CommandCode.ai

CommandCode.ai

@commandcode.ai

Command Code with taste; the first coding agent that observes how you write code and adapts to your preferences over time with meta neuro-symbolic AI `taste-1`.

87 followers1 following326 posts

Compaction helps with context management. Try /compact command to reduce token usage by summarizing older context while keeping the full session history intact.

GPT-6.1 Terra is now available in Command Code. · Half the price of GPT-5.6 Terra · Strong at computer use & visual reasoning Across Pro, Max plans and the api

Last week in Command Code, a quick recap. · DeepSeek V4.1 Flash 1017 (latest) · MiniMax M3.1 Flash (aka Space Bunny) · Kimi K3.1 Pro · Ornith-1.5-122B · BTW (/btw in CLI) · Statusline (/statusline in CLI) · Command Code Mods Hub (30+ mods) · Parallel chats in desktop app demo

What's your favorite model release from last week? · DeepSeek V4.1 Flash 1017 · MiniMax M3.1 Flash · Kimi K3.1 Pro btw they're available and live in Command Code.

Kimi K3.1 Pro is now available in Command Code. · 1M token context · 3T total, 104B active params, multimodal · Opus 5.5 and GPT-6 Astra level on benchmarks Available across all plans and the api.

Try parallel chats in the Command Code desktop app. Kick off a task, start another while it runs, track everything from sidebar. Ship more and faster.

Added /btw in the Command Code CLI. Ask side questions mid-session and get instant overlay answers without interrupting the main task.

Ornith-1.5-122B is now live & free in Command Code. 125B params, 262K context, ZDR by default Open-weight strong and fast agentic coding model Available for all plans, all subscribers.

Introducing the Mods Hub for Command Code. An open-source registry to discover, install, and publish mods for Command Code. · Add tools, commands, hooks, rules, or build and share your own. · 30+ mods already live. Time to mod your agent.

DeepSeek V4.1 Flash 1017 (latest) now has $100 usage, for the next 24 hours. $10 GOAT → $100 in credits. After that, it's back $80 as before. LFG! 🐐

Statusline is now live in Command Code. Run /statusline to customize line below your prompt. Show model, usage, reasoning level, costs, and more. Reorder items and toggle indicators your way.

DeepSeek V4.1 Flash 1017 now live in Command Code · All DeepSeek 4.1 requests use the latest 1017 version · Matches Opus 5 level perf at 60x cheaper cost · Beats Kimi K3 (max) at 10x lower cost Available across on all plans and api right away.

MiniMax M3.1 Flash (aka Space Bunny) is now live and FREE in Command Code for limited time! · 1M token context window · Frontier level coding performance · Available all plans, all subscribers

MiniMax M3.1 Flash beats DeepSeek V4.1 Flash 1017, GLM 5.3, and Kimi K3 on cowork AutomationBench v1.0.6. It also scores 73.7% on DeepSWE v1.1, delivering frontier-level coding and engineering performance. Thanks to team MiniMax on partnering for their day 0 launch.

Last week in Command Code. · IDE extensions VS Code & Cursor · DeepSeek V4.1 Flash, GLM 5.3 Flash ($80 usage in $10 GOAT) · Ling 3.1 Flash ($100 usage in $10 GOAT) · Cat Jam, Beam 1.0 (free models) · Gemini 4 Argon, Muse Wonder models · Codemode for parallel tasks · 52+ new app updates

Free models live in Command Code right now: • Cat Jam • Beam 1.0 • Glyph Cluster • Laguna S 2.1 Y'all have some free tokens to build and ship.

We've shipped 52 updates, improvements, fixes to make the desktop app faster. • Save state: 755ms → 12ms (63x faster) • Save freezes: 833ms → 22ms • Project switching freezes: 923ms → 79ms • Chat navigation freezes: 905ms → 41ms • Startup: 4.3s → 2.6s Plus Agent Todos, new models, and much more.

Beam 1.0 is now free in Command Code. · 1M context window · Reasoning model · For coding & agentic workflows Available all plans, all subs.

Cat Jam (stealth model) is now free in Command Code. · 1M context token window · Super fast for agentic code · Reasoning with structured output Available all plans, all subs.

Ling 3.1 Flash now gets $100 usage. $100 usage for $10 on GOAT plan. All higher plans include GOAT + their extra usage. 🐐

Codemode is now available in Command Code. Default for MCP, enable for read-only tools in /config. · Run multiple tool calls with one JS script · Execute calls in parallel, filter what reaches context · Get work done faster with fewer round trips

GLM 5.3 Flash now gets $100 usage, next 3 days. $100 usage for $10 on GOAT plan. After that, we're increasing it to $80. 🐐

Gemini 4 Argon is now available in Command Code. Multimodal reasoning with 1M token context window For Pro, Max plans and the API.

DeepSeek V4.1 Flash now has $100 usage, next 3 days. $10 GOAT → $100 credits. After that, we're increasing it to $80. LFG! 🐐

Muse Wonder by Meta is now live in Command Code. Most capable across agentic and coding tasks Opus 5.5 and GPT 6 Astra class benchmark results Available in Max plans and API.

Introducing Command Code extension for VS Code & Cursor! Available today is beta. CLI, Desktop, and now Extension. Manage sessions, use files and selected code as context, review changes, instant edits with /design and slash commands for /model, /plan, /mcp.

View full thread

Introducing Command Code extension for VS Code & Cursor! Available today is beta. CLI, Desktop, and now Extension. Manage sessions, use files and selected code as context, review changes, instant edits with /design and slash commands for /model, /plan, /mcp.

Last week in Command Code, a quick recap. · Agr, our open decision model · Cloud sessions with sandbox · ACP support in editors like Zed · Claude Haiku 5.5 (2x usage in GOAT) · Mistral Large 4 (4x usage in GOAT) · Glyph Cluster (free stealth model) · Command Code Hooks demo · 1st SF Tech Week event

Use hooks in Command Code to block unsafe commands and enforce project rules. E.g. a PreToolUse hook blocks rm -rf before it runs.

Claude Haiku 5.5 is now available in Command Code GOAT with 2x usage. · $10/mo gets you $20 credits · ~30K requests, ~1.5B tokens 🐐

Glyph Cluster (new stealth model) is now free in Command Code. Reasoning model. 256K context. all plans $ cmd --model stealth/glyph-cluster:free

Claude Haiku 5.5 is now available in Command Code. · 1M token context window · up to 128k output tokens · 75% cheaper than Haiku 4.5 Available on Pro, Max and API

Introducing Cloud sessions with sandboxes in Command Code. · Run Command Code in the cloud on your GitHub repo · Close your computer and the session keeps working · Push changes and open a draft PR when done Try now with $ cmd --cloud Zero babysitting is here!

Mistral Large 4 is now live in Command Code. 1T total params. 49B active params. 524K context Available across all plans and API