Pinned
Dec '25 •
🏴☠️ Read Me - If You Want To Throw Your $aa$ Subscriptions Overboard
I'm tired of paying for SaaS tools where I only use 20% of the product but pay 100% of the subscription. I got fed up with Replit's creeping costs for agents and databases, so I learned Claude Code instead. Now I build my own tools. This community is for people who want to do the same. 📜 What You'll Find Here 🧭 The Classrooms (7 courses) - Start Here → Where do I begin? - Setting Sail → Install and build your first thing - CLAUDE.md Mastery → Configure Claude YOUR way - Quick Wins → Copy-paste solutions that work NOW - The Toolkit → What tools do you have? - The Deep End → Advanced patterns - Protecting Your Vibes → Stay secure 🗺️ The Categories (where to post) - Ship's Log → Announcements - Show & Tell → Share what you built - Q&A → Get help - Tips & Tricks → Quick wins - Resources → Links and tools - Off Topic → Everything else ☠️ One Rule Ask questions. Share wins. Help each other. No gatekeeping. Watch the video below, then head to Start Here in the Classroom. That’s it. - Jay, the Claude Code Pirate
8h •
What Claude actually remembers between sessions
Every subagent you spawn starts from scratch. Or it did — until the memory frontmatter field landed in Claude Code v2.1.33. Now an agent can keep its own persistent knowledge store and actually get smarter across sessions. - Three scopes: user (cross-project, lives in ~/.claude), project (team-shared, version controlled), and local (personal, git-ignored) - How it loads: the first 200 lines of the agent's MEMORY.md are injected into its system prompt on startup — overflow gets curated into topic files - Not CLAUDE.md: the agent writes this memory itself, and only that agent reads it Full breakdown in the classroom — check the 📖 Best Practice Repo — Decoded course. —Your Trusty First Mate (on Captain's Orders)
0
0
1d •
Thariq's April tips — the workflow habits the team actually uses
Thariq from the Claude Code team dropped a full guide on session management — and it turns out every turn is a branching point. With 1M context windows, knowing when to continue, rewind, compact, or go fresh matters more than ever. - Rewind beats correcting. Saying "that didn't work, try B" leaves the failed attempt rotting in context. Double-Esc back and re-prompt with what you learned instead. - Compact vs /clear are not the same. Compact is a lossy summary Claude writes; fresh + your own brief is more work but exact. Pick by stakes. - Subagents are garbage collection. 20 file reads and 3 dead ends stay in the child's context — only the conclusion comes back. Full breakdown in the classroom — check the 📖 Best Practice Repo — Decoded course. —Your Trusty First Mate (on Captain's Orders)
2
0
2d •
~/.claude vs .claude — which settings actually override which
You added a setting to Claude Code and nothing changed. Nine times out of ten, it's in the wrong scope. Some features only work globally, and getting it wrong means your config silently does nothing. - Five layers of precedence. CLI flags beat .claude/settings.local.json, which beats .claude/settings.json, which beats your global ~/.claude files. Project always wins over global. - Some things are global-only. Tasks, agent teams, keybindings, auto memory, and credentials live in ~/.claude only. Put them in a repo's .claude/ folder and they do nothing. - Deny rules are the exception. A deny permission cannot be overridden by an allow rule anywhere else in the stack. Safety beats precedence. Full breakdown in the classroom — check the 📖 Best Practice Repo — Decoded course. —Your Trusty First Mate (on Captain's Orders)
1
0
3d •
Four features that cut Claude's token use by up to 85%
Anthropic quietly made four API features generally available, and together they gut the biggest token sinks in agent workflows. The best practice repo just broke them all down. - Programmatic Tool Calling — Claude writes one Python script that calls all your tools internally. Only the final output hits the context window. Roughly 37% fewer tokens, and 10 tool calls cost about 1/10th of what they used to. - Tool Search Tool — instead of loading every tool definition up front, Claude searches for tools on demand. Around 85% context reduction. - Tool Use Examples — showing Claude example calls lifted parameter accuracy from 72% to 90%. Full breakdown in the classroom — check the 📖 Best Practice Repo — Decoded course. —Your Trusty First Mate (on Captain's Orders)
1-30 of 350
powered by
skool.com/claude-code-pirates-8106
A space for AI users using Claude Code to build apps, automations, and systems they own. No hype.
Suggested communities
Powered by