NeuraWork Claude Code harness: repo-local, self-maintaining project knowledge. Bundles two independently installable skills — knowledge-compiler (distils session logs into a per-repo knowledge base) and claudemd-lerner (keeps the CLAUDE.md hierarchy + docs/ current). Knowledge and docs always live inside the repo, never in .claude/. Recon + brownfield seed on install so existing repos can be upgraded.
Install a per-repo learner that keeps the CLAUDE.md hierarchy and docs/ tree current from Claude Code sessions. Captures sessions into daily logs and, on a manual command or a 6-hour SessionStart gate, edits CLAUDE.md + docs/ in place (no knowledge wiki). Trigger when the user says "claudemd lerner", "install claudemd lerner", "keep CLAUDE.md current", "update my project docs automatically", "CLAUDE.md aktuell halten", "docs aktuell halten", or wants session-driven CLAUDE.md + docs/ maintenance that can seed an existing repo.
Install a per-repo, self-building knowledge base into the current repository. Captures Claude Code sessions into daily logs and compiles them into a queryable knowledge/ wiki (concepts + connections + index), injected back at session start. Trigger when the user says "knowledge compiler", "install knowledge compiler", "set up a knowledge base", "knowledge compiler einrichten", "distil my sessions into knowledge", or wants per-repo memory that builds itself and can seed from an existing repo.
How to build software in 2026.
This repository documents modern practices, tools, and workflows for building software in 2026 — from project setup and architecture through delivery and operations.
🚧 Early stage. Structure and content are evolving.
This repo ships a Claude Code plugin, neurawork-cc-harness (under
plugins/), bundling two independently installable skills:
neurawork-cc-harness:knowledge-compiler — per-repo, self-building knowledge base.neurawork-cc-harness:claudemd-lerner — keeps your CLAUDE.md hierarchy + docs/ current.You do not clone this repo to use it. Install the plugin via its marketplace from inside the repo you want to upgrade, in a Claude Code session:
/plugin marketplace add neurawork-git/howtobuildsoftware2026
/plugin install neurawork-cc-harness@neurawork-harness
Then install a skill into your repo by invoking it:
/neurawork-cc-harness:knowledge-compiler
For the full install/upgrade flow (requirements, recon, seeding, FQN/collision),
see the install & upgrade guide. For how it differs from the
coding-suite skills of the same name, see when to use which.
The principles and setup in this repo draw on:
CLAUDE.md, derived from Andrej Karpathy's observations on LLM coding pitfallsWorking on the harness (not just using it)? Clone the repo:
git clone [email protected]:neurawork-git/howtobuildsoftware2026.git
cd howtobuildsoftware2026
See the install guide's local-development section for loading the plugin from a checkout.
Issues and pull requests welcome. Keep changes focused and documented.
MIT — see LICENSE.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub neurawork-git/howtobuildsoftware2026 --plugin neurawork-cc-harnessClaude Code plugin for building, validating, and deploying n8n workflows. Wraps the n8nac CLI (reference 2.4.0) and delegates schema research to the companion plugin `n8n-as-code` by Etienne Lescot.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Build and maintain an LLM-curated personal knowledge base with default local FastEmbed + sqlite-vec search, BM25 fusion, structured evidence, incremental caching, and a compiled graph layer.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 41 skills, 8 agents, 23 commands, 37 hook scripts across 24 events. Cross-agent via skills add.