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`.https://bsky.app/profile/commandcode.aihttps://bsky.app/profile/commandcode.ai/post/3muxzt226qx23The /fork command creates a new session from the current one with the same context.08 Sep 2026 03:01 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3muxzt226qx23https://bsky.app/profile/commandcode.ai/post/3muwyotjh4e2pMuse Spark 1.3 Max is live in Command Code. New reasoning effort param for harder problems and frontier performance. Run /model, select Muse Spark 1.3, choose max for reasoning07 Sep 2026 17:08 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3muwyotjh4e2phttps://bsky.app/profile/commandcode.ai/post/3mupuctsg2h2xGPT-6 Astra is live in Command Code.04 Sep 2026 21:01 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mupuctsg2h2xhttps://bsky.app/profile/commandcode.ai/post/3mupi26nbjm2xConnect to MCP servers to query data, use tools and automate workflows.04 Sep 2026 17:21 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mupi26nbjm2xhttps://bsky.app/profile/commandcode.ai/post/3mumulx6d3s2xQwen 3.8 Max 0902 is now live in Command Code. It's an upgraded Qwen 3.8 Max: · 2.4T params · 1M context · Post-trained on coding & cowork Available on GOAT, Pro, Max and API03 Sep 2026 16:28 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mumulx6d3s2xhttps://bsky.app/profile/commandcode.ai/post/3mulo3fxgar2xRan 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 finished03 Sep 2026 04:59 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mulo3fxgar2xhttps://bsky.app/profile/commandcode.ai/post/3mul6ifthlz26Meta Muse Spark 1.3 Contributor now live in Command Code. Most capable lowest cost model yet. Opus 5 & GPT 5.6 Sol class benchmark results. Muse spark is one of the top five models in Command Code. 6T tokens already. And it's going open source next week! 🐐 Available in GOAT, Pro, Max, & API.03 Sep 2026 00:19 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mul6ifthlz26https://bsky.app/profile/commandcode.ai/post/3mukr4amaqq2aGemini 3.8 Flash is now live in Command Code GOAT(4x usage). Input: $1.50 Output: $7.50 Cache Read: $0.15 Available on GOAT, Pro, Max plans and API.02 Sep 2026 20:20 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mukr4amaqq2ahttps://bsky.app/profile/commandcode.ai/post/3mukifwcxol25LongCat-2.0 is now free in Command Code. 1.6T params. 1M context. 48B activate. Available on all plans to all subscribers. npm i -g command-code 🐐02 Sep 2026 17:44 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mukifwcxol25https://bsky.app/profile/commandcode.ai/post/3muijuqsakc2sFable 5.1 is now live in Command Code. Claude's most advanced coding model. 75% cheaper cache reads. Available on Max plans and API.01 Sep 2026 23:05 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3muijuqsakc2shttps://bsky.app/profile/commandcode.ai/post/3mucjrntzng2kUse Ctrl+G to open an external editor for your multi-line prompts.30 Aug 2026 13:48 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mucjrntzng2khttps://bsky.app/profile/commandcode.ai/post/3mu7yhwnbi72jUse /plan-review mode to comment on the plan, revise, and approve it when it’s ready.29 Aug 2026 13:33 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mu7yhwnbi72jhttps://bsky.app/profile/commandcode.ai/post/3mu6zfntsue2yTested 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 three29 Aug 2026 04:17 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mu6zfntsue2yhttps://bsky.app/profile/commandcode.ai/post/3mu5sh45zzq2dTencent Hy4 Preview is live in Command Code 🐐 770B mode, 49B active, 1M context. `cmd update` available in GOAT and above plans. Our early internal benchmarks show strong perf yet cheaper per task compared to GLM 5.3 Flash. Y'all share how it goes.28 Aug 2026 16:39 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mu5sh45zzq2dhttps://bsky.app/profile/commandcode.ai/post/3mu2wqzwy3j2kType /resume and get back to your previous conversation • $ cmd --resume opens a picker for earlier sessions • $ cmd --continue resumes your latest session27 Aug 2026 13:19 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mu2wqzwy3j2khttps://bsky.app/profile/commandcode.ai/post/3mtztyfe7qq2cQwen 3.8 Flash is now available in Command Code with 2x usage limits on the GOAT plan. 🐐27 Aug 2026 02:56 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mtztyfe7qq2chttps://bsky.app/profile/commandcode.ai/post/3mtyqpimnr72rGLM 5.3 Flash aka Ox Alpha is now live in Command Code 4x usage in GOAT plan $40 credits. ~24K reqs. ~1.2B tokens Available across all plans and API 🐐26 Aug 2026 16:25 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mtyqpimnr72rhttps://bsky.app/profile/commandcode.ai/post/3mtxdgthpct2tMinimax M3 and M2.7 are now free in Command Code. next 10 days. all subs. all plans. 🐐26 Aug 2026 02:55 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mtxdgthpct2thttps://bsky.app/profile/commandcode.ai/post/3mtvwgwnvje2ePaste 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.25 Aug 2026 13:30 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mtvwgwnvje2ehttps://bsky.app/profile/commandcode.ai/post/3mttyrh5wmp2rAlipay is now supported in Command Code. More ways to pay and be a GOAT.24 Aug 2026 19:06 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mttyrh5wmp2rhttps://bsky.app/profile/commandcode.ai/post/3mtnja4yy2d2tBinge code this weekend with free "Ox Alpha" 🐐22 Aug 2026 05:12 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mtnja4yy2d2thttps://bsky.app/profile/commandcode.ai/post/3mtkkvbkf5m2aTested 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 iterations21 Aug 2026 01:04 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mtkkvbkf5m2ahttps://bsky.app/profile/commandcode.ai/post/3mtjy6s422o2rText-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.20 Aug 2026 19:29 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mtjy6s422o2rhttps://bsky.app/profile/commandcode.ai/post/3mtfqd7go7q2rQwen 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 🐐19 Aug 2026 02:58 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mtfqd7go7q2rhttps://bsky.app/profile/commandcode.ai/post/3mtfd6kdx5w2eGLM-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) 🐐18 Aug 2026 23:02 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mtfd6kdx5w2ehttps://bsky.app/profile/commandcode.ai/post/3mtecq5ebvl2yLaunching `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 project18 Aug 2026 13:22 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mtecq5ebvl2yhttps://bsky.app/profile/commandcode.ai/post/3mtcvgx75le2nGPT 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. 🐐17 Aug 2026 23:51 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mtcvgx75le2nhttps://bsky.app/profile/commandcode.ai/post/3mt4pwnnj2c2kWriting 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.15 Aug 2026 12:57 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mt4pwnnj2c2khttps://bsky.app/profile/commandcode.ai/post/3mt3pfzerfa2aTested 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 5.315 Aug 2026 03:15 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mt3pfzerfa2ahttps://bsky.app/profile/commandcode.ai/post/3mt2woyiua32sGLM 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 & API14 Aug 2026 19:52 +0000at://did:plc:k2iztyhcmp2buz2a6aenwkcn/app.bsky.feed.post/3mt2woyiua32s