By jukqaz
Lightweight control plane skills for current agent state, radar, and evidence.
Use when the user wants one pass that researches external agent tools, compares them, and recommends GroundLine upgrades for Codex, Claude Code, or Antigravity.
Use when the user asks about Codex, Claude Code, or Antigravity settings, official documentation alignment, guidance files, skills, custom agents, rules, hooks, provider boundaries, private config sync, or runtime doctor output.
Use when analyzing local Codex, Claude Code, or Antigravity history stores; when comparing current provider storage; when improving retention; when recovering prior context; or when deriving reusable skills from past agent work.
Use when local tests or CI appear complete but dev, review, staging, production, app store, worker, queue, scheduler, or browser-visible runtime state must be proven before saying deployment or release work is done.
Use when comparing agent tools, skills, plugins, MCP servers, hooks, workflow frameworks, or provider features against GroundLine scope and supported runtimes.
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.
GroundLine helps an AI coding agent slow down at the moments that usually go wrong: resuming someone else's work, touching risky systems, claiming work is complete too early, or letting a release grow without a stop point.
GroundLine is a lightweight control plane for Codex, Claude Code, and Antigravity. It keeps capability blueprints, detects runtime and ecosystem drift, prepares research and upgrade packets, and guides agents through current-state proof, side-effect boundaries, live evidence, and handoff.
GroundLine is not a synced config dump, a heavy bootstrap CLI, or an always-on MCP bundle.
GroundLine also does not reimplement provider-native features. Built-in goal modes, subagents, hook engines, plugin installers, MCP launchers, browser controls, and app context features stay owned by Codex, Claude Code, or Antigravity. GroundLine provides the provider-neutral task contracts, safety boundaries, and verification language around them.
If you only want to try GroundLine, do this:
git clone https://github.com/jukqaz/groundline.git
cd groundline
PYTHONDONTWRITEBYTECODE=1 python3 scripts/validate_pack.py --json
PYTHONDONTWRITEBYTECODE=1 python3 scripts/groundline_provider_smoke.py --json
validate_pack.py should report status=PASS. The provider smoke command is
read-only: it should report mutation_performed=false and no real provider
home writes, but it may return PARTIAL when an existing provider install is
stale relative to the checked-out package. Use --require-installed when the
goal is post-install release proof rather than package/path validation. Read
top-level next_actions before installing or refreshing Codex, Claude Code, or
Antigravity.
If you want to install from the public repository:
codex plugin marketplace add jukqaz/groundline --ref main
codex plugin add groundline@groundline
claude plugin marketplace add jukqaz/groundline
claude plugin install groundline@groundline
agy plugin install https://github.com/jukqaz/groundline
Use GroundLine when the next step needs evidence or a boundary:
| Situation | Ask the agent |
|---|---|
| A previous agent worked on this | "Recheck the current state before continuing." |
| A thread is too long | "Package this task so another agent can continue." |
| The task keeps expanding | "Hold the line and decide what ships now." |
| Tests passed but the runtime may still be wrong | "Close this with live evidence." |
| The action may change files, remotes, production, access, or secrets | "Classify side effects before doing anything." |
| You are near release | "Polish the release candidate and lock the release cut." |
| You are comparing agent tools or skills | "Evaluate this capability before adopting it." |
By default, GroundLine is skills-first:
English is the default and canonical language for GroundLine documentation. Korean companion docs are available for human-facing setup and workflow reading:
README.ko.mddocs/ko/index.mddocs/language-policy.mdLLM-readable references, output contracts, manifests, and skill instructions stay in English unless a release explicitly changes that policy.
docs/human-guide.mdREADME.ko.mddocs/install.md, docs/update.mddocs/provider-packaging.mddocs/provider-activation-matrix.mddocs/examples.mddocs/workflow-cookbook.mddocs/artifact-lifecycle.mddocs/skill-portfolio.mddocs/skill-graduation-plan.mddocs/maturity-assessment.mddocs/llm-guide.mdnpx claudepluginhub jukqaz/groundlineLightweight control plane skills for current agent state, radar, and evidence.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
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.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.