Set up or audit Claude Code project memory the right way — a lean CLAUDE.md plus offloaded docs, path-scoped .claude/rules/, and skills — so instructions stay high-signal instead of bloating context.
A personal Claude Code plugin marketplace. It hosts my reusable plugins — commands, agents, skills, and hooks — that I can install into any Claude Code session.
Add the marketplace once, then install any plugin from it:
/plugin marketplace add NebraskaCoder/nebraskacoder-claude-plugins
/plugin install <plugin-name>@nebraskacoder-claude-plugins
You can also browse and manage everything interactively with /plugin.
Useful management commands:
/plugin marketplace list # list added marketplaces
/plugin marketplace update nebraskacoder-claude-plugins
/plugin marketplace remove nebraskacoder-claude-plugins
nebraskacoder-claude-plugins/
├── .claude-plugin/
│ └── marketplace.json # marketplace catalog (lists every plugin)
├── plugins/ # one subdirectory per plugin
│ └── <plugin-name>/
│ ├── .claude-plugin/
│ │ └── plugin.json # the plugin's manifest
│ ├── commands/ # slash commands (*.md)
│ ├── agents/ # subagents (*.md)
│ ├── skills/ # skills (<name>/SKILL.md)
│ └── hooks/
│ └── hooks.json # hook definitions
└── README.md
marketplace.json, at the repo root under
.claude-plugin/.plugins/ and has its own
.claude-plugin/plugin.json.source paths in the catalog are relative to the repo root, e.g.
"./plugins/<plugin-name>".Each new plugin needs a plugins/<plugin-name>/ folder with a
.claude-plugin/plugin.json, plus an entry appended to the plugins array in
.claude-plugin/marketplace.json.
The fastest way is the built-in create-plugin skill (in
.claude/skills/): just say something like "create a new plugin" while
working in this repo and it will scaffold the folder, manifest, and any
components you pick, then register the plugin in the marketplace for you.
After changing an existing plugin, its version needs bumping in two places that
must stay in sync — the plugin's .claude-plugin/plugin.json and its entry in
.claude-plugin/marketplace.json — since Claude Code resolves plugin updates
from that per-plugin version.
The built-in update-plugin skill (in .claude/skills/) handles this: say
something like "bump the version", "cut a new release", or "I added a skill,
sync the marketplace" while working in this repo. It surveys what changed, asks
whether it's a patch, minor, or major bump, updates the version in both files,
syncs descriptions/keywords, wires up any newly added component, and validates
that everything lines up. (The top-level marketplace.json version is catalog
metadata and is left alone on a routine plugin bump.)
Released into the public domain under The Unlicense —
see LICENSE. Use, copy, modify, and distribute freely, no
attribution required.
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 claimnpx claudepluginhub nebraskacoder/nebraskacoder-claude-plugins --plugin project-setupBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Install NebraskaCoder's three-line Claude Code statusline — model/fast/effort/dir/git/PR, a context-usage bar with cost and duration, and Pro/Max rate-limit windows — via a bundled script.
Disciplined iterative web research — decompose a question, search in batches, verify load-bearing facts against primary sources, and synthesize a cited answer.
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.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
Connect to Atlassian products including Jira and Confluence. Search and create issues, access documentation, manage sprints, and integrate your development workflow with Atlassian's collaboration tools.
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.
20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.
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).