Claude Code Plugins Marketplace

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.

Installation

Add this marketplace to your Claude Code installation:

/plugin marketplace add L3Digital-Net/Claude-Code-Plugins

Or using the full URL:

/plugin marketplace add https://github.com/L3Digital-Net/Claude-Code-Plugins.git

Then install individual plugins:

/plugin install agent-orchestrator@l3digitalnet-plugins

Staying Up to Date

Auto-update keeps plugins current automatically. To verify it's enabled:

1. Run /plugin in Claude Code
2. Go to the Marketplaces tab
3. Select l3digitalnet-plugins
4. 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

Available Plugins

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
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
KeePass Cred Mgr	MCP + Commands + Skills	varies	KeePass vault access via 10 MCP tools, YubiKey auth, credential rotation, and audit logging
Linux SysAdmin	Skills + Commands	94 skills	Per-service knowledge for daemons, CLI tools, and filesystems; guided /sysadmin stack interview
Plugin Review	Commands + Agents + Hooks	/review, /review-efficiency, /tighten	Multi-pass assertion-driven audit of plugin principles, UX, docs, and context efficiency
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 Suite	MCP + Commands + Skills + Agents	/qt-suite:scaffold, /qt-suite:coverage, /qt-suite:visual	Complete Qt development and testing toolkit: proactive agents, 16 skills, scaffolding, and headless GUI testing

Principles

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.

---

Agent Orchestrator

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-plugins

Learn more: plugins/agent-orchestrator/README.md

---

Design Assistant

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-plugins

Learn more: plugins/design-assistant/README.md

---

GitHub Repo Manager

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-plugins

Learn more: plugins/github-repo-manager/README.md

---

Home Assistant Dev

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-plugins

Learn more: plugins/home-assistant-dev/README.md

---

KeePass Cred Mgr

KeePass credential manager for Claude Code: 10 MCP tools for vault read/write, YubiKey HMAC-SHA1 authentication, credential rotation workflows, and structured audit logging.

Features:

• unlock_vault opens a persistent keepassxc-cli REPL; one YubiKey touch covers all subsequent tool calls
• 9 additional tools: list groups/entries, search, get entry/attachment, create, deactivate, add attachment, bulk import
• Background YubiKey poller auto-locks vault on removal with configurable grace period
• Per-credential-type skills for cPanel, FTP/SFTP, SSH, Brave Search API, and Anthropic API
• /keepass-rotate: guided create-then-deactivate rotation with safety checks
• Structured JSONL audit log for all secret-returning operations

Install:

/plugin install keepass-cred-mgr@l3digitalnet-plugins

Learn more: plugins/keepass-cred-mgr/README.md

---

Linux SysAdmin

Linux system administration knowledge base: 94 per-service skills covering daemons, CLI tools, and filesystems. Skills load automatically when you mention a service by name; no commands required for most usage.

Features:

• Per-service skills for 94 services across web/proxy, DNS, databases, security/VPN, containers, monitoring, filesystems, storage, mail, self-hosted apps, IoT, and 30+ CLI tools
• Annotated configs for daemons (nginx, sshd, samba, postfix, mosquitto, and more) with every directive documented
• Task-organized cheatsheets for CLI tools (nmap, tcpdump, jq, rsync, borg, tmux, and more)
• /sysadmin command: guided interview to design a complete server stack with rationale and setup order
• No build step, no MCP server, no dependencies

Install:

/plugin install linux-sysadmin@l3digitalnet-plugins

Learn more: plugins/linux-sysadmin/README.md

---

Plugin Test Harness

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-plugins

Learn more: plugins/plugin-test-harness/README.md

---

Release Pipeline

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-plugins

Learn more: plugins/release-pipeline/README.md

---

Autonomous Refactor

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-plugins

Learn more: plugins/autonomous-refactor/README.md

---

Docs Manager

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
• /docs command for manual queue management and auditing

Install:

/plugin install docs-manager@l3digitalnet-plugins

Learn more: plugins/docs-manager/README.md

---

Plugin Review

Multi-pass assertion-driven plugin audit: four parallel analyst subagents cover principles alignment, terminal UX quality, documentation freshness, and context efficiency, then the orchestrator auto-implements all fixes and re-audits to convergence.

Features:

• Four parallel read-only analyst tracks: principles (A), UX (B), docs (C), efficiency (D)
• Assertion-based confidence scoring: loop continues until 100% or budget exhausted
• /review-efficiency: standalone 5-stage context efficiency audit against 12 structural principles
• /tighten: prose-level rewriting pass to eliminate token waste without changing meaning
• All fixes auto-implemented by the orchestrator, no manual copy/paste
• Findings severity-sorted: critical → high → medium → low

Install:

/plugin install plugin-review@l3digitalnet-plugins

Learn more: plugins/plugin-review/README.md

---

Repo Hygiene

Autonomous maintenance sweep: five parallel mechanical checks plus a semantic README pass, with safe corrections applied automatically and destructive changes requiring explicit approval.

Features:

• .gitignore pattern validation against actual repo contents
• marketplace.json path and format checks
• Orphaned plugin cache detection
• Stale enabledPlugins entry cleanup
• Semantic README freshness scan with inline AI reasoning
• --dry-run flag shows full plan without touching anything

Install:

/plugin install repo-hygiene@l3digitalnet-plugins

Learn more: plugins/repo-hygiene/README.md

---

Qt Suite

Complete Qt development and testing toolkit: proactive specialist agents, 16 domain skills, scaffolding commands, and headless GUI testing via the bundled Qt Pilot MCP server. Covers PySide6, PyQt6, and C++/Qt.

Features:

• 4 proactive agents: development specialist, debugger, code reviewer, and UX advisor
• 16 context-aware skills covering signals/slots, layouts, Model/View, threading, QML, styling, and more
• /qt-suite:scaffold: generates a complete PySide6 project with pyproject.toml, src layout, and test config
• /qt-suite:generate: scans codebase and generates unit tests for untested files
• /qt-suite:coverage: gcov/lcov (C++) or coverage.py (Python) report with gap-targeted test generation
• /qt-suite:visual: launches app headlessly via Xvfb, drives UI via the bundled Qt Pilot MCP server

Install:

/plugin install qt-suite@l3digitalnet-plugins

Learn more: plugins/qt-suite/README.md

---

Plugin Development

This repository also serves as a development workspace for creating new plugins. See CLAUDE.md for architectural guidance and docs/ for the full reference.

Quick Start

1. Create a new plugin:

   mkdir -p plugins/my-plugin/.claude-plugin
   cd plugins/my-plugin

2. Add manifest:

   {
     "name": "my-plugin",
     "version": "0.1.0",
     "description": "Plugin description"
   }

3. Test locally:

   claude --plugin-dir ./plugins/my-plugin

4. Add to marketplace catalog (.claude-plugin/marketplace.json)

Documentation

• 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

Repository Structure

Claude-Code-Plugins/
├── .claude-plugin/
│   └── marketplace.json        # Marketplace catalog
├── plugins/                     # All plugin implementations
│   ├── agent-orchestrator/      # Agent team orchestration
│   ├── autonomous-refactor/     # Test-driven autonomous refactoring
│   ├── 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
│   ├── keepass-cred-mgr/        # KeePass credential manager (10 MCP tools, YubiKey auth)
│   ├── linux-sysadmin/          # Linux sysadmin skills (94 per-service guides)
│   ├── plugin-review/           # Multi-pass plugin quality audit
│   ├── plugin-test-harness/     # Iterative plugin testing framework
│   ├── qt-suite/                # Qt development and testing toolkit (agents, skills, MCP)
│   ├── 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

Contributing

To add a plugin to this marketplace:

1. Work on the testing branch (all development happens here)
2. Create plugin in plugins/ directory
3. Add entry to .claude-plugin/marketplace.json
4. Validate with ./scripts/validate-marketplace.sh
5. Commit and push to testing branch
6. 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 testing

See BRANCH_PROTECTION.md for detailed workflow documentation.

License

MIT - See LICENSE file for details