Shipyard

Full-stack ephemeral environments on every pull request.
Co-hosting @readkubelist | Spreading the gospel:

[Shipyard @shipyardbuild]

https://t.co/RBHs2ascbH

[Shipyard @shipyardbuild]

up until recently, there was a very real tradeoff between delivery velocity and stability

shipping fast meant monitoring new deployments really closely

fast forward to 2026, and we have a new environment “stack” that developers and agents move with, not around

[Shipyard @shipyardbuild]

here's how to use the /loop command:

https://t.co/PKkUqyLfSy

[Shipyard @shipyardbuild]

now you can schedule your #ClaudeCode tasks to repeat on a loop

devs are finding this super valuable for PR babysitting:

tell Claude to watch your PRs, react to build logs, and resolve any issues brought up in the comments

[Shipyard @shipyardbuild]

here's how Claude Code handles different types of tokens:

https://t.co/aGLLrJAiZb

[Shipyard @shipyardbuild]

Claude tokens == NLP tokens

these are the smallest units of text that LLMs use to process input/generate output (1 token = 1 word, 1 subword, or 1 letter, depending on your model)

[Shipyard @shipyardbuild]

https://t.co/lPE9os3VUi

[Shipyard @shipyardbuild]

there isn’t exactly a wrong choice for a container registry, but how to eval which is right for you?

- use the CR bundled with your cloud/git ecosystem
- OSS vs. proprietary: both $$ in different ways
- artifact support (OCI, helm, AI model)
- vuln scanning/IAM

[Shipyard @shipyardbuild]

engineering teams are improving their #ClaudeCode workflows every day. but CC should test its own work

a feature might take ~10 tweaks to get right, most obvious after running simple smoke/UI tests

give agents access to real infra: they can self-verify

https://t.co/yhlfmMsBXm

[Shipyard @shipyardbuild]

some tasks are too complex for @claudeai subagents. that's where #multiagent orchestrators come in, allowing a lead coding agent to delegate tasks and spawn agents as needed

in this post, we take a quick look at Gas Town and Multiclaude ⬇️

https://t.co/CThyHEsFNz

[Shipyard @shipyardbuild]

6 months in, #ClaudeCode and #GeminiCLI have become two of the most established CLI-based coding agents

they're both driven by SOTA models (Opus 4.5 and Gemini 3 Pro).

here's how they compare

https://t.co/p95flD0X6S

[Shipyard @shipyardbuild]

#claudecode has always stood out for its filesystem + ops capabilities. in fact, CC is a CLI-based agent for anything, not just coding

they built a solid UI on top of Claude Code’s foundation to make a tool for file-related work, called Claude Cowork

https://t.co/QgmQCC0gBc

[Heavybit @heavybit]

On episode 48 of The Kubelist Podcast (@readkubelist), Marc (@marccampbell) and Benjie (@shipyardbuild) sit down with Justin Cappos, professor at NYU and a pioneer in software supply chain security. Tune in!

https://t.co/uwzS9ELMNH

[Shipyard @shipyardbuild]

engineering teams spend so much time during the year talking about dev productivity.

dec is a difficult time to keep those metrics up anyway. why not use the holiday stretch to catch up on your skills + learn new things?

read about dev enrichment:

https://t.co/hdQhLNQlmF

[Shipyard @shipyardbuild]

AI #agents alone are pretty capable, but #MCP servers extend what they can accomplish

as a dev, you’ll want to connect your tools to your agent via MCP to handle more types of tasks

here are six MCP servers that help our team code more efficiently ⬇️

https://t.co/JOZgdgdWll

[Shipyard @shipyardbuild]

agents need smarter feedback loops to validate the code they write

a test-first approach can help with that

give #agents well-defined prompting, the @playwrightweb #MCP, and #TDD principles to help them write (and improve) their own tests, + run those tests against their code

[Shipyard @shipyardbuild]

@mazeincoding staging's broken

[Shipyard @shipyardbuild]

are you ready to introduce a coding #agent into your dev loop?

at Shipyard, we're big fans of #claudecode. we wrote a guide with our best pro tips, so you can get high-quality code from your agent right away 🤖

https://t.co/UHSYyJZ9IM

#AIagents #developers

[Shipyard @shipyardbuild]

@hey_amandam @torcdotdev @apollographql @goose_oss 🔥🔥🔥

[Shipyard @shipyardbuild]

we’ve got some HUGE news:

the Shipyard #MCP server is now in open beta!

use it for:
✅ writing + improving #E2E tests
✅ sandboxing #agent workflows
✅ live, in-depth code reviews

we’re looking for user feedback, so reach out with any questions/comments 👀