iiinova — where your digital self keeps evolving

Remote Control now available in Command Code. · Run /rc to open your session in Telegram or Discord · Message from your phone and get live responses · Sessions keep running on your computer Control Command Code with your mobile

100

CommandCode.ai @commandcode.ai · 25/09/2026

New in Command Code: /loop command Run a task, then repeat it on a fixed or self-paced schedule until the job is done. Try now: $ npm i -g command-code

000

CommandCode.ai @commandcode.ai · 24/09/2026

You can now use Shift+Tab to bypass permissions. · Switch mid-session · No need to restart with cmd --yolo

001

CommandCode.ai @commandcode.ai · 23/09/2026

Tested Mimo-V2.6-Flash, Grok-4.7, and DeepSeek-V4.1-Flash with 3D SubwayBench. 🔹 DSV4.1-Flash: 9/10 · $0.024 · one-shot · strong 3D UI/UX + gameplay 🔹 Mimo-V2.6-Flash: 8/10 · $0.018 · playable 2D result in ~4 iterations 🔹 Grok 4.7: 3/10 · $0.35 · slower UI + gameplay, needs more iteration

100

CommandCode.ai @commandcode.ai · 22/09/2026

Command Code supports Git worktrees. Use /worktree to create or switch and run parallel sessions, each on its own branch.

000

CommandCode.ai @commandcode.ai · 20/09/2026

Ran FlappyBench on Qwen3.8-Omni-Flash, DeepSeek V4.1-Flash & Gemini 3.8 Flash with the same /design prompt. 🔹 Qwen3.8-Omni-Flash: 9/10 · $0.013 · smooth gameplay & cheaper 🔹 DSV4.1-Flash: 9/10 · $0.0089 one-shot with the lowest cost 🔹 Gemini-3.8-Flash: 5/10 · $0.205 · hard-coded gameplay

101

CommandCode.ai @commandcode.ai · 17/09/2026

Stop copy-pasting errors. IDE diagnostics are quite strong. Open Command Code. Select your code. Type fix this

000

CommandCode.ai @commandcode.ai · 16/09/2026

Introducing Command Code Desktop App! Available today in beta for Mac, Linux, & Windows. Building the most powerful agentic app, starting with code. Multiple agents, files, Git, terminal, browser previews, plans, and instant edits with /design.

100

CommandCode.ai @commandcode.ai · 15/09/2026

Mods are more powerful than plugins. Command Code can build mods and modify any behavior from programmatic hooks to a completely different inference provider. We bet you haven’t experienced something as powerful before. Build a mod now and make Command Code do anything you want.

100

CommandCode.ai @commandcode.ai · 11/09/2026

Ran FlappyBench on DeepSeek V4.1-Flash, GLM 5.3, and Kimi K3 with the same /design prompt. 🔹 DSV4.1-Flash: 9/10 · $0.0089 one-shot with the lowest cost 🔹 GLM-5.3: 9.5/10 · $0.0184 · nailed the UI but cost 2x more 🔹 Kimi K3: 8/10 · $0.0740 · hard-coded gameplay and 8x more

101

CommandCode.ai @commandcode.ai · 10/09/2026

DeepSeek V4.1 Flash is GOAT 🐐

011

CommandCode.ai @commandcode.ai · 08/09/2026

The /fork command creates a new session from the current one with the same context.

000

CommandCode.ai @commandcode.ai · 04/09/2026

Connect to MCP servers to query data, use tools and automate workflows.

000

CommandCode.ai @commandcode.ai · 03/09/2026

Ran FlappyBench on Muse Spark 1.3, Gemini 3.8 Flash, and Grok-4.6 with same /design prompt. 🔹 Muse Spark 1.3: 9/10 · $0.072. Nailed UI in 2 iterations with lowest cost 🔹 Grok-4.6: 9/10 · $0.095 · Matched Muse’s output, but cost 2x more 🔹 Gemini 3.8 Flash: 7/10 · $0.205 · Expensive and not finished

100

CommandCode.ai @commandcode.ai · 30/08/2026

Use Ctrl+G to open an external editor for your multi-line prompts.

000

CommandCode.ai @commandcode.ai · 29/08/2026

Use /plan-review mode to comment on the plan, revise, and approve it when it’s ready.

000

CommandCode.ai @commandcode.ai · 29/08/2026

Tested FlappyBench with /design on Hy4 Preview, Kimi K3, and GLM 5.3. 🔹 Hy4 Preview ($0.0480): Most distinct UI and gameplay 🔹 Kimi K3 ($0.0740): Hardest gameplay and the most expensive 🔹 GLM 5.3 ($0.0184): Smooth gameplay and the cheapest of the three

000

CommandCode.ai @commandcode.ai · 27/08/2026

Type /resume and get back to your previous conversation • $ cmd --resume opens a picker for earlier sessions • $ cmd --continue resumes your latest session

000

CommandCode.ai @commandcode.ai · 25/08/2026

Paste images as your chat input. • Take a screenshot • Paste it into the chat • Describe what’s wrong • Watch Command Code fix the issue Let your screenshots be the context.

011

CommandCode.ai @commandcode.ai · 22/08/2026

Binge code this weekend with free "Ox Alpha" 🐐

000

CommandCode.ai @commandcode.ai · 21/08/2026

Tested FlappyBench on Qwen 3.8 27B, DeepSeek V4 Pro 0813, and Gemini 3.7 Flash All scored 9/10, it comes down to cost, quality, and iterations 🔹 DSV4 ($0.0036): Low cost, solid, but movement need work 🔹 Qwen ($0.0068): One-shot, playable, with UI finish 🔹 Gemini ($0.0083): Needed 2–3 iterations

100

CommandCode.ai @commandcode.ai · 20/08/2026

Text-only models now have vision in Command Code. • A vision model reads the attached image • Your main model gets the context in the same thread • /config lets you choose the vision model Stop describing screenshots. Just attach them.

000

CommandCode.ai @commandcode.ai · 19/08/2026

Qwen 3.8 27B is now live in Command Code. Beats Opus 4.6 Max, GPT 5.6 Luna Max on Artificial Analysis Intelligence Index. Best for coding and long agent tasks. Multimodal with reasoning toggled on/off Available on all plans & API 🐐

010

CommandCode.ai @commandcode.ai · 19/08/2026

GLM-5.3 is already live in Command Code. Same price as GLM-5.2, ~50% better on Zai's internal Code Bench. Still 5–10x cheaper than the frontier closed models (per 1M output tokens, list price today). Plans: $1 Go ($10 credits) · $10 GOAT ($20 credits) 🐐

000

CommandCode.ai @commandcode.ai · 18/08/2026

Launching `a11y` mode in `/design` Run `/design a11y` to catch: • Tap targets that are too small • Focus management problems • Broken keyboard navigation • ARIA and accessible name gaps • Missing or incorrect form labels and errors Run `cmd update`, then try `/design a11y` in your project

000

CommandCode.ai @commandcode.ai · 18/08/2026

GPT 5.6 Sol is now in Command Code GOAT 🐐 Best coding plan with best GPT model. $70 credits. $10/mo GOAT plan gets you: GPT Sol has $70 credits ~105M tokens ~2.1K reqs We've also achieved 99.43% cache hit ratio. Available on GOAT + above. Limited time deal. 🐐

000

CommandCode.ai @commandcode.ai · 15/08/2026

Writing tests is now the easiest part of your workflow. Pick a file, and Command Code will: - Analyze the code - Generate the right test cases - Run the test suite - Resolve failures - Re-run until all tests pass Try it on a file that hasn’t been tested yet.

000

CommandCode.ai @commandcode.ai · 15/08/2026

Tested FlappyBench with GLM 5.3, Fable 5 and GPT-5.6 Sol 3 models. Same prompt with /design command. Scored on features, UX/UI, and cost. 🔹 Fable 5 → 9.5/10 · $0.420 🔹 GLM 5.3 → 9/10 · $0.018 🔹 GPT-5.6 Sol → 9/10 · $0.150 Fable 5 wins on quality, but costs 23x more than GLM 5.3

132

CommandCode.ai @commandcode.ai · 14/08/2026

GLM 5.3 is live in Command Code (2x usage) The best deal: 2x usage, permanently. 🐐 $10 GOAT plan has $20 worth of GLM 5.3 usage. That's ~70M tokens & ~1.3K requests. • Text-reasoning. 1M context • IN $1.4/M · OUT $4.4/M · Cache $0.26/M • Available on all plans & API

000

CommandCode.ai @commandcode.ai · 14/08/2026

Gemini 3.7 Flash is now live in Command Code at 50% OFF. - It's fast with frontier level intelligence - $0.75 input/$3.75 output per 1M tokens - Available on GOAT, Max and Team plans Starts at $10/month $ npm i -g command-code

010

CommandCode.ai @commandcode.ai · 13/08/2026

Pull requests are easier now. Just ask to open a PR, It will: • Read your changes • Draft the description and test plan • Commit and push your branch • Open a well-documented PR Try it with our $10/mo GOAT plan.

000

CommandCode.ai @commandcode.ai · 13/08/2026

Tested FlappyBench with Grok 4.6, GPT-5.6 Sol, and Opus 5. 3 frontier models. Same prompt with /design command. Scored on gameplay features, UX/UI, and cost. 🔹 Grok 4.6 → 9.5/10 · $0.095 🔹 GPT-5.6 Sol → 9/10 · $0.150 🔹 Opus 5 → 9/10 · $0.253 Grok 4.6 gave best output with lowest cost.

100

CommandCode.ai @commandcode.ai · 12/08/2026

Grok 4.6 is now live in Command Code GOAT.

000

CommandCode.ai @commandcode.ai · 12/08/2026

Tested New DSV4 Pro 0813, Kimi K3, and GLM 5.2 with our FlappyBench 3 models, same prompt with the /design command. Reviewed gameplay features, UX/UI, and cost. 🔹 DSV4 Pro 0813 → 8/10 · $0.0005 🔹 Kimi K3 → 9.5/10 · $0.0740 🔹 GLM 5.2 → 9/10 · $0.0480

110

CommandCode.ai @commandcode.ai · 07/08/2026

Code reviews should help you ship faster, not block you. Run /review [PR number] and get your code reviews directly in the terminal • scans the diff • flags risky changes • finds missing tests • posts a ready-to-ship PR review Try now with our $10/mo GOAT plan.

000

CommandCode.ai @commandcode.ai · 06/08/2026

Browse through plans with /plans Browse, review, and annotate saved plans. Select plans from current session vs all. Search across all plans. Keep up with all your planning.

000

CommandCode.ai @commandcode.ai · 06/08/2026

We benchmarked Muse Spark 1.2, Kimi K3, and GLM 5.2 with Flappy Bench 3 models, same prompt with the /design command. Reviewed gameplay features, UX/UI, and cost. 🔹 Kimi K3 → 9.5/10 · $0.0740 🔹 GLM 5.2 → 9/10 · $0.0480 🔹 Muse Spark 1.2 → 8/10 · $0.0187

100

CommandCode.ai @commandcode.ai · 04/08/2026

Plan mode removes the guesswork. When the change is too big for a quick fix: • Your code stays untouched • Plan it first, then review it • Apply exactly as planned No surprises, just clarity.

000

CommandCode.ai @commandcode.ai · 03/08/2026

We ran a test between the new Qwen3.8-Max, Opus 5 and GPT-5.6 Sol. 3 open models. same prompt. one-shot with the /design command. Reviewed gameplay, UX/UI and cost. 🔹 Qwen3.8-Max → 9/10 · $0.0480 🔹 Opus 5 → 9/10 · $0.253 🔹 GPT-5.6 Sol → 9/10 · $0.150

110

CommandCode.ai @commandcode.ai · 02/08/2026

Create custom slash commands and use them frequently. 🔹 Save a prompt as a markdown file 🔹 Define its scope per project or user level 🔹 Run it anytime with dynamic arguments $ /<command-name> [arguments]

000

CommandCode.ai @commandcode.ai · 01/08/2026

GPT-5.6 Terra and Luna are 50% off in Command Code. Get 2X requests for every dollar of credit you spend Luna: - $0.10/M input, $0.60/M output tokens - Available on all plans (Go, Pro, Max, Team) Terra: - $1/M input, $6/M output tokens - Available on Pro, Max, Team For limited time only.

000

CommandCode.ai @commandcode.ai · 01/08/2026

Tested the new DeepSeek V4 Flash, Kimi K3, GLM 5.2. 3 models. 1 prompt. /design command. Reviewed features, UX and cost. 🔹 Kimi K3: 9.5/10 · $0.0740 🔹 GLM 5.2: 9/10 · $0.0480 🔹 DeepSeek V4 Flash: 7/10 · $0.0005 DSV4 is ~150x cheaper, but rough around edges Kimi K3 & GLM 5.2 built a polished game

110

CommandCode.ai @commandcode.ai · 30/07/2026

Inkling-Small by Thinking Machines Lab is now live in Command Code. - $0.50/M input, 1.20/M output tokens - Light-weight model with 12B params - Multimodal: text, image, audio Available on all plans $ cmd --update (to latest) $ cmd --model thinkingmachines/inkling-small

000

CommandCode.ai @commandcode.ai · 30/07/2026

New in v1: Stashing Prompts - `ctrl+s` sets the prompt you are typing aside - press it again and it reappears - no need for ctrl+c and ctrl+v again Never leave a prompt behind, stash it instead.

000

CommandCode.ai @commandcode.ai · 30/07/2026

Stop repeating the same prompt in every session. Agent Skills: an open standard for teaching agents specialized knowledge and workflows. Write it once in a SKILL[.]md file (with references/assets) and reuse it. Save it per project, globally, or in a repo: $ cmd skills add [repo name] --global

000

CommandCode.ai @commandcode.ai · 26/07/2026

Bring back any message or code instantly. Use /rewind to pick a checkpoint, then choose what to restore: conversation, code, or both. Never lose your conversation or code again.

000

CommandCode.ai @commandcode.ai · 25/07/2026

We ran a test between Opus 5, GPT-5.6 Sol, and Kimi K3. One prompt. Across all three models. With our /design command. Ranking (DX, features, and cost): 🔹 Opus 5: 10/10 · $0.25 🔹 Kimi K3: 9.5/10 · $0.12 🔹 GPT-5.6 Sol: 7/10 · $0.32

100

CommandCode.ai @commandcode.ai · 25/07/2026

New in Command Code: dont-ask permission mode. Runs exactly what your allowlist permits Everything else gets denied Built for CI jobs, cron, and unattended runs $ cmd --permission-mode dont-ask No more hung jobs. Opposite of --yolo

000

CommandCode.ai @commandcode.ai · 24/07/2026

Claude Opus 5 is now live in Command Code. - Anthropic's latest thoughtful and proactive model - On frontier intelligence, closet to Fable 5 at half price - Available on plans (Pro, Max, Team) Try now: $ cmd --model claude-opus-5

000

CommandCode.ai @commandcode.ai · 23/07/2026

Ling 3.0 Flash is live in Command Code MoE model built for token-efficient agentic inference at production scale. - Free for all subscribers - 124B params (~5.1B active/token) - 256K context, tool use, implicit caching Try it: $ cmd --model inclusionai/ling-3.0-flash-free

000