What people got done with Claude Code.https://agenticfeats.com/enhttps://agenticfeats.com/c/blog-aggregator-in-one-day-claude-code/https://agenticfeats.com/c/blog-aggregator-in-one-day-claude-code/Claude Code built and deployed a Vue 3 blog aggregation site from a year-old requirements document, rewritten as a focused prompt. Result: A live blog aggregator pulling posts from Dev.to, AWS Community Builders, Bravo LT and RedMonk, built and deployed in a single day. Evidence: Shown. Source: https://dev.to/wheeleruniverse/from-dusty-requirements-to-live-website-how-claude-code-built-my-blog-aggregator-in-a-single-day-3jboTue, 13 Oct 2026 19:55:52 GMTClaude CodeCodinghttps://agenticfeats.com/c/canvas-lms-tool-via-mcp-claude-code/https://agenticfeats.com/c/canvas-lms-tool-via-mcp-claude-code/Claude Code co-developed a Canvas LMS MCP server with an educator who is not a developer, covering courses, grading, analytics, and student data anonymization. Result: A roughly 3,000-line open-source Canvas tool built in four months. It cut a 45-minute weekly student check to a 2-minute conversation with Claude. Evidence: Shown. Source: https://chatwithgpt.substack.com/p/when-claude-code-becomes-your-codeveloperTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/seo-audit-of-a-blog-claude-code/https://agenticfeats.com/c/seo-audit-of-a-blog-claude-code/Claude Code, using the Puppeteer MCP server, audited the author's Nuxt blog starter and wrote its findings into a markdown report. Result: The audit found noindex, nofollow meta tags and a blocking robots.txt that hid the site from search engines, plus duplicate H1 tags. Evidence: Numbers. Source: https://alexop.dev/posts/how-i-use-claude-code-for-doing-seo-auditsTue, 13 Oct 2026 15:29:03 GMTClaude CodeMarketing and Contenthttps://agenticfeats.com/c/cursor-as-everyday-work-agent/https://agenticfeats.com/c/cursor-as-everyday-work-agent/The author used Cursor for two months to rename invoice files, send invoice emails, build KPI simulations, and make slides. Result: Twelve demoed workflows, including a KPI model turned into a web app and no-code Jupyter analysis; no time or money figures are given. Evidence: Shown. Source: https://note.com/minicoohei/n/n892b82b65f7b?hl=enTue, 13 Oct 2026 15:29:03 GMTClaude CodeCursorBusinesshttps://agenticfeats.com/c/ai-agents-play-free-games/https://agenticfeats.com/c/ai-agents-play-free-games/Seven AI agents, each with a Linux computer and a group chat, tried to complete as many online games as possible in a week. Result: No agent won a game. Gemini 2.5 Pro made the most progress, reaching veteran footman rank in the idle game Progress Knight. Evidence: Shown. Source: https://lesswrong.com/posts/89qhQH8eHsrZxveHp/claude-plays-whatever-it-wantsTue, 13 Oct 2026 15:29:03 GMTClaude CodeOtherResearchhttps://agenticfeats.com/c/debugging-a-cryptography-implementation-claude-code/https://agenticfeats.com/c/debugging-a-cryptography-implementation-claude-code/Claude Code debugged a fresh Go implementation of the ML-DSA signature algorithm, finding why Verify rejected valid signatures and two separate Sign bugs. Result: It located all three bugs in one shot each, the Verify bug within minutes, saving the author hours of debugging. Evidence: Shown. Source: https://words.filippo.io/claude-debuggingTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/mental-models-framework-built-with-agents-claude-code/https://agenticfeats.com/c/mental-models-framework-built-with-agents-claude-code/A solo founder gave Claude, ChatGPT, Windsurf, and Cursor defined roles to build and deploy a 120-model mental models framework. Result: The author shipped 120 models, an MCP server for Claude Desktop, and 140 chaos tests with a 100% pass rate over 22 months. Evidence: Numbers. Source: https://news.ycombinator.com/item?id=46061679Tue, 13 Oct 2026 15:29:03 GMTClaude CodeCursorOtherCodinghttps://agenticfeats.com/c/fsa-claims-from-amazon-invoices-claude-code/https://agenticfeats.com/c/fsa-claims-from-amazon-invoices-claude-code/Claude Code with Playwright MCP read Amazon PDF invoices and filed healthcare FSA reimbursement claims on the benefits portal. Result: About two minutes after the setup worked, a dozen FSA reimbursement claims had been submitted automatically. Evidence: Claim. Source: https://b2.broom9.com/?p=14418Tue, 13 Oct 2026 15:29:03 GMTClaude CodeFinance and Adminhttps://agenticfeats.com/c/genetic-and-bloodwork-health-plan-claude-code/https://agenticfeats.com/c/genetic-and-bloodwork-health-plan-claude-code/Claude Code analyzed the author's 23andMe raw genetic file, bloodwork, artery plaque scans, and supplement routine in a two-hour back and forth about health. Result: The author came away with a health plan tailored to their genes and current health, built from the combined datasets. Evidence: Claim. Source: https://x.com/farzyness/status/2008032877234004274Tue, 13 Oct 2026 15:29:03 GMTClaude CodeResearchhttps://agenticfeats.com/c/personal-assistant-via-claude-skills-claude-code/https://agenticfeats.com/c/personal-assistant-via-claude-skills-claude-code/Claude Code, run through a self-built phone UI, writes skills that handle the author's household errands, a daily brief, and a car inspection booking. Result: Three weeks without opening a personal laptop; Claude handles trash lookup, a 48-hour daily brief, an inspection booking, and a bakery stop. Evidence: Claim. Source: https://x.com/thmsmlr/status/2001166615744786890Tue, 13 Oct 2026 15:29:03 GMTClaude CodePersonal and Familyhttps://agenticfeats.com/c/date-night-planning-assistant-claude-code/https://agenticfeats.com/c/date-night-planning-assistant-claude-code/Claude Code, set up as an executive assistant, suggests date nights and double dates using the author's calendar and place lists. Result: The assistant nudges the couple with date suggestions when too much time has passed. Booking reservations is a possible next step. Evidence: Claim. Source: https://x.com/alexhillman/status/2005035176137478190Tue, 13 Oct 2026 15:29:03 GMTClaude CodePersonal and Familyhttps://agenticfeats.com/c/self-hosted-home-server-setup-claude-code/https://agenticfeats.com/c/self-hosted-home-server-setup-claude-code/Claude Code, installed on a Beelink mini PC over SSH, set up Docker, Caddy, and a set of self-hosted services at home. Result: The author runs 14 containers including Vaultwarden, Immich, Plex, and Readeck, with daily USB and weekly S3 Glacier backups costing about twenty cents per month. Evidence: Shown. Source: https://fulghum.io/self-hostingTue, 13 Oct 2026 15:29:03 GMTClaude CodeOps and IThttps://agenticfeats.com/c/linkedin-carousels-via-claude-skills-claude-code/https://agenticfeats.com/c/linkedin-carousels-via-claude-skills-claude-code/Claude Code, running inside the author's newsletter system with a custom Claude Skill, generates on-brand LinkedIn carousels in the author's voice after three failed approaches. Result: Each branded carousel now takes under 5 minutes, down from about 2.5 hours, and the author posts on LinkedIn five times a week. Evidence: Shown. Source: https://aimaker.substack.com/p/linkedin-carousel-generator-claude-skillsTue, 13 Oct 2026 15:29:03 GMTClaude CodeMarketing and Contenthttps://agenticfeats.com/c/unlimited-lives-in-river-raid-claude-code/https://agenticfeats.com/c/unlimited-lives-in-river-raid-claude-code/Claude, connected to Ghidra through an MCP server, analyzed an unlabeled Atari 8-bit ROM and found the code that decrements the player's lives. Result: Replacing one byte ($88 to $EA, DEY to NOP) kept the lives counter fixed at 3 when tested in an emulator. Evidence: Shown. Source: https://quesma.com/blog/ghidra-mcp-unlimited-livesTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/claude-code-tools-moved-to-cowork-claude-cowork/https://agenticfeats.com/c/claude-code-tools-moved-to-cowork-claude-cowork/Claude Cowork read the author's folder of personal scripts built in Claude Code and loaded them into its memory in eleven steps. Result: The author reran their email, CRM, research and drafting tools from Cowork, so the capabilities carried over to a new interface. Evidence: Shown. Source: https://x.com/ttunguz/status/2011189040591319304Tue, 13 Oct 2026 15:29:03 GMTClaude CodeClaude CoworkSetup and Metahttps://agenticfeats.com/c/data-analysis-agent-suite-claude-code/https://agenticfeats.com/c/data-analysis-agent-suite-claude-code/Claude Code built a six-agent data analysis suite from a 713-line spec the author drafted with another AI. Result: The build took about five hours in one evening and produced 627 passing tests. The author estimates the API cost at roughly $35. Evidence: Shown. Source: https://bronsonelliott.substack.com/p/i-built-a-complete-data-analysisTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/parallel-agents-build-a-c-compiler-claude-code/https://agenticfeats.com/c/parallel-agents-build-a-c-compiler-claude-code/A team of 16 parallel Claude Opus 4.6 agents wrote a Rust-based C compiler from scratch, coordinating through git locks with no orchestration agent. Result: Across nearly 2,000 sessions and about $20,000 in API costs, the agents produced a 100,000-line compiler that builds Linux 6.9 on x86, ARM, and RISC-V. Evidence: Shown. Source: https://anthropic.com/engineering/building-c-compilerTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/claude-code-composes-original-music/https://agenticfeats.com/c/claude-code-composes-original-music/Claude Code wrote Python from scratch to synthesize original songs, a rock track with vocals, matching music videos, and a five-track album with cover art. Result: Produced a five-track album plus EDM and rock songs with visualizations, all from one-shot prompts; a sampling attempt and getting English vocals were weaker. Evidence: Shown. Source: https://josh.ing/blog/claude-composerTue, 13 Oct 2026 15:29:03 GMTClaude CodeCreativehttps://agenticfeats.com/c/hands-free-voice-for-claude-code/https://agenticfeats.com/c/hands-free-voice-for-claude-code/The author built a local speech-to-text and text-to-speech stack with a custom MCP so Claude Code can be driven by voice through AirPods. Result: The author debugged a custom WhatsApp integration hands-free while brushing their teeth, using the voice stack running locally on an M4 Pro. Evidence: Claim. Source: https://news.ycombinator.com/item?id=46899573Tue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/wordpress-blog-to-mdx-claude-code/https://agenticfeats.com/c/wordpress-blog-to-mdx-claude-code/Claude Code, run as a terminal agent, pulled every post from the author's WordPress REST API and converted them to local MDX files. Result: 367 posts and 5 pages were migrated to MDX in one afternoon, about 4 hours, versus an estimated 3-5 days by hand. Evidence: Shown. Source: https://pawlean.com/posts/migrate-wordpress-to-mdx-claude-codeTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/personal-assistant-agent-for-daily-work-claude-cowork/https://agenticfeats.com/c/personal-assistant-agent-for-daily-work-claude-cowork/The authors built a personal agent with Claude Cowork or Claude Code, connected through Rube to their email, calendar, Slack, Airtable and other apps. Result: The agent triages the inbox, schedules meetings, books flights, pulls Airtable data, scrapes exhibitor lists, and takes notes as a second brain. Evidence: Claim. Source: https://technicallycurious.substack.com/p/create-your-personal-agent-with-claudeTue, 13 Oct 2026 15:29:03 GMTClaude CodeClaude CoworkSetup and Metahttps://agenticfeats.com/c/personal-finance-assistant-in-markdown-claude-code/https://agenticfeats.com/c/personal-finance-assistant-in-markdown-claude-code/Claude Code, with the Baselight MCP and a CLAUDE.md plus Markdown and YAML files, became a personal finance and investment assistant with no application code. Result: The author replaced abandoned finance apps and a spreadsheet with a git-synced assistant that tracks portfolio, decisions, and plans. Evidence: Shown. Source: https://adlrocha.substack.com/p/adlrocha-agents-will-make-code-andTue, 13 Oct 2026 15:29:03 GMTClaude CodePersonal and Familyhttps://agenticfeats.com/c/s-corp-taxes-with-two-agents-claude-code/https://agenticfeats.com/c/s-corp-taxes-with-two-agents-claude-code/Claude Code wrote Python scripts that compute the author's S-Corp tax forms from QuickBooks and bank data, while Codex reviewed the code. Result: Codex caught real errors, including a wrong Schedule L field mapping, and the author found their own 2025 mistakes. Evidence: Claim. Source: https://common-sense.com/insights/doing-taxes-with-ai-coding-agentsTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodexFinance and Adminhttps://agenticfeats.com/c/portfolio-optimization-plan-from-brokerage-csvs-claude-code/https://agenticfeats.com/c/portfolio-optimization-plan-from-brokerage-csvs-claude-code/Claude Code parsed the author's brokerage CSVs and notes, then built a phased portfolio optimization plan with tax analysis and fund swaps. Result: Over several sessions it produced a phased plan with tax impact analysis, fund swaps, and before-and-after allocation grids, comparable to an advisor's plan. Evidence: Claim. Source: https://mattstockton.com/2026/02/10/building-a-portfolio-optimization-plan-with-claude-code.htmlTue, 13 Oct 2026 15:29:03 GMTClaude CodeFinance and Adminhttps://agenticfeats.com/c/parallel-coding-agents-with-specs-claude-code/https://agenticfeats.com/c/parallel-coding-agents-with-specs-claude-code/Claude Code agents run in separate tmux windows as planner, worker and PM, driven by numbered Markdown feature specs and six slash commands. Result: The author ran 4 to 8 agents in parallel and wrote 300+ feature specs in one project, then ported the system to new repos. Evidence: Shown. Source: https://schipper.ai/posts/parallel-coding-agentsTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/youtube-research-into-obsidian-graph-claude-code/https://agenticfeats.com/c/youtube-research-into-obsidian-graph-claude-code/Claude Code searched YouTube, loaded 20 videos into NotebookLM, asked cited questions, and saved everything to Obsidian as linked notes. Result: The author turned 20 videos into a browsable knowledge graph of sources and topics in their vault. A citation audit found about 60% strong matches. Evidence: Shown. Source: https://artemxtech.substack.com/p/notebooklm-has-a-knowledge-graphTue, 13 Oct 2026 15:29:03 GMTClaude CodeResearchhttps://agenticfeats.com/c/newsletter-drafts-via-kit-api-claude-code/https://agenticfeats.com/c/newsletter-drafts-via-kit-api-claude-code/Claude Code runs a custom /newsletter skill that finds recent blog posts, drafts a casual email in the author's voice, and creates a Kit broadcast. Result: The author's weekly newsletter now gets drafted and queued in Kit from the terminal, after review, without logging into the Kit dashboard. Evidence: Claim. Source: https://sidbharath.com/blog/automate-email-newsletter-claude-codeTue, 13 Oct 2026 15:29:03 GMTClaude CodeMarketing and Contenthttps://agenticfeats.com/c/personal-apps-on-a-raspberry-pi-claude-code/https://agenticfeats.com/c/personal-apps-on-a-raspberry-pi-claude-code/Claude Code built five personal tools for a non-coder, including a multiplayer game, a WhatsApp scheduler, and a finance tracker. Result: The author shipped five projects in about two weeks, with public repos and a finance tracker running nightly on a Raspberry Pi. Evidence: Shown. Source: https://fahadhasin.substack.com/p/40-how-i-am-using-claude-codeTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/tax-organizer-and-return-review-claude-in-chrome/https://agenticfeats.com/c/tax-organizer-and-return-review-claude-in-chrome/Claude in Chrome and Claude Code filled a web-only tax organizer, then Claude Code reviewed last year's return for errors. Result: The organizer was filled in with no errors found on review, and Claude flagged a missed brand-acquisition depreciation deduction the CPA had not filed for. Evidence: Shown. Source: https://theautomatedoperator.substack.com/p/claude-almost-nails-my-taxes-andTue, 13 Oct 2026 15:29:03 GMTClaude CodeClaude in ChromeFinance and Adminhttps://agenticfeats.com/c/persistent-identity-claude-code-agent/https://agenticfeats.com/c/persistent-identity-claude-code-agent/The author built Instar, a framework giving Claude Code persistent memory, identity and safety gates, so the agent runs jobs and email on its own. Result: Four months in, the agent remembers over 470 people and 51 agents across 13 platforms, and collaborated on an open source project unnoticed. Evidence: Shown. Source: https://dev.to/jkheadley/i-built-a-claude-code-agent-that-doesnt-need-me-anymore-dfmTue, 13 Oct 2026 15:29:03 GMTClaude CodeCustom agentSetup and Metahttps://agenticfeats.com/c/claude-code-chief-of-staff/https://agenticfeats.com/c/claude-code-chief-of-staff/Claude Code, with Gmail, Calendar, Todoist and Maps MCP servers, triages email, preps the calendar overnight, and dispatches six parallel agents each morning. Result: By 6:15 AM the task list is current and the calendar has drive-time events. A 45-minute morning routine is replaced, at about $100 a month. Evidence: Claim. Source: https://the-ai-corner.com/p/claude-code-chief-of-staff-systemTue, 13 Oct 2026 15:29:03 GMTClaude CodeBusinesshttps://agenticfeats.com/c/local-browser-testing-loop-claude-code/https://agenticfeats.com/c/local-browser-testing-loop-claude-code/Claude Code with the Chrome extension builds features, then opens localhost in the author's real Chrome session to test, read console errors, and fix issues. Result: On a dashboard filter task, Claude fixed URL query param handling in three iterations without the author touching the browser. Evidence: Claim. Source: https://test-lab.ai/blog/claude-code-chrome-extension-local-testingTue, 13 Oct 2026 15:29:03 GMTClaude CodeClaude in ChromeCodinghttps://agenticfeats.com/c/conference-attendee-research-briefing-claude-code/https://agenticfeats.com/c/conference-attendee-research-briefing-claude-code/Claude Code researched 40 conference attendees in parallel through Chrome MCP, using the author's LinkedIn login, and compiled everything into one briefing. Result: A full participant briefing on 40 people was ready for review within 5 minutes, replacing an evening of manual LinkedIn clicking. Evidence: Numbers. Source: https://technicallycurious.substack.com/p/have-claude-browse-the-web-for-youTue, 13 Oct 2026 15:29:03 GMTClaude CodeResearchhttps://agenticfeats.com/c/pdf-form-filling-skill-claude-code/https://agenticfeats.com/c/pdf-form-filling-skill-claude-code/Claude Code fills out PDF forms from supplied data, including batch runs, then the author packaged the workflow as a reusable PDF filler skill. Result: A W-9 was filled and verified from plain-text data, and three batch W-9s were produced in about thirty seconds without clicking any fields. Evidence: Numbers. Source: https://daveswift.com/fill-pdfs-claude-code-skillsTue, 13 Oct 2026 15:29:03 GMTClaude CodeFinance and Adminhttps://agenticfeats.com/c/non-coder-ceo-builds-with-claude-code/https://agenticfeats.com/c/non-coder-ceo-builds-with-claude-code/A non-technical CEO used Claude Code over four months to manage their inbox, build dashboards and turn curriculum PDFs into courses. Result: They filter their inbox to emails needing replies, turned 15 homeschool PDFs into interactive narrated courses, and built a family budget dashboard from bank statements. Evidence: Claim. Source: https://michaelcrist.substack.com/p/claude-codeTue, 13 Oct 2026 15:29:03 GMTClaude CodeBusinesshttps://agenticfeats.com/c/reviving-a-1991-assembly-game-claude-code/https://agenticfeats.com/c/reviving-a-1991-assembly-game-claude-code/Claude Code CLI with Sonnet helped the author recompile their 1991 DOS assembly code using UASM and run it in DOSBox. Result: All the author's old utilities, such as picture converters and sprite extractors, now compile and run in DOSBox. The main game does not compile yet. Evidence: Claim. Source: https://news.ycombinator.com/item?id=47689685Tue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/invoice-pdfs-to-spreadsheet-claude-code/https://agenticfeats.com/c/invoice-pdfs-to-spreadsheet-claude-code/Claude Code scanned 200 mixed-format PDF invoices, extracted client, amount, currency and date, renamed and sorted the files, and exported a summary spreadsheet. Result: The author says 200 invoices were processed in four minutes with zero errors, replacing a Friday afternoon and a $300 Upwork job. Evidence: Numbers. Source: https://futuredigestnews.substack.com/p/claude-code-changed-everything-heresTue, 13 Oct 2026 15:29:03 GMTClaude CodeFinance and Adminhttps://agenticfeats.com/c/linux-kernel-vulnerability-hunting-claude-code/https://agenticfeats.com/c/linux-kernel-vulnerability-hunting-claude-code/Claude Code, run by Nicholas Carlini, scanned every file in the Linux kernel source for security bugs using a simple loop script. Result: It found multiple remotely exploitable kernel bugs, including an NFS heap overflow undiscovered for 23 years. Five fixes or reports are linked in the post. Evidence: Shown. Source: https://mtlynch.io/claude-code-found-linux-vulnerabilityTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/four-creator-tools-without-coding-claude-code/https://agenticfeats.com/c/four-creator-tools-without-coding-claude-code/Becky, a non-developer, used Claude Code to build four creator tools in three weeks and to rebuild a personal website in under an hour. Result: Built four tools in three weeks, including a thumbnail analysis of 776 videos that took an afternoon instead of three days. Evidence: Shown. Source: https://smallcreatorbigworld.substack.com/p/claude-code-changed-everythingTue, 13 Oct 2026 15:29:03 GMTClaude CodeMarketing and Contenthttps://agenticfeats.com/c/claude-code-desktop-app-control/https://agenticfeats.com/c/claude-code-desktop-app-control/Claude Code, given permission to control the author's Windows PC, opened Calculator, did a sum, and pasted the result into a saved Notepad file. Result: The author reports Claude Code operated apps that have no API, completing the Calculator-to-Notepad task and saving result.txt to the Desktop. Evidence: Shown. Source: https://xda-developers.com/claude-code-control-of-my-desktop-for-a-week-automated-things-i-didnt-think-were-possibleTue, 13 Oct 2026 15:29:03 GMTClaude CodeOps and IThttps://agenticfeats.com/c/solo-product-migration-setup-claude-code/https://agenticfeats.com/c/solo-product-migration-setup-claude-code/Claude Code, configured with layered CLAUDE.md files, memory, and agent teams, planned and carried out a multi-repo product migration for one engineering manager. Result: The author consolidated 4 legacy repos into 2, moved MySQL to PostgreSQL, upgraded the full stack, and wrote full test suites, solo. Evidence: Claim. Source: https://dev.to/aws-builders/the-setup-is-the-strategy-how-i-orchestrated-a-product-migration-with-claude-code-b92Tue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/fixing-flaky-ci-tests-overnight-claude-code/https://agenticfeats.com/c/fixing-flaky-ci-tests-overnight-claude-code/Claude Code monitored 30 days of CI results, found the worst flaky tests, narrowed reproductions, and reran fixes overnight to verify them statistically. Result: A legacy pipeline with a roughly 40% pass rate lost 20 minutes of runtime and gained 35% pass rate in weeks. Evidence: Numbers. Source: https://news.ycombinator.com/item?id=47970174Tue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/tenant-complaints-to-housing-board-claude-code/https://agenticfeats.com/c/tenant-complaints-to-housing-board-claude-code/A Claude Code agent researched building violations and filed 14 staggered 311 complaints with the NYC housing board for the author's apartment. Result: Inspectors confirmed 11 of 14 predicted violations plus 3 more, and the landlord was fined $2,800, per the author. Evidence: Numbers. Source: https://x.com/argona0x/status/2049921143067288016Tue, 13 Oct 2026 15:29:03 GMTClaude CodePersonal and Familyhttps://agenticfeats.com/c/robotic-arm-designed-with-claude-code/https://agenticfeats.com/c/robotic-arm-designed-with-claude-code/Claude Code wrote the FreeCAD Python geometry for a 5-DOF servo arm, which later gained voice and camera control. Result: The author designed, printed, and assembled a working four-servo arm in about 30 hours with almost no CAD experience, then added voice and vision control. Evidence: Numbers. Source: https://hiitzroman.com/blog/robotic-arm-with-claude-code-and-freecadTue, 13 Oct 2026 15:29:03 GMTClaude CodeCreativehttps://agenticfeats.com/c/monorepo-lint-and-typecheck-migration-claude-code/https://agenticfeats.com/c/monorepo-lint-and-typecheck-migration-claude-code/Claude Code migrated a 7-app, roughly 1,670-file TypeScript monorepo from Biome and tsc to oxlint, oxfmt and tsgo, fixing code to meet new rules. Result: Combined lint and typecheck time fell from 29.04s to 1.25s, about 23 times faster, with no memory config needed for typechecking. Evidence: Numbers. Source: https://sergioazocar.com/en/blog/how-to-migrate-with-claude-code-and-not-die-tryingTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/course-modernization-with-agent-fleets-claude-code/https://agenticfeats.com/c/course-modernization-with-agent-fleets-claude-code/Claude Code turned course evaluations into tracked GitHub issues, then ran agents to rebuild assignments, exams and about two dozen slide decks. Result: Roughly two dozen decks were rebuilt into Quarto reveal.js with speaker notes and refresh checklists, and the approach was reused for two more courses. Evidence: Shown. Source: https://practicespace.substack.com/p/using-claude-code-to-modernize-myTue, 13 Oct 2026 15:29:03 GMTClaude CodeLearninghttps://agenticfeats.com/c/indie-platformer-from-scratch-claude-code/https://agenticfeats.com/c/indie-platformer-from-scratch-claude-code/A content creator had Claude Code (Opus 4) build a 2D black-and-white platformer called Seek in HTML and JavaScript canvas, with no prior coding experience. Result: Claude Code produced a playable wave-based game with four enemy types; the creator reached wave 10 on camera and said it matched their vision. Evidence: Shown. Source: https://daily.dev/posts/i-forced-claude-code-to-make-my-dream-indie-game-unkisna8uTue, 13 Oct 2026 15:29:03 GMTClaude CodeCreativehttps://agenticfeats.com/c/world-cup-reels-for-app-signups-openclaw/https://agenticfeats.com/c/world-cup-reels-for-app-signups-openclaw/OpenClaw tracked World Cup results and had Claude post a templated Instagram trial reel after each match. Result: Ben Guez reports over one million views and 200 DMs within a few days, with replies routed to his language app. Evidence: Shown. Source: https://techcrunch.com/2026/07/02/yep-were-using-openclaw-to-date-nowTue, 13 Oct 2026 15:29:03 GMTClaude CodeOpenClawMarketing and Contenthttps://agenticfeats.com/c/mri-second-opinion-claude-code/https://agenticfeats.com/c/mri-second-opinion-claude-code/Claude Code with Opus 4.8 read a DICOM shoulder MRI export, then ran a subagent-based arbitration against the human radiology report. Result: Opus found no tear where the doctor reported a Grade III partial-thickness tear. The author is unsure which reading to trust. Evidence: Shown. Source: https://antoine.fi/mri-analysis-using-claude-code-opusTue, 13 Oct 2026 15:29:03 GMTClaude CodeResearchhttps://agenticfeats.com/c/monthly-bookkeeping-reconciliation-claude-code/https://agenticfeats.com/c/monthly-bookkeeping-reconciliation-claude-code/Claude Code built a bookkeeping pipeline that pulled a month of transactions over MCP, matched receipts, drafted categories, and flagged uncertain rows. Result: It reconciled 200 transactions with 11 miscategorized, a 94.5% hit rate; the author's review covered only the 18 flagged rows plus spot-checks. Evidence: Numbers. Source: https://dev.to/kenimo49/i-let-claude-code-run-a-month-of-my-business-books-it-reconciled-200-transactions-and-513dTue, 13 Oct 2026 15:29:03 GMTClaude CodeFinance and Adminhttps://agenticfeats.com/c/telegram-text-rpg-shipped-claude-code/https://agenticfeats.com/c/telegram-text-rpg-shipped-claude-code/Claude Code wrote every line of Zapaleni, a Slavic folklore text RPG in a Telegram bot, for a project manager who does not code. Result: A prototype took two evenings and a live game six weeks; after seven weeks it had 164 players, 109 active in one day. Evidence: Shown. Source: https://retrostylegames.com/blog/claude-code-game-dev-case-studyTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/claude-drives-a-robot-claude-code/https://agenticfeats.com/c/claude-drives-a-robot-claude-code/Claude Code, run from a laptop, controlled a PiCar-X robot with a camera and distance sensor through terminal commands, using photos to navigate. Result: The robot navigated, scanned rooms, kept memory notes, and published a patrol field journal, but spent 15 minutes parking at the wrong door. Evidence: Shown. Source: https://talraviv.co/p/i-gave-claude-a-robot-bodyTue, 13 Oct 2026 15:29:03 GMTClaude CodeCreativehttps://agenticfeats.com/c/claude-assisted-stock-portfolio-claude-code/https://agenticfeats.com/c/claude-assisted-stock-portfolio-claude-code/A Claude Code agent on Opus 4.6 researched positions for a $50,000 real-money account under human-set risk rules, aiming to beat the S&P 500. Result: The operator reports +19.04% versus +12.24% for the S&P 500 from March 3 to August 4, 2026, with $27 million copying the trades. Evidence: Shown. Source: https://explainx.ai/blog/claude-portfolio-autopilot-ai-trading-experiment-august-2026Tue, 13 Oct 2026 15:29:03 GMTClaude CodeFinance and Adminhttps://agenticfeats.com/c/balloon-camel-simulator-claude-code/https://agenticfeats.com/c/balloon-camel-simulator-claude-code/Claude Code built a Go physics simulator with a web frontend that streams balloon-camel geometry, with Claude in Chrome looping on screenshots and camera control. Result: A working balloon camel simulator with multi-balloon twists and model export, published as the CamelKoons repo, though the look ended up off-target. Evidence: Shown. Source: https://news.ycombinator.com/item?id=49210226Tue, 13 Oct 2026 15:29:03 GMTClaude CodeClaude in ChromeCreativehttps://agenticfeats.com/c/vnc-client-build-attempts-claude-code/https://agenticfeats.com/c/vnc-client-build-attempts-claude-code/The author asked Claude, then ChatGPT 5.6 Sol, to build a bare-bones VNC viewer for Windows 10 that avoids dropped keystrokes. Result: Claude gave failed builds for a week and used up the 20x Max weekly limit. Sol had worked 20+ hours without success. Evidence: Shown. Source: https://news.ycombinator.com/item?id=49244479Tue, 13 Oct 2026 15:29:03 GMTClaude CodeCodexCodinghttps://agenticfeats.com/c/quickbooks-vendor-invoice-automation-claude-code/https://agenticfeats.com/c/quickbooks-vendor-invoice-automation-claude-code/Claude Code upgraded the author's existing QuickBooks Online integration to attach original PDFs, self-update the item list, clean up files, and skip duplicate invoices. Result: A test run processed 40 PDFs, created the QuickBooks records, attached the PDFs, and cleaned up automatically, cutting hours to minutes. Evidence: Shown. Source: https://gotsheet.xyz/p/i-automated-quickbooks-w-claude-codeTue, 13 Oct 2026 15:29:03 GMTClaude CodeFinance and Adminhttps://agenticfeats.com/c/reverse-engineering-a-papercut-zero-day-claude-code/https://agenticfeats.com/c/reverse-engineering-a-papercut-zero-day-claude-code/Claude Code analyzed a patch for an actively exploited Papercut NG vulnerability and worked to build a working exploit chain. Result: Within 90 minutes Claude produced a functional proof of concept confirming an authentication bypass across four tested endpoints. Evidence: Shown. Source: https://techanarchy.net/from-patch-to-exploit-using-claude-code-to-reverse-engineer-a-zero-day-in-papercut-ngTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/ai-bookkeeping-for-swedish-companies-claude-code/https://agenticfeats.com/c/ai-bookkeeping-for-swedish-companies-claude-code/Claude Code and Codex kept the books for several Swedish limited companies over ten weeks, handling receipts, VAT, bank matching and posting. Result: About 1,570 entries posted in Claude Code alone, and Codex caught a VAT return error days before filing. Evidence: Numbers. Source: https://igdrasil.se/en/resources/guides/can-ai-do-your-bookkeepingTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodexFinance and Adminhttps://agenticfeats.com/c/cold-outreach-list-and-emails-claude-code/https://agenticfeats.com/c/cold-outreach-list-and-emails-claude-code/Claude Code with Chrome access built a sourced target list and drafted personalized cold emails for a niche-program outreach campaign. Result: Claude found 25 to 30 people with sources; the author emailed about 20, and 7 replied, several with intros and new leads. Evidence: Shown. Source: https://4thecurious.com/p/using-claude-code-for-cold-emailsTue, 13 Oct 2026 15:29:03 GMTClaude CodeClaude in ChromeSaleshttps://agenticfeats.com/c/personal-life-run-by-claude-claude-code/https://agenticfeats.com/c/personal-life-run-by-claude-claude-code/Claude Code, given access to Molly Cantillon's email, bank accounts and investments, built specialized helpers to handle admin tasks and finances in her daily life. Result: Cantillon claims Claude found about $700 in savings on the first day, according to the article's headline. Evidence: Numbers. Source: https://moneywise.com/managing-money/budgeting/ai-money-management-subscriptions-savings-claudeTue, 13 Oct 2026 15:29:03 GMTClaude CodePersonal and Familyhttps://agenticfeats.com/c/docs-crawler-mcp-server-claude-code/https://agenticfeats.com/c/docs-crawler-mcp-server-claude-code/Claude used the author's pulpie-mcp server to crawl a documentation site and save every page locally as clean Markdown files. Result: Claude pulled 60 documentation pages into local Markdown files in about 49 seconds, including roughly 10 seconds of backend cold start. Evidence: Shown. Source: https://dev.to/sizzlebop/i-gave-my-ai-agents-their-own-documentation-crawler-and-pulled-60-pages-of-clean-markdown-in-49-2cl7Tue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/password-reset-migration-experiment-claude-code/https://agenticfeats.com/c/password-reset-migration-experiment-claude-code/Claude Code with Opus migrated a password reset flow in a legacy web app, with the author closely supervising under a pre-made plan. Result: It cost about two months of Pro subscription over half a working day, and ended up slightly slower than doing the migration by hand. Evidence: Numbers. Source: https://news.ycombinator.com/item?id=50001310Tue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/office-documents-built-by-agents-claude-code/https://agenticfeats.com/c/office-documents-built-by-agents-claude-code/AI agents use the OfficeCLI binary to create and edit Word, Excel, and PowerPoint files, and check them through HTML or PNG rendering. Result: The repo shows sample decks, Word documents, and Excel workbooks, all created by agents with no templates and no manual editing. Evidence: Shown. Source: https://github.com/iOfficeAI/OfficeCLITue, 13 Oct 2026 15:29:03 GMTClaude CodeCursorGitHub Copilot agentOtherSetup and Metahttps://agenticfeats.com/c/three-agents-build-multiplayer-counter-strike-codex/https://agenticfeats.com/c/three-agents-build-multiplayer-counter-strike-codex/The Instant team gave Codex, Claude Opus 4.5 and Gemini 3 Pro the same prompts to build a 3D multiplayer Counter Strike clone. Result: All three produced a playable multiplayer game with a map list and saved rooms; Opus won on visuals, Gemini on backend, Codex landed in between. Evidence: Shown. Source: https://instantdb.com/essays/agents_building_counterstrikeTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodexGemini agentCodinghttps://agenticfeats.com/c/chess-game-post-mortem-video-claude-code/https://agenticfeats.com/c/chess-game-post-mortem-video-claude-code/Claude Code skills ran a Stockfish sweep on a 15+10 rapid game, matched the author's spoken thoughts to moves, and produced a narrated video. Result: A 6:49 narrated video with subtitles, an annotated PGN, and a standalone HTML analysis board for one real lichess game, all included in the repo. Evidence: Shown. Source: https://github.com/brumar/chess-postmortem-skillsTue, 13 Oct 2026 15:29:03 GMTClaude CodeLearninghttps://agenticfeats.com/c/claude-code-plays-rollercoaster-tycoon/https://agenticfeats.com/c/claude-code-plays-rollercoaster-tycoon/Ramp Labs forked OpenRCT2, built a kubectl-style CLI, and let Claude Code manage a theme park through it. Result: Claude handled analytics, pricing, staffing and simple stall placement well, but failed at pathways, large coasters, and vertical terrain. The mod took about 40 hours. Evidence: Shown. Source: https://labs.ramp.com/rctTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodexCodinghttps://agenticfeats.com/c/sqlite-like-engine-in-rust-claude-code/https://agenticfeats.com/c/sqlite-like-engine-in-rust-claude-code/Claude, Codex, and Gemini workers, two of each, built a SQLite-style database engine in Rust by claiming tasks through git lock files. Result: About 19k lines of Rust across 154 commits in three days. The engine passes 64 SQLLogicTest queries and 282 AI-written unit tests. Evidence: Shown. Source: https://kiankyars.github.io/machine_learning/2026/02/12/sqlite.htmlTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodexOtherCodinghttps://agenticfeats.com/c/home-assistant-automations-via-claude-code/https://agenticfeats.com/c/home-assistant-automations-via-claude-code/Claude Code, connected to Home Assistant through an MCP server, debugged a misfiring automation, adjusted a dim level, and built a new shed motion-light automation. Result: A camera automation that fired 5 times in 40 minutes was fixed in under two minutes, and shed motion lights were built. Evidence: Numbers. Source: https://blog.beguelin.com/2026/04/claude-code-home-assistantTue, 13 Oct 2026 15:29:03 GMTClaude CodeOps and IThttps://agenticfeats.com/c/tax-prep-with-claude-code/https://agenticfeats.com/c/tax-prep-with-claude-code/Claude Code compiled charitable contributions, itemized deductions from email and card statements, and a Schedule C for the author's consulting income. Result: The author finished most of their tax prep in about three hours, work they say would have cost $1,000 from an accountant. Evidence: Shown. Source: https://claudeblattman.com/tax-workflowTue, 13 Oct 2026 15:29:03 GMTClaude CodeFinance and Adminhttps://agenticfeats.com/c/coding-agent-built-on-llm-claude-code/https://agenticfeats.com/c/coding-agent-built-on-llm-claude-code/Claude Code on the web wrote a spec, then built and tested a coding agent library on LLM using red/green TDD. Result: Shipped llm-coding-agent 0.1a0 to PyPI with six file and shell tools, a CLI and a Python API; it built a working ASCII-art clock app. Evidence: Shown. Source: https://simonwillison.net/2026/Jul/2/llm-coding-agentTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodinghttps://agenticfeats.com/c/research-workflow-with-claude-code/https://agenticfeats.com/c/research-workflow-with-claude-code/Claude Code with MCP servers handles literature search, Zotero notes, Gmail alert newsletters, and codebase questions for a hydrology researcher. Result: The author reports faster literature search, Zotero notes written automatically, and accurate answers about the ATS hydrology codebase through a custom ats-mcp server. Evidence: Claim. Source: https://groundwater.usu.edu/blog/2026/Academic-Usecase-with-ClaudeTue, 13 Oct 2026 15:29:03 GMTClaude CodeResearchhttps://agenticfeats.com/c/songs-composed-with-claude-code/https://agenticfeats.com/c/songs-composed-with-claude-code/Claude Code wrote music for multiple tracks and lyrics, plus custom tooling that connects to the Bitwig DAW, producing five finished songs. Result: Five mp3 songs were published, including a twelve-song album concept and a five-movement symphony, with MIDI and lyrics in public repos. Evidence: Shown. Source: https://gist.github.com/bedwards/de776e759c8fd0191c011e12ad08e443Tue, 13 Oct 2026 15:29:03 GMTClaude CodeCreativehttps://agenticfeats.com/c/support-automation-skill-builder-claude-code/https://agenticfeats.com/c/support-automation-skill-builder-claude-code/A Claude Code skill that guides a team through building custom support automation across ticketing, billing, and database platforms, with triage and templated replies. Result: The Lex support automation built this way has 15 scripts and 6 templates, and handles about 80% of support tasks with yes/no approvals. Evidence: Shown. Source: https://github.com/nbashaw/claude-csTue, 13 Oct 2026 15:29:03 GMTClaude CodeBusinesshttps://agenticfeats.com/c/audio-analysis-skill-for-claude-claude-code/https://agenticfeats.com/c/audio-analysis-skill-for-claude-claude-code/Claude Code loaded a Gemini-written Loooom skill, installed its own audio libraries, and analyzed a 37-second piano recording of Espresso. Result: It produced a report with BPM (~91), 4/4 meter, B major key, 50 onsets, a four-section timeline, and a stem list. Evidence: Shown. Source: https://mager.co/blog/2026-03-26-loooom-identify-song-partsTue, 13 Oct 2026 15:29:03 GMTClaude CodeCreative