claude

lnpl

Authoring and verification for LNPL, the language of the linkly LLM-native platform (declare entities, services and workflows; the compiler lowers them to a semantic IR that runs on an interpreter or compiles through MLIR to a native binary). LNPL's verb vocabulary is closed and absent from model training data, so a plausible word compiles into a step that silently does nothing. The plugin routes Claude to the lexicon generated from the compiler's own tables, surfaces lnpl compile diagnostics on every save, offers an independent reviewer subagent, derives spec cases, and gates completion on evidence.

3,741 on GitHubby choiyounggiv0.8.0MITupdated 2 days agodevelopment
/

Plugin lnpl from marketplace buildwithclaude in davepoon/buildwithclaude. Commands read from the repo's manifest — yesterday.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (5)

  • lnpl-authoring

    Use when writing, editing, or reviewing `.lnpl` sources for the linkly platform — entity/service/workflow declarations, guard conditions, spec blocks, refinements. LNPL uses closed vocabularies that are not in your training data; a plausible-looking file compiles and then silently does nothing. Rout

  • lnpl-doctor

    Use when the lnpl CLI is missing, the .lnpl diagnostics hook is silent, `lnpl` commands fail, or the plugin and the installed CLI may have drifted apart in version. Diagnoses installation and version mismatch for the linkly platform.

  • lnpl-kb

    Use before making an architecture, naming, performance, security, testing, concurrency, database, or cloud decision in a `.lnpl` module — routes to linkly's knowledge base instead of guessing. The KB is built for agent lookup (RFC-0005) and is keyed by trigger phrases.

  • lnpl-spec

    Use when writing or reviewing a `spec` block in a `.lnpl` workflow for the linkly platform — derives test cases mechanically from the module's own declarations instead of guessing assertions. Covers given/when/expect and the declaration-to-expectation rules.

  • lnpl-verify

    Use before claiming a `.lnpl` change is done, complete, working, or ready — the completion gate for the linkly platform. Runs compile diagnostics, the spec manifest, and the mode A/B differential when the toolchain allows. Evidence before assertions.

Subagents (1)

  • lnpl-reviewer

    Use to review a `.lnpl` source that another session just wrote or changed — before calling it done. Reads the file, runs the compiler, and judges every diagnostic against what the author said they intended. The session that wrote a file cannot grade its own vocabulary: in LNPL a wrong word is not an

Hooks (2)

  • SessionStart

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/lnpl-session-start.sh

  • PostToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/lnpl-diagnostics.sh

View source on GitHub buildwithclaude.com

More from davepoon/buildwithclaude

All 277 plugins →

all-skills

claude

Complete collection of ~110 Claude Code skills across document processing, development, automation, CRM, DevOps, and more

200 skills

3,741

all-commands

claude

Complete collection of 174 slash commands across 22 categories

177 commands

3,741

all-agents

claude

Complete collection of 117 specialized AI agents across 11 categories

117 agents

3,741

gsd

claude

Get Shit Done -- a structured workflow plugin for Claude Code that adds planning, execution, and verification commands with MCP-backed project state

83 skills · 33 agents · 1 MCP server

3,741

forge

claude

Full-lifecycle SDLC orchestrator: a 12-stage pipeline (SRS, architecture, spec, plan, build, eval, deploy, monitor, release) driven by specialized agents, persistent cross-session memory, auto-reflection, gate enforcement, and semantic skill mining that proposes new skills from recurring workflows.

45 skills · 27 agents · hooks

3,741

suede-skills

claudecodex

74 skills for Claude Code and Codex. A build DAG researches your repo, fans out disjoint lanes, and refutes its own review before anything lands. A blunt A-F ship grade blocks the bad merge instead of complimenting it. The same folder designs the page, writes the copy, and ships native iOS and Android builds.

70 skills · 1 MCP server

3,741

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

cli-anything

claude

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

agent-browser

claude

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Open Code Review

codex

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain lnpl?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins277 plugins