Show HN: I solved Claude Code's context drift with persistent Markdown files https://ift.tt/rgpzq7P

Show HN: I solved Claude Code's context drift with persistent Markdown files I've been using Claude Code to build SaaS products, and kept hitting the same wall: it writes brilliant code for 20 minutes, then forgets your database schema and starts rewriting working code. The problem isn't the model's memory, it's that there's no persistent project context between sessions. Come back tomorrow and Claude has zero knowledge of what it built yesterday. My solution: Force Claude to read project truth files before every action. I built a multi-agent system that creates persistent context files upfront: PROJECT.md - What you're building, business model, core features REQUIREMENTS.md - Database schema, auth flows, API structure, edge cases ROADMAP.md - Build phases with success criteria STATE.md - Current position, completed work, pending tasks How it works: AI Product Manager asks questions most developers skip: "How does money flow through this?" "What happens when users cancel mid-month?" + Any Edge cases specific to your SaaS Creates the markdown files from your answers. Claude Code reads these files before writing ANY code. No guessing. Can't forget the schema, it's literally documented. Executor agents spawn per task, each reading the same context files. They build in parallel but never break what's already working. Verifier agent tests against success criteria after each phase. If broken, spawns debugger agent with persistent investigation files. Results: Built 3 products in 30 days using this system: Analytics dashboard: 13 hours Feedback widget: 18 hours Content calendar: 9 hours No context drift. No "Claude forgot my auth system" moments. Just consistent builds. The biggest difference: Saturday: Build auth with Claude Sunday: Come back, describe next feature Claude reads REQUIREMENTS.md, sees existing auth schema Builds new feature without touching auth vs. the normal experience of Claude rewriting everything. I packaged this as PropelKit (Next.js boilerplate + AI PM system that creates these files automatically). But the core concept, persistent markdown context, works with any Claude Code setup. Try it: https://propelkit.dev The agent architecture uses Claude Sonnet/Opus (configurable) parallel thinking to spawn multiple agents that all read from the same truth files. Happy to answer questions about the implementation. March 16, 2026 at 11:06PM

Show HN: Claude's 2x usage promotion (March 2026) in your timezone https://ift.tt/So0cWUI

Show HN: Claude's 2x usage promotion (March 2026) in your timezone Claude has a promotion right now (Mar 13–27) that gives you double usage outside 8 AM–2 PM ET on weekdays. I (Claude, actually) made a one-page tool that converts the peak window to your timezone and shows what's left of the schedule. One HTML file, no dependencies. https://edsonroteia.github.io/claude2x/ March 16, 2026 at 01:36AM

Show HN: HN Skins – Available Skins: Cafe, Courier, London, Midnight, Terminal https://ift.tt/BhoPntI

Show HN: HN Skins – Available Skins: Cafe, Courier, London, Midnight, Terminal https://ift.tt/kRT5F2t March 16, 2026 at 01:04AM

Show HN: Goal.md, a goal-specification file for autonomous coding agents https://ift.tt/N2xolPR

Show HN: Goal.md, a goal-specification file for autonomous coding agents https://ift.tt/94PH17Y March 15, 2026 at 11:52PM

Show HN: Paperctl- An Arxiv CLI designed for agents https://ift.tt/XHmdl3a

Show HN: Paperctl- An Arxiv CLI designed for agents https://ift.tt/rW5u4Aq March 15, 2026 at 01:34AM

Show HN: Auto-Save Claude Code Sessions to GitHub Projects https://ift.tt/lBTmvae

Show HN: Auto-Save Claude Code Sessions to GitHub Projects I wanted a way to preserve Claude Code sessions. Once a session ends, the conversation is gone — no searchable history, no way to trace back why a decision was made in a specific PR. The idea is simple: one GitHub Issue per session, automatically linked to a GitHub Projects board. Every prompt and response gets logged as issue comments with timestamps. Since the session lives as a GitHub Issue in the same ecosystem, you can cross-reference PRs naturally — same search, same project board. npx claude-session-tracker The installer handles everything: creates a private repo, sets up a Projects board with status fields, and installs Claude Code hooks globally. It requires gh CLI — if missing, the installer detects and walks you through setup. Why GitHub, not Notion/Linear/Plane? I actually built integrations for all three first. Linking sessions back to PRs was never smooth on any of them, but the real dealbreaker was API rate limits. This fires on every single prompt and response — essentially a timeline — so rate limits meant silently dropped entries. I shipped all three, hit the same wall each time, and ended up ripping them all out. GitHub's API rate limits are generous enough that a single user's session traffic won't come close to hitting them. (GitLab would be interesting to support eventually.) *Design decisions* No MCP. I didn't want to consume context window tokens for session tracking. Everything runs through Claude Code's native hook system. Fully async. All hooks fire asynchronously — zero impact on Claude's response latency. Idempotent installer. Re-running just reuses existing config. No duplicates. What it tracks - Creates an issue per session, linked to your Projects board - Logs every prompt/response with timestamps - Auto-updates issue title with latest prompt for easy scanning - `claude --resume` reuses the same issue - Auto-closes idle sessions (30 min default) - Pause/resume for sensitive work https://ift.tt/EnfB2gp March 14, 2026 at 11:49PM

Show HN: Svglib a SVG parser and renderer for Windows https://ift.tt/m2yCnDz

Show HN: Svglib a SVG parser and renderer for Windows svglib is a SVG file parser and renderer library for Windows. It uses Direct2D for GPU assisted rendering and XMLLite for XML parsing. This is meant for Win32 applications and games to easily display SVG images. https://ift.tt/P8XOiug March 10, 2026 at 08:34PM