A Claude Code plugin marketplace. Plugins cover the full development lifecycle: agent orchestration, release automation, design review, Home Assistant integration dev, Linux system administration, GitHub repo health, and plugin testing.
Add this marketplace to your Claude Code installation:
/plugin marketplace add L3DigitalNet/Claude-Code-PluginsOr using the full URL:
/plugin marketplace add https://github.com/L3DigitalNet/Claude-Code-Plugins.gitThen install individual plugins:
/plugin install agent-orchestrator@l3digitalnet-pluginsAuto-update keeps plugins current automatically. To verify it's enabled:
- Run
/pluginin Claude Code - Go to the Marketplaces tab
- Select l3digitalnet-plugins
- Look for Disable auto-update (meaning it's already on)
When auto-update is enabled, Claude Code refreshes the marketplace catalog and updates installed plugins at the start of each session.
Manual update if you prefer to control when updates happen:
# Refresh the marketplace catalog
/plugin marketplace update l3digitalnet-plugins
# Then update individual plugins via /plugin → Installed tab → Update now| Plugin | Type | Command | Description |
|---|---|---|---|
| Agent Orchestrator | Commands + Hooks | /orchestrate |
Delegates complex tasks to agent teams with context management |
| Autonomous Refactor | Commands + Agents | /refactor |
Test-driven autonomous refactoring against project design principles |
| Context Efficiency Toolkit | Commands + Skills | /review-context-efficiency, /tighten-markdown |
Audits and reduces plugin context footprint |
| Design Assistant | Commands + Skills | /design-draft, /design-review |
Guided design document authoring and principle-enforced review |
| Docs Manager | Commands + Agents + Hooks | /docs |
Documentation lifecycle management with drift detection |
| GitHub Repo Manager | Commands + Skills | /repo-manager |
Conversational GitHub repo health assessment and maintenance |
| Home Assistant Dev | Commands + Skills + MCP | varies | Full HA integration development toolkit with 27 skills |
| Linux SysAdmin MCP | MCP | ~100 tools | Linux system administration across 15 modules |
| Plugin Review | Commands + Agents + Hooks | /review |
Multi-pass assertion-driven audit of plugin principles, UX, and docs |
| Plugin Test Harness | MCP | 18 tools | Iterative test/fix/reload loop for plugin development |
| Release Pipeline | Commands + Skills | /release |
Semver releases with pre-flight checks and changelog generation |
| Repo Hygiene | Commands | /hygiene |
Autonomous maintenance sweep for .gitignore, manifests, and READMEs |
| Qt Test Suite | MCP + Commands | /qt:generate, /qt:run, /qt:coverage, /qt:visual |
AI test generation, coverage-gap analysis, and headless GUI testing for PySide6 and C++/Qt |
| Qt Dev Suite | Commands + Skills | /qt-dev-suite:scaffold, /qt-dev-suite:new-component |
Qt GUI development companion with proactive agents, 13 domain skills, and scaffolding commands |
These principles apply across all plugins in this collection. Individual plugins may define additional principles scoped to their domain.
[P1] Act on Intent: Invoking a command is consent to its implied scope. When intent is ambiguous, clarify scope before executing, not after. When intent is clear, execute without narration or confirmation of the obvious. A confirmation gate is warranted only when an operation is both truly irreversible and its scope materially exceeds what the invocation implies, not for operations that are merely large or look dangerous. If scope materially changes mid-execution, stop and re-confirm. Routine friction is a tax, not a safeguard.
[P2] Scope Fidelity: Execute the full scope of what was asked, completely, without routine sub-task confirmation gates. When a sub-task's scope is genuinely ambiguous, clarify before proceeding rather than assuming. Do not act beyond the declared scope; surface only material out-of-scope findings as notes; routine adjacent observations are not worth raising. Scope undershoot triggers additional iteration; scope overshoot violates the consent established at invocation.
[P3] Succeed Quietly, Fail Transparently: Lead with findings, not intent or preamble. Output results, not narration. Emit a compact factual summary at task completion, not after every step. On transient or infrastructure errors, retry silently. On critical failures, stop immediately and surface the complete failure (raw output included) with a recovery plan; do not attempt autonomous workarounds.
[P4] Use the Full Toolkit: When interaction is required, prefer structured choices over open-ended prompts; bound the user's decision space before presenting it. Use Claude Code's interaction primitives: bounded choices (AskUserQuestion), markdown previews for side-by-side comparisons, multi-select for non-exclusive options.
[P5] Convergence is the Contract: Iterative work defines completion as a measurable criterion (set by the plugin, the user, or collaboratively) and drives toward it without check-ins. Proceed quietly when converging normally. Surface immediately if progress stalls or regresses unexpectedly. If the cycle begins oscillating (making and undoing the same changes repeatedly), flag the pattern and stop rather than continuing. Stop only when the criterion is met, oscillation is detected, or the user intervenes.
[P6] Composable, Focused Units: Every plugin component (command, skill, hook) does one thing and is independently useful. Complex workflows emerge from combining atomic units at runtime; orchestration is assembled from the outside, not baked in.
General-purpose agent team orchestration with automatic context management, file isolation via git worktrees, and mechanical enforcement hooks.
Features:
- Triage gate for simple vs complex tasks
- Parallel execution via agent teams (or sequential fallback)
- Git worktree isolation for concurrent work
- Context degradation prevention via hooks
- Quality gate with integration checking
Install:
/plugin install agent-orchestrator@l3digitalnet-pluginsLearn more: plugins/agent-orchestrator/README.md
Full design document lifecycle in two commands: guided authoring from blank page through principle-enforced iterative review.
Features:
/design-draft: 5-phase interview: context deep dive, principles discovery, scope confirmation, gap-filling, and draft generation- Principle stress-testing and tension resolution before any architecture is committed
/design-review: multi-pass principle enforcement, gap analysis, and optional auto-fix- Principle Conflict Screening: all proposed fixes checked against established principles before presentation
- Automatic warm handoff from draft to review (principles registry transferred)
- Runs until the document converges to zero findings across all review tracks
Install:
/plugin install design-assistant@l3digitalnet-pluginsLearn more: plugins/design-assistant/README.md
Conversational GitHub repository maintenance: assess and fix repo health interactively, with owner approval at every step.
Features:
- Wiki sync: keeps wiki pages in sync with in-repo docs and code
- Community health: audits and updates CONTRIBUTING, SECURITY, CODE_OF_CONDUCT, issue/PR templates
- PR triage: conflict detection, staleness checks, review summaries
- Issue triage: labels, assignees, staleness, linked PRs
- Release health: unreleased commits, changelog drift, draft releases
- Security posture: Dependabot alerts, code scanning, secret scanning
- Dependency audit: outdated packages, license concerns
- Notifications & discussions: triage and summarise
- Cross-repo mode: scan all accessible repos for a specific concern and fix in batch
- Structured maintenance report generated at session end
Install:
/plugin install github-repo-manager@l3digitalnet-pluginsLearn more: plugins/github-repo-manager/README.md
Home Assistant integration development toolkit: 27 AI skills, an MCP server for live HA connections, automated validation, example integrations, and project templates.
Features:
- 27 context-aware skills covering architecture, config flows, coordinators, entities, testing, and more
- 3 specialized agents (development, review, debugging)
- MCP server with 12 tools for live HA connection and documentation search
- 5 validation scripts with PostToolUse hook enforcement
- 3 example integrations (Bronze/Silver/Gold tier)
- 9 project templates for CI/CD, testing, and documentation
- Full Integration Quality Scale coverage (all 52 rules)
Install:
/plugin install home-assistant-dev@l3digitalnet-pluginsLearn more: plugins/home-assistant-dev/README.md
Linux system administration MCP server: ~100 tools across 15 modules. Covers packages, services, users, firewall, networking, security, storage, containers, and more.
Features:
- ~100 tools across 15 modules (see the full tool table)
- Distro-agnostic command abstraction (Debian/RHEL auto-detection)
- 5-tier risk classification with confirmation gates
- YAML knowledge profiles for 8 services (sshd, nginx, docker, ufw, fail2ban, pihole, unbound, crowdsec)
- SSH remote execution support
- Git-backed documentation generation
Install:
/plugin install linux-sysadmin-mcp@l3digitalnet-pluginsLearn more: plugins/linux-sysadmin-mcp/README.md
Iterative plugin testing framework: generates tests, records pass/fail results, applies source fixes, reloads the target plugin, and retests until convergence.
Features:
- Auto-generates tests from plugin source and schema introspection
- Test/fix/reload loop with convergence tracking (improving, plateau, oscillating, diverging)
- Dedicated git branch per session for a complete audit trail of fixes
- Sessions persist to disk and can be resumed after interruption
- Native MCP client for MCP-mode plugins; source analysis for hook/command plugins
- 18 tools across session management, test management, execution, and fix management
Install:
/plugin install plugin-test-harness@l3digitalnet-pluginsLearn more: plugins/plugin-test-harness/README.md
Autonomous release pipeline: quick merge or full semver release with parallel pre-flight checks, changelog generation, and GitHub release creation.
Features:
- Two modes: quick merge (testing → main) or full versioned release
- Parallel pre-flight agents (test runner, docs auditor, git validator)
- Automatic changelog generation from conventional commits
- Version bumping across Python, Node.js, Rust, and plugin manifests
- GitHub release creation with release notes
- Human-in-the-loop approval gates at critical stages
- Fail-fast with rollback guidance on errors
Install:
/plugin install release-pipeline@l3digitalnet-pluginsLearn more: plugins/release-pipeline/README.md
Test-driven autonomous refactoring: reads your project's design principles, generates a behavioural test baseline, applies each refactoring opportunity in an isolated git worktree, and commits only changes that keep tests green.
Features:
- Derives refactoring opportunities from principles declared in
README.md - Generates a green test baseline before touching any source file
- Applies each change in an isolated git worktree, reverting automatically on red tests
- Detects oscillation (repeated make/undo of the same change) and stops
- Produces a before/after report with LOC, cyclomatic complexity, and alignment score
Install:
/plugin install autonomous-refactor@l3digitalnet-pluginsLearn more: plugins/autonomous-refactor/README.md
Audit and reduce plugin context footprint: two structured workflows for eliminating token waste: a twelve-principle architectural audit and a prose-level rewriting pass.
Features:
/review-context-efficiency: audits against 12 structural efficiency principles (deferred loading, hook vs instruction, template extraction, and more)/tighten-markdown: rewrites instruction files to remove motivational text, restatements, hedging, and syntax narration without changing meaning- Approval-gated: findings presented before any file is modified
- Designed to run in sequence: architecture first, prose second
Install:
/plugin install context-efficiency-toolkit@l3digitalnet-pluginsLearn more: plugins/context-efficiency-toolkit/README.md
Documentation lifecycle management: monitors file changes via hooks, accumulates documentation tasks into a persistent queue without interrupting active work, and surfaces the queue for batch review at session end.
Features:
- Hook-driven change detection: queues documentation tasks as files are written
- Persistent queue across sessions with no item loss between restarts
- Central library index with per-document freshness tracking
- Third-party doc verification against upstream authoritative sources
- Batch review at session end rather than interrupting active work
/docscommand for manual queue management and auditing
Install:
/plugin install docs-manager@l3digitalnet-pluginsLearn more: plugins/docs-manager/README.md
Multi-pass assertion-driven plugin audit: three parallel analyst subagents cover principles alignment, terminal UX quality, and documentation freshness, then the orchestrator auto-implements all fixes and re-audits to convergence.
Features:
- Three parallel read-only analyst tracks: principles (A), UX (B), docs (C)
- Assertion-based confidence scoring: loop continues until 100% or budget exhausted
--autonomousflag adds regression guard (Track D) and build/test validation- All fixes auto-implemented by the orchestrator, no manual copy/paste
- Findings severity-sorted: critical → high → medium → low
Install:
/plugin install plugin-review@l3digitalnet-pluginsLearn more: plugins/plugin-review/README.md
Autonomous maintenance sweep: five parallel mechanical checks plus a semantic README pass, with safe corrections applied automatically and destructive changes requiring explicit approval.
Features:
.gitignorepattern validation against actual repo contentsmarketplace.jsonpath and format checks- Orphaned plugin cache detection
- Stale
enabledPluginsentry cleanup - Semantic README freshness scan with inline AI reasoning
--dry-runflag shows full plan without touching anything
Install:
/plugin install repo-hygiene@l3digitalnet-pluginsLearn more: plugins/repo-hygiene/README.md
AI-powered Qt testing pipeline: test generation, coverage-gap analysis, and headless GUI testing for PySide6 and C++/Qt projects.
Features:
/qt:generate: scans codebase and generates unit tests for untested files/qt:run: auto-detects Python (pytest) or C++ (CTest) and runs the full suite/qt:coverage: gcov/lcov (C++) or coverage.py (Python) → HTML report → gap-targeted test generation loop/qt:visual: launches app headlessly via Xvfb, drives UI interactions with the bundled Qt Pilot MCP server- Auto-installed virtual environment for Qt Pilot dependencies on first run
Install:
/plugin install qt-test-suite@l3digitalnet-pluginsLearn more: plugins/qt-test-suite/README.md
Qt GUI application development companion: proactive specialist agents, 13 domain skills, and scaffolding commands for PySide6, PyQt6, and C++/Qt projects.
Features:
- 4 proactive agents: development specialist, debugger, code reviewer, and UX advisor) activate automatically on context
- 13 context-aware skills covering signals/slots, layouts, Model/View, threading, QML, styling, and more
/qt-dev-suite:scaffold: generates a complete PySide6 project with pyproject.toml, src layout, and test config/qt-dev-suite:new-component: generates widget, dialog, or window boilerplate with correctsetObjectName()calls- Designed to pair with
qt-test-suite; scaffolded components are immediately testable by the GUI tester
Install:
/plugin install qt-dev-suite@l3digitalnet-pluginsLearn more: plugins/qt-dev-suite/README.md
These plugins are in development and not yet available in the marketplace.
| Plugin | Description |
|---|---|
performance-profiler |
Latency measurement, flamegraph generation, and regression tracking for MCP servers |
This repository also serves as a development workspace for creating new plugins. See CLAUDE.md for architectural guidance and docs/ for the full reference.
-
Create a new plugin:
mkdir -p plugins/my-plugin/.claude-plugin cd plugins/my-plugin -
Add manifest:
{ "name": "my-plugin", "version": "0.1.0", "description": "Plugin description" } -
Test locally:
claude --plugin-dir ./plugins/my-plugin
-
Add to marketplace catalog (
.claude-plugin/marketplace.json)
- docs/plugins.md - Plugin development guide
- docs/plugin-marketplaces.md - Marketplace creation
- docs/plugins-reference.md - Technical reference
- docs/skills.md - Creating AI-invoked skills
- docs/sub-agents.md - Custom agent definitions
- docs/hooks.md - Lifecycle event handlers
- docs/mcp.md - MCP server integration
Claude-Code-Plugins/
├── .claude-plugin/
│ └── marketplace.json # Marketplace catalog
├── plugins/ # All plugin implementations
│ ├── agent-orchestrator/ # Agent team orchestration
│ ├── autonomous-refactor/ # Test-driven autonomous refactoring
│ ├── context-efficiency-toolkit/ # Plugin context footprint audit and reduction
│ ├── design-assistant/ # Design document lifecycle
│ ├── docs-manager/ # Documentation lifecycle management
│ ├── github-repo-manager/ # Conversational GitHub repo maintenance
│ ├── home-assistant-dev/ # Home Assistant integration dev toolkit
│ ├── linux-sysadmin-mcp/ # Linux sysadmin MCP server (~100 tools)
│ ├── performance-profiler/ # MCP performance profiling (in development)
│ ├── plugin-review/ # Multi-pass plugin quality audit
│ ├── plugin-test-harness/ # Iterative plugin testing framework
│ ├── release-pipeline/ # Autonomous release pipeline
│ └── repo-hygiene/ # Autonomous repo maintenance sweep
├── scripts/
│ └── validate-marketplace.sh # Marketplace validation
├── docs/ # Comprehensive documentation
├── CLAUDE.md # Development guidance for AI agents
├── BRANCH_PROTECTION.md # Branch protection and workflow guide
└── README.md # This file
To add a plugin to this marketplace:
- Work on the
testingbranch (all development happens here) - Create plugin in
plugins/directory - Add entry to
.claude-plugin/marketplace.json - Validate with
./scripts/validate-marketplace.sh - Commit and push to
testingbranch - When ready to deploy, merge
testing→main
Branch workflow:
main- Protected production branch (GitHub blocks direct pushes)testing- Development branch (direct commits allowed)
Deployment:
git checkout testing
./scripts/validate-marketplace.sh
git checkout main
git merge testing --no-ff -m "Deploy: <description>"
git push origin main
git checkout testingSee BRANCH_PROTECTION.md for detailed workflow documentation.
MIT - See LICENSE file for details