# Claude Code Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/claude-code?page=2
> Markdown URL: https://aitinkerers.org/technologies/claude-code.md?page=2
> Technology record last updated: 2026-09-18T15:14:01Z
> Generated: 2026-09-21T15:42:15Z

Anthropic's agentic coding tool: Unleash Claude's raw power directly in your terminal or IDE to turn complex, hours-long workflows into a single command.

Claude Code is Anthropic’s powerful agentic coding assistant, designed for high-velocity development. It operates natively within your terminal, IDE (VS Code, JetBrains), or via a web interface, allowing you to delegate complex tasks like feature building, bug fixing, and codebase navigation. The agent plans, edits files, executes commands, and creates commits, maintaining awareness of your entire project structure. Internally, Anthropic engineers using Claude Code reported a 67% increase in productivity, demonstrating its capacity to deliver significant gains for Pro and Max plan users.

- Official technology site: https://claude.com/code
- Public AI Tinkerers demos and talks: 215
- Result page: 2 of 9

## Recent Public Talks and Demos

### [Researching agent memory](https://columbus.aitinkerers.org/talks/rsvp_9_U1zLJVobc)

What started as a conversation to understand agent memory frameworks turned into a directory website and a fully autonomous self learning researcher and reporter.

- Event context: AI Tinkerers - Columbus July Meetup — 2026-07-06 — Columbus
- Public talk page: https://columbus.aitinkerers.org/talks/rsvp_9_U1zLJVobc

### [Building Agentic OS for Marketing](https://denver-boulder.aitinkerers.org/talks/rsvp_BZZDcloDPXM)

I have been solo for 3 years after selling my Denver marketing agency. I was doing everything low code until early March when I discovered Claude Code and working at the terminal. I know have moved my system to a full dev stack using Neon, Claude Managed Agents, 5 repos (website, clients, agent os, reporting admin app) to run my entire AI native consultancy with 12+ clients.

- Event context: AI Tinkerers Denver - June Meetup — 2026-06-30 — Denver
- Public talk page: https://denver-boulder.aitinkerers.org/talks/rsvp_BZZDcloDPXM

### [The Blueprint of a North Korean Attack on Open-Source](https://sf.aitinkerers.org/talks/rsvp_OPre5EDPY9A)

I reverse engineered an attempted attack on better-auth, one of the most popular auth libraries on npm. My demo shows you a step-by-step what happens when your repo is under attack and damage it can cause.

- Event context: AI Tinkerers San Francisco: Offensive Security Demo Night — 2026-06-26 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_OPre5EDPY9A

### [Hacking The Browser For Fun ~And Profit~](https://sf.aitinkerers.org/talks/rsvp_dZETAb_xF00)

We'll talk about XBOW's research into native application hacking: the agents' structure, objectives, and inner "iteration" patterns which worked to discover a few dozen high severity bugs in Chromium, including demoing an exploit of one vulnerability which has already been patched.

- Event context: AI Tinkerers San Francisco: Offensive Security Demo Night — 2026-06-26 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_dZETAb_xF00

### [Build a dark factory that’s right for you](https://tokyo.aitinkerers.org/talks/rsvp_F9L8oeUgPp4)

A dark factory for code: an autonomous, multi-agent build crew in Claude Code. I describe what I want in plain language, and a crew of Claude agents does the labour — designing, building, testing, and double-checking — with a single human yes/no before anything lands on main. Work is batched into waves: each wave splits into tasks, and every task runs a fixed five-stage cycle — brainstorm → implement → test → review → wrap-up — as its own Claude Code subagent in its own git worktree, so many build in parallel without colliding. The factory runs each agent as a full interactive Claude session in a tmux pane (rather than headless claude -p), signalled complete by a Stop-hook; I drive and watch the windows through cmux. The whole run is journaled to an on-disk ledger, so it survives reboots and resumes where it left off. The quality net is a Claude Code skill I lean on constantly — a talmudic study, where N orthogonal expert agents each write an independent position on a design, then argue it out (filing challenges, conceding points, revising) until a redactor synthesizes one settled design with the dissent preserved. The factory runs two of these panels over every finished wave and auto-spawns corrective tasks for anything they catch. Then it parks the wave at a "front desk" and asks the only question I ever have to answer: merge, or hold? I'll show how it's wired and share the two pieces that do the most work — the talmudic-study skill, and the plain-language map of the factory itself. Two things are shared here. Both are deliberately product-agnostic — the patterns work on any codebase.

- Event context: AI Tinkerers Tokyo - Shinagawa: June 18th Meetup — 2026-06-18 — Tokyo
- Public talk page: https://tokyo.aitinkerers.org/talks/rsvp_F9L8oeUgPp4

### [Graph-Oriented Generation: Deterministic Context Retrieval for Code](https://manchester-nh.aitinkerers.org/talks/rsvp_SMbTB_Lslqs)

GOG (Graph-Oriented Generation) is a deterministic context-retrieval system for code generation: instead of embedding chunks and pulling them by similarity, it parses the codebase into an AST-derived graph and traverses it to assemble precise context for a prompt. Live, I'll run the same prompt through Claude Code two ways — vanilla, and with GOG injecting context — and walk the full path from the initial prompt, through decomposing the project structure into stratum relationships, to the actual AST graph traversal that selects what the model sees. You'll see the retrieval working, not a slide about it.

- Event context: AI Tinkerers Manchester (Bedford), NH - June 2026 Meetup — 2026-06-17 — Manchester NH
- Public talk page: https://manchester-nh.aitinkerers.org/talks/rsvp_SMbTB_Lslqs

### [Claude Code e Google Vertex para Experimentos de Machine Learning](https://curitiba.aitinkerers.org/talks/rsvp_OoWoCfnBRoo)

É uma apresentação sobre como é possível utilizar claude code em seu computador para realizar experimentos de machine learning. A apresentação mostra o fluxo de trabalho para realizar experimentos a partir de uma idéia. Também se demonstra a possibilidade de utilizar Google Vertex AI para trabalhar com a Cloud caso seu computador principal não seja suficiente para experimentos que necessitam de mais recursos.

- Event context: AI Tinkerers Curitiba: Evento Inaugural — 2026-06-10 — Curitiba
- Public talk page: https://curitiba.aitinkerers.org/talks/rsvp_OoWoCfnBRoo

### [Engenheiro civil + Claude Code: app de terraplenagem 100% determinístico construído por conversa](https://curitiba.aitinkerers.org/talks/rsvp_iwCDvtHEc-s)

KML Earthworks é um app Streamlit que transforma um traçado de estrada de acesso desenhado no Google Earth em estimativa de terraplenagem (perfil longitudinal, volumes de corte/aterro pela fórmula do prismatoide, balanço de massa, diagrama de Bruckner) em segundos — upload de .kml, download de Excel, zero GIS de desktop. Na demo eu vou: (1) desenhar um acesso ao vivo no Google Earth e rodar o app em produção (kml-earthworks.streamlit.app) mostrando o pipeline completo (parse → stationing a cada 20m → enriquecimento de elevação com fallback de API → otimização de grade → volumes → export); (2) abrir o repo no editor e mostrar a estrutura src/ modular, o CLAUDE.md que funciona como guideline persistente para o agente, e rodar os 58 testes ao vivo no terminal; (3) navegar pelos commits para mostrar a evolução notebook → pacote → app por desenvolvimento conversacional com Claude Code, incluindo os pontos onde eu tive que intervir manualmente.

- Event context: AI Tinkerers Curitiba: Evento Inaugural — 2026-06-10 — Curitiba
- Public talk page: https://curitiba.aitinkerers.org/talks/rsvp_iwCDvtHEc-s

### [Cloud Zombie Hunter: An AI Agent vs. the Dead Weight on My Bill](https://medellin.aitinkerers.org/talks/rsvp_OESkSSQF6_o)

I built a terminal-based agent — Claude Code running locally — that hunts two kinds of cloud waste across AWS and Databricks in one session, with evidence and grounded dollar estimates, and never touches anything without my say-so. It looks for two things: Zombies — abandoned resources still billing. On AWS: unattached EBS volumes, unassociated Elastic IPs, NAT gateways with near-zero traffic, stale snapshots, and the one everyone forgets — orphaned CloudWatch alarms left behind when a resource is decommissioned. On Databricks: all-purpose clusters left running with no auto-termination, SQL warehouses with no auto-stop, and scheduled jobs that fail silently but keep getting provisioned. Over-provisioned / mis-configured resources. ECS services whose CPU/memory reservation dwarfs actual utilization, or with autoscaling that never triggers (min capacity too high, scale-in disabled, or tracking a metric that never moves). Oversized EC2/RDS vs Compute Optimizer. Databricks clusters with oversized worker types, autoscaling minimums set too high, all-purpose clusters doing jobs that belong on job clusters, or warehouses sized XXL where LARGE would do.

- Event context: AI Tinkerers Medellín #21 - Source Meridian - 09 de Junio — 2026-06-09 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_OESkSSQF6_o

### [SPEAR: A Framework for Autonomous Agents](https://seattle.aitinkerers.org/talks/rsvp_NEJrLyIhHRU)

I built SPEAR, a management framework for autonomous agents that turns AI work from “prompt → output” into a structured loop: Scope, Plan, Execute, Assess, Resolve. The core idea is that most AI failures are not model failures; they are process failures. Agents often start strong and finish weak because they skip the same steps humans skip when they are moving too fast: clarifying the scope, making the plan visible, checking the work against a rubric, and narrowing the gap before calling it done. In the demo, I’ll show how SPEAR works as a reusable workflow for agentic software development and creative production. I’ll walk through the five phases, show how an agent scopes a task, produces a plan, executes the work, assesses the result against a MECE rubric, and loops back until the output passes. I’ll also show the logs, the assessment rubric, and examples of how the same loop can run for seconds, minutes, hours, or a full workstream. The goal is to show a working management system for autonomous agents, not just another prompting trick.

- Event context: AI Dev Tools Track - Seattle - June 8 — 2026-06-09 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_NEJrLyIhHRU

### [Inhabited-design: an adversarial-persona Claude Code skill that produces delightful AI design (not slop)](https://seattle.aitinkerers.org/talks/rsvp_r_8j0_bmQOg)

Inhabited-design is a Claude Code skill that fights the AI Slop problem: the purple gradients, 3 column CTAs, rounded buttons. It turns "build me an X for Y" into a delightful design with unique UI that actually has a personality. Instead of one-shotting that, the skill samples a different real designer to inhabit on every run. So an energy drink for finance bros came back as Peter Zumthor with actual references, then critiques its own work in the voice of another inhabited critic: Tanner, the 26 year old investment banker living in midtown. The skill uses two established techniques, verbalized sampling (https://arxiv.org/abs/2510.01171) and Intent Factored Generation (https://arxiv.org/abs/2506.09659) to coax the model out the same old design attractors that are models often gets trapped in when designing content. Burns a silly number of tokens. Turns out unique design is expensive. Code: github.com/Shimin-Zhang/inhabited-design

- Event context: AI Dev Tools Track - Seattle - June 8 — 2026-06-09 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_r_8j0_bmQOg

### [Hacking on the Phone](https://nyc.aitinkerers.org/talks/rsvp_u61d13ZwJpY)

Coding over the phone.

- Event context: NY Tech Week Demo Day ft PostHog, Convex, Veris, & HPE — 2026-06-03 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_u61d13ZwJpY

### [Jules: Uma Raposa Que Toca o Meu Negócio Inteiro no Claude Code](https://saopaulo.aitinkerers.org/talks/rsvp_dm9xlYot2e4)

AI collaborator system on top of Claude Code that helps run my whole business and a live recording studio, Jules Live Studio, that turns it into a real two-way conversation with my AI cohost Jules (a fox). The system has two layers worth showing builders: The skills layer. - Custom workflow skills — /think, /dialogue, /write, /research, and a routing rule that picks between them — force the model through structural gates instead of letting it default to the two failure modes every LLM has: enthusiastically agreeing with whatever I just said, and anchoring on its first answer instead of asking what I actually think. Each skill is a small workflow with explicit phases — elicit, challenge, adversarial review, only-then-recommend — that the model cannot skip. The studio layer. - Jules Live Studio is a local recording app that wires the skills layer into a live voice and video loop: speech-to-text in with Whisper, Claude reasoning, ElevenLabs voice out, fox avatar on screen, and OBS recording. The audience watches a real conversation, not a terminal scrollback. For an AI Tinkerers audience, the demo focuses on the parts that matter to builders: - how the routing layer sends different kinds of requests to different workflows - how a skill structurally forces the model to push back instead of agree - how memory and feedback loops keep it useful across sessions - how the live voice/video loop is wired together with off-the-shelf parts - how far you can get without piling on heavyweight agent frameworks

- Event context: AI Tinkerers SP - Meetup de Maio - Kiro & AWS — 2026-05-28 — São Paulo
- Public talk page: https://saopaulo.aitinkerers.org/talks/rsvp_dm9xlYot2e4

### [Will people want your product? Bots can help you find out (and fix it)](https://seattle.aitinkerers.org/talks/rsvp_tYS3msXujf8)

I've made a set of agents that will pressure test your product idea to help it create better product/market fit. I will demo the bots that I trained on my personal 20-years of product leadership experience. I will show how they can help you sharpen your idea to focus on your ICP, do research to help validate it, and create messaging to reach that ICP.

- Event context: GTM / Growth Track - Seattle — 2026-05-27 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_tYS3msXujf8

### [Website RAG-based chatbot that doesn't suck (much)](https://seattle.aitinkerers.org/talks/rsvp_3o5HjPc5kJo)

"What if visitors to our website could chat with our years of free content without making sh*t up?" Will show the bot itself live, walk through how it works, and talk about the future integration.

- Event context: GTM / Growth Track - Seattle — 2026-05-27 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_3o5HjPc5kJo

### [Six Claude Agents and a Trust Boundary: A Clinical Co-Pilot](https://montreal.aitinkerers.org/talks/rsvp_4qzrWmd9MiM)

A multi-agent clinical co-pilot that runs six specialist Claude agents in parallel on top of a PHI-safe pipeline : every LLM call sees only de-identified text, and re-identification happens server-side after the model returns. Live, I'll load a synthetic 68F new-AFib case where the cardiology plan proposes amiodarone for a patient already on warfarin. The Triage, Differential, Pharmacy, Guidelines, Bias-Check, and Communication agents stream into six panels via asyncio.gather. The Pharmacy agent flags the warfarin–amiodarone CYP2C9/3A4 interaction; Bias-Check independently flags anchoring on rhythm control; the orchestrator detects the cross-agent convergence and elevates it as a high-severity flag. I'll then toggle the Safety Gate off so the audience sees raw PHI hit the LLM and get echoed back — then flip it on and show the audit log assertion (zero raw PHI, only counts + SHA-256 hashes). I'll show the FastAPI/WebSocket code that fans out the agents, the trust-boundary diagram, the structured-field redactor, the live audit log tail, and the keystone pytest (test_pharmacy_catches_warfarin_amiodarone). Repo, logs, and 35/35 passing tests are all open.

- Event context: AI Tinkerers Montreal - May Demo Meetup @ Ubisoft — 2026-05-26 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_4qzrWmd9MiM

### [Pull-architecture agents: how I forced myself to do growth work](https://valencia.aitinkerers.org/talks/rsvp_-p7b50BEZW0)

A multi-agent system that manufactures pull for the growth work — writing, conference follow-up, CRM hygiene, responding to news — that I'd otherwise skip when product and ops eat my week. Seven agents across five repos, two APIs, and two websites (one fully autonomous), all driven from the only two surfaces I actually live in: my terminal and Mattermost. The demo walks a live pass through the rig: a LinkedIn contact lands in our self-hosted CRM, an article draft gets pushed to a website, a post-conference follow-up gets queued — every action is a curl command an agent emits, with circuit breakers I can tighten in the moment or across the long arc.

- Event context: AI Tinkerers Valencia May Meetup — 2026-05-26 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_-p7b50BEZW0

### [Dev tools are all you need](https://seattle.aitinkerers.org/talks/rsvp_FBwC1XbQpYE)

Maibook is a desktop app - a network of you and AI agents personalized based on your file system activity. Demo will show: - Maibook briefly - Customized dev tools built for the project - strings_web - centrally manage all strings AI agents see - system and user prompts, tool schemas, tool docstrings, tool field descriptions and constraints - edit in tool, updates source files - dev_web - see sessions and debug what works, what doesn't - inspired by cc viewer - in the works - ccdbug - Others - threadviewer, benchmarking models, etc.

- Event context: AI Tinkerers Seattle: May Demo Night (Ft. Oracle & NVIDIA) — 2026-05-22 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_FBwC1XbQpYE

### [Relighting pictures after they are taken](https://manchester-nh.aitinkerers.org/talks/rsvp_vzrJ5r46hyA)

Using AI and ML I built an application that relights pictures after they were taken. I will demo this process producing pictures that are re-lit using off-the-shelf photography items. Examples can be seen here: https://www.instagram.com/jackshap1/.

- Event context: AI Tinkerers Manchester (Bedford), NH - May 2026 Meetup — 2026-05-20 — Manchester NH
- Public talk page: https://manchester-nh.aitinkerers.org/talks/rsvp_vzrJ5r46hyA

### [GTM in the Terminal — Agent-driven personalized outbound](https://sf.aitinkerers.org/talks/rsvp_O2H7CQUJ6IU)

Cyrus is the cofounder of The Synthesis Company (YC S24). Previously, he was a core contributor to Stanford NLP's DSPy framework and cofounder of WOMBO.ai (100M+ downloads). He'll be demoing GTM-OS, a CLI and TUI he used to programmatically drive hyper-personalized LinkedIn outbound. For AI tinkerers he built usesocial.dev, a CLI to connect your agents to LinkedIn / X and build your own workflows and systems.

- Event context: AI Tinkerers San Francisco: GTM Engineering Track — 2026-05-19 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_O2H7CQUJ6IU

### [From .md Dump to DAG: Rethinking Skills for Multi-Step Workflows](https://doha.aitinkerers.org/talks/rsvp_pXmYX7paZjs)

A new paradigm for Claude Code Agent Skills whose steps actually depend on each other. The current pattern - what every Skill on the market does- is dump a long SKILL.md into the agent's context and hope it follows the instructions in order. It mostly doesn't: the agent skips prereqs, hallucinates outputs that "look right," can't resume after /compact, and produces a different run every time you ask. ClawBio 2.0 replaces the hope with a contract: each skill ships a pipeline.yaml DAG, and a ~500-line CLI exposes start → next → open → done → bundle as the only legal moves. Instead of trying to read prose & remember, the agent calls CLI next, gets told exactly which step is unblocked, and is physically refused if it tries to skip ahead. State lives in one atomic state.json that survives /compact and /clear. Live I'll show: starting a multi-step run, the CLI rejecting an out-of-order step, the agent recovering cleanly from a forced /clear, and the reproducibility bundle (commands.sh + checksums + env) that a Stop hook refuses to let the agent skip. Bioinformatics is just the testbed - the pattern is for any skill where order matters and outputs feed inputs.

- Event context: AI Tinkerers – Doha Inaugural Meetup — 2026-05-18 — Doha
- Public talk page: https://doha.aitinkerers.org/talks/rsvp_pXmYX7paZjs

### [Presentations Made Easy](https://doha.aitinkerers.org/talks/rsvp_9LeSd0u-leg)

I built an internal slide generator where users add in the slide title and some details about the presentation - and it generates on-brand slides, with built-in interactivity.

- Event context: AI Tinkerers – Doha Inaugural Meetup — 2026-05-18 — Doha
- Public talk page: https://doha.aitinkerers.org/talks/rsvp_9LeSd0u-leg

### [Remotion Your Videos](https://hong-kong.aitinkerers.org/talks/rsvp_Dh6XudV0F2c)

I have experimented with Remotion for Video Generation By Claude Code and would be pleased to share this in a 10 - 15 mins live demo. Will prep another good topic that can gen the vid within the demo time :) ps - no worry if demo slots are full, I can do it in another time https://www.linkedin.com/posts/activity-7440352340945117184-XXt0?utm_source=share&utm_medium=member_desktop&rcm=ACoAAAAoDEgBPV2V1HF_Xk1xwmFPNE8qXiGa10g

- Event context: AI Tinkerers Hong Kong & GBA: AI Demo Night @ Google (May) — 2026-05-07 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_Dh6XudV0F2c

### [Taylor Solves Wordle -> New Website Generated on Answer by 3 Competing LLMs](https://raleigh.aitinkerers.org/talks/rsvp_FhyjRFJIyCo)

I'll be presenting a little system I built that allows me, after solving the Wordle, to push the answer up to my home computer where a series of LLMs run to generate three different landing pages based on the Wordle word. It then automatically deploys it to my website, notifying me along the way at each step.

- Event context: AI Tinkerers Raleigh Meetup — May 6, 2026 — 2026-05-06 — Raleigh
- Public talk page: https://raleigh.aitinkerers.org/talks/rsvp_FhyjRFJIyCo

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [MCP](https://aitinkerers.org/technologies/mcp) ([Markdown](https://aitinkerers.org/technologies/mcp.md)) — 129 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [Codex](https://aitinkerers.org/technologies/codex) ([Markdown](https://aitinkerers.org/technologies/codex.md)) — 44 public demos
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [Supabase](https://aitinkerers.org/technologies/supabase) ([Markdown](https://aitinkerers.org/technologies/supabase.md)) — 90 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 220 public demos
- [Cursor](https://aitinkerers.org/technologies/cursor) ([Markdown](https://aitinkerers.org/technologies/cursor.md)) — 65 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [GitHub](https://aitinkerers.org/technologies/github) ([Markdown](https://aitinkerers.org/technologies/github.md)) — 74 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [Anthropic API](https://aitinkerers.org/technologies/anthropic-api) ([Markdown](https://aitinkerers.org/technologies/anthropic-api.md)) — 66 public demos
- [Markdown](https://aitinkerers.org/technologies/markdown) ([Markdown](https://aitinkerers.org/technologies/markdown.md)) — 24 public demos
- [Node](https://aitinkerers.org/technologies/node) ([Markdown](https://aitinkerers.org/technologies/node.md)) — 99 public demos
- [Vercel](https://aitinkerers.org/technologies/vercel) ([Markdown](https://aitinkerers.org/technologies/vercel.md)) — 48 public demos
- [Gemini CLI](https://aitinkerers.org/technologies/gemini-cli) ([Markdown](https://aitinkerers.org/technologies/gemini-cli.md)) — 16 public demos

## More Results

- Previous: https://aitinkerers.org/technologies/claude-code.md
- Next: https://aitinkerers.org/technologies/claude-code.md?page=3