenAI: GPT-5",
-      "description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.",
-      "provider": "Openai",
-      "category": "reasoning",
-      "priority": 7,
-      "pricing": {
-        "input": "$1.25/1M",
-        "output": "$10.00/1M",
-        "average": "$5.63/1M"
-      },
-      "context": "400K",
-      "maxOutputTokens": 128000,
-      "modality": "text+image->text",
-      "supportsTools": true,
-      "supportsReasoning": true,
-      "supportsVision": true,
-      "isModerated": true,
-      "recommended": true
-    },
-    {
-      "id": "google/gemini-3-pro-preview",
-      "name": "Google: Gemini 3 Pro Preview",
-      "description": "Gemini 3 Pro is Google’s flagship frontier model for high-precision multimodal reasoning, combining strong performance across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks. It delivers state-of-the-art benchmark results in general reasoning, STEM problem solving, factual QA, and multimodal understanding, including leading scores on LMArena, GPQA Diamond, MathArena Apex, MMMU-Pro, and Video-MMMU. Interactions emphasize depth and interpretability: the model is designed to infer intent with minimal prompting and produce direct, insight-focused responses.\n\nBuilt for advanced development and agentic workflows, Gemini 3 Pro provides robust tool-calling, long-horizon planning stability, and strong zero-shot generation for complex UI, visualization, and coding tasks. It excels at agentic coding (SWE-Bench Verified, Terminal-Bench 2.0), multimodal analysis, and structured long-form tasks such as research synthesis, planning, and interactive learning experiences. Suitable applications include autonomous agents, coding assistants, multimodal analytics, scientific reasoning, and high-context information processing.",
-      "provider": "Google",
-      "category": "vision",
-      "priority": 8,
-      "pricing": {
-        "input": "$2.00/1M",
-        "output": "$12.00/1M",
-        "average": "$7.00/1M"
-      },
-      "context": "1048K",
-      "maxOutputTokens": 65536,
-      "modality": "text+image->text",
-      "supportsTools": true,
-      "supportsReasoning": true,
-      "supportsVision": true,
-      "isModerated": false,
-      "recommended": true
-    },
     {
       "id": "qwen/qwen3-vl-235b-a22b-instruct",
       "name": "Qwen: Qwen3 VL 235B A22B Instruct",
       "description": "Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table extraction, multilingual OCR). The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\n\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows—turning sketches or mockups into code and assisting with UI debugging—while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.",
       "provider": "Qwen",
       "category": "vision",
-      "priority": 9,
+      "priority": 6,
       "pricing": {
         "input": "$0.21/1M",
         "output": "$1.90/1M",
@@ -191,27 +128,6 @@
       "supportsVision": true,
       "isModerated": false,
       "recommended": true
-    },
-    {
-      "id": "openrouter/polaris-alpha",
-      "name": "Polaris Alpha",
-      "description": "openrouter/polaris-alpha (metadata pending - not yet available in API)",
-      "provider": "Openrouter",
-      "category": "programming",
-      "priority": 10,
-      "pricing": {
-        "input": "N/A",
-        "output": "N/A",
-        "average": "N/A"
-      },
-      "context": "N/A",
-      "maxOutputTokens": null,
-      "modality": "text->text",
-      "supportsTools": false,
-      "supportsReasoning": false,
-      "supportsVision": false,
-      "isModerated": false,
-      "recommended": true
     }
   ]
 }

package/scripts/extract-models.ts

@@ -120,6 +120,16 @@ export const ENV = {
   CLAUDISH_ACTIVE_MODEL_NAME: "CLAUDISH_ACTIVE_MODEL_NAME", // Set by claudish to show active model in status line
   ANTHROPIC_MODEL: "ANTHROPIC_MODEL", // Claude Code standard env var for model selection
   ANTHROPIC_SMALL_FAST_MODEL: "ANTHROPIC_SMALL_FAST_MODEL", // Claude Code standard env var for fast model
+  // Claudish model mapping overrides (highest priority)
+  CLAUDISH_MODEL_OPUS: "CLAUDISH_MODEL_OPUS",
+  CLAUDISH_MODEL_SONNET: "CLAUDISH_MODEL_SONNET",
+  CLAUDISH_MODEL_HAIKU: "CLAUDISH_MODEL_HAIKU",
+  CLAUDISH_MODEL_SUBAGENT: "CLAUDISH_MODEL_SUBAGENT",
+  // Claude Code standard model configuration (fallback if CLAUDISH_* not set)
+  ANTHROPIC_DEFAULT_OPUS_MODEL: "ANTHROPIC_DEFAULT_OPUS_MODEL",
+  ANTHROPIC_DEFAULT_SONNET_MODEL: "ANTHROPIC_DEFAULT_SONNET_MODEL",
+  ANTHROPIC_DEFAULT_HAIKU_MODEL: "ANTHROPIC_DEFAULT_HAIKU_MODEL",
+  CLAUDE_CODE_SUBAGENT_MODEL: "CLAUDE_CODE_SUBAGENT_MODEL",
 } as const;
 
 // OpenRouter API Configuration

package/skills/claudish-usage/SKILL.md

@@ -5,7 +5,7 @@ description: CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to
 
 # Claudish Usage Skill
 
-**Version:** 1.0.0
+**Version:** 1.1.0
 **Purpose:** Guide AI agents on how to use Claudish CLI to run Claude Code with OpenRouter models
 **Status:** Production Ready
 
@@ -214,14 +214,22 @@ claudish --version
 ### Step 2: Get Available Models
 
 ```bash
-# List all available models (auto-updates if cache >2 days old)
-claudish --list-models
+# List ALL OpenRouter models grouped by provider
+claudish --models
+
+# Fuzzy search models by name, ID, or description
+claudish --models gemini
+claudish --models "grok code"
+
+# Show top recommended programming models (curated list)
+claudish --top-models
 
 # JSON output for parsing
-claudish --list-models --json
+claudish --models --json
+claudish --top-models --json
 
 # Force update from OpenRouter API
-claudish --list-models --force-update
+claudish --models --force-update
 ```
 
 ### Step 3: Run Claudish
@@ -275,11 +283,18 @@ git diff | claudish --stdin --model openai/gpt-5-codex "Review these changes"
 
 **Get Latest Models:**
 ```bash
-# Auto-updates every 2 days
-claudish --list-models
+# List all models (auto-updates every 2 days)
+claudish --models
+
+# Search for specific models
+claudish --models grok
+claudish --models "gemini flash"
+
+# Show curated top models
+claudish --top-models
 
 # Force immediate update
-claudish --list-models --force-update
+claudish --models --force-update
 ```
 
 ## NEW: Direct Agent Selection (v2.1.0)
@@ -503,8 +518,8 @@ Use Claudish CLI to implement this feature with Grok model:
 ${featureDescription}
 
 INSTRUCTIONS:
-1. First, get list of available models:
-   claudish --list-models
+1. Search for available models:
+   claudish --models grok
 
 2. Run implementation with Grok:
    claudish --model x-ai/grok-code-fast-1 "${featureDescription}"
@@ -682,7 +697,8 @@ done
 |------|-------------|---------|
 | `--model <model>` | OpenRouter model to use | `--model x-ai/grok-code-fast-1` |
 | `--stdin` | Read prompt from stdin | `git diff \| claudish --stdin --model grok` |
-| `--list-models` | List available models | `claudish --list-models` |
+| `--models` | List all models or search | `claudish --models` or `claudish --models gemini` |
+| `--top-models` | Show top recommended models | `claudish --top-models` |
 | `--json` | JSON output (implies --quiet) | `claudish --json "task"` |
 | `--help-ai` | Print AI agent usage guide | `claudish --help-ai` |
 
@@ -781,7 +797,7 @@ Model 'invalid/model' not found
 **Fix:**
 ```bash
 # List available models
-claudish --list-models
+claudish --models
 
 # Use valid model ID
 claudish --model x-ai/grok-code-fast-1 "task"
@@ -869,10 +885,13 @@ await Task({
 **How:**
 ```bash
 # Auto-updates every 2 days
-claudish --list-models
+claudish --models
+
+# Search for specific models
+claudish --models deepseek
 
 # Force update now
-claudish --list-models --force-update
+claudish --models --force-update
 ```
 
 ### 6. ✅ Use --stdin for Large Prompts
@@ -982,13 +1001,13 @@ const MODELS = ["x-ai/grok-code-fast-1", "openai/gpt-5"];
 **Right:**
 ```typescript
 // Query dynamically
-const { stdout } = await Bash("claudish --list-models --json");
+const { stdout } = await Bash("claudish --models --json");
 const models = JSON.parse(stdout).models.map(m => m.id);
 ```
 
 ### ✅ Do Accept Custom Models From Users
 
-**Problem:** User provides a custom model ID that's not in --list-models
+**Problem:** User provides a custom model ID that's not in --top-models
 
 **Wrong (rejecting custom models):**
 ```typescript
@@ -1002,7 +1021,7 @@ if (!availableModels.includes(userModel)) {
 
 **Right (accept any valid model ID):**
 ```typescript
-// Claudish accepts ANY valid OpenRouter model ID, even if not in --list-models
+// Claudish accepts ANY valid OpenRouter model ID, even if not in --top-models
 const userModel = "custom/provider/model-123";
 
 // Validate it's a non-empty string with provider format
@@ -1056,7 +1075,7 @@ const model = prefs.preferredModel || defaultModel;
 ```typescript
 // In a multi-step workflow, ask once
 if (!process.env.CLAUDISH_MODEL) {
-  const { stdout } = await Bash("claudish --list-models --json");
+  const { stdout } = await Bash("claudish --models --json");
   const models = JSON.parse(stdout).models;
 
   const response = await AskUserQuestion({
@@ -1086,7 +1105,7 @@ await Bash(`claudish --model ${model} "task 2"`);
 1. ✅ **Accept any model ID** user provides (unless obviously malformed)
 2. ✅ **Don't filter** based on your "shortlist" - let Claudish handle validation
 3. ✅ **Offer to set CLAUDISH_MODEL** environment variable for session persistence
-4. ✅ **Explain** that --list-models shows curated recommendations, not all possibilities
+4. ✅ **Explain** that --top-models shows curated recommendations, --models shows all
 5. ✅ **Validate format** (should contain "/") but not restrict to known models
 6. ❌ **Never reject** a user's custom model with "not in my shortlist"
 
@@ -1163,7 +1182,7 @@ async function reviewCodeWithMultipleModels(files: string[]) {
  */
 async function implementWithModel(featureDescription: string) {
   // Step 1: Get available models
-  const { stdout } = await Bash("claudish --list-models --json");
+  const { stdout } = await Bash("claudish --models --json");
   const models = JSON.parse(stdout).models;
 
   // Step 2: Let user select model
@@ -1226,7 +1245,7 @@ Include:
 **Symptoms:** Unexpected API costs
 
 **Solutions:**
-1. Use budget-friendly models (check pricing with `--list-models`)
+1. Use budget-friendly models (check pricing with `--models` or `--top-models`)
 2. Enable cost tracking: `--cost-tracker`
 3. Use --json to monitor costs: `claudish --json "task" | jq '.total_cost_usd'`
 
@@ -1244,7 +1263,7 @@ Include:
 **Symptoms:** "Model not found" error
 
 **Solutions:**
-1. Update model cache: `claudish --list-models --force-update`
+1. Update model cache: `claudish --models --force-update`
 2. Check OpenRouter website for model availability
 3. Use alternative model from same category
 
@@ -1275,5 +1294,5 @@ claudish --help-ai     # AI agent usage guide
 ---
 
 **Maintained by:** MadAppGang
-**Last Updated:** November 19, 2025
-**Skill Version:** 1.0.0
+**Last Updated:** November 25, 2025
+**Skill Version:** 1.1.0