Skip to content

Releases: sjnims/plugin-dev

v0.3.2

25 Jan 01:49
41fd5b9

Choose a tag to compare

Summary

Documentation improvements and bug fix release.

What's Changed

Fixed

  • Restore MCP tool naming patterns - Fixed mcp__plugin_*__* patterns in mcp-integration docs that prettier corrupted to mcp**plugin_*__*; added .prettierignore to prevent recurrence

Documentation

  • Expand LSP integration skill - Aligned with official Claude Code docs for comprehensive LSP server guidance
  • Optimize agent-development skill - Trimmed SKILL.md to target word count for faster loading
  • Align tools/allowed-tools format - Updated documentation to match official Claude Code docs terminology
  • Update CI/CD workflow documentation - Fixed workflow list in docs/ci-cd.md (added yaml-lint.yml, removed non-existent weekly-maintenance.yml)

Full Changelog: v0.3.1...v0.3.2

v0.3.1

24 Jan 23:54
7caad42

Choose a tag to compare

Summary

Hotfix release addressing issues discovered immediately after v0.3.0.

What's Changed

Fixed

  • Replace ! with [BANG] in skill-development dynamic context examples - fixes shell execution errors during skill loading

Documentation

  • Update skill counts from 8 to 9 in CONTRIBUTING.md and README.md
  • Add LSP Integration to README skills table
  • Add 0.3.x to SECURITY.md supported versions

Full Changelog: v0.3.0...v0.3.1

v0.3.0

24 Jan 23:27
a6f1b89

Choose a tag to compare

Summary

Documentation sync with official Claude Code, workflow improvements, and security hardening.

What's Changed

Changed

  • Sync documentation with official Claude Code docs - Updated all skill documentation to align with latest Claude Code features and terminology (#192)
  • Replace deprecated TodoWrite with Task tools - Updated documentation to use current TaskCreate, TaskUpdate, TaskGet, TaskList tools (#190)
  • Update documentation for Skill tool consolidation - Reflect Claude Code's unified Skill tool approach (#186)
  • Optimize CLAUDE.md with progressive disclosure - Restructured for faster onboarding

Fixed

  • Use dynamic GitHub release badge - Badge now updates automatically from GitHub releases

Security

  • Remove untrusted checkout in ci-failure-analysis - Hardened workflow against potential code injection

CI/CD

  • Improve workflow consistency and add YAML linting
  • Improve links and markdownlint workflows
  • Eliminate workflow dependencies and optimize CI
  • Various workflow and template improvements

Dependencies

  • Bump anthropics/claude-code-action to v1.0.34
  • Bump actions/checkout to v6.0.2
  • Bump actions/cache to v5.0.2
  • Bump yamllint to 1.38.0

Full Changelog: v0.2.1...v0.3.0

v0.2.1

13 Dec 19:16
710a213

Choose a tag to compare

Summary

Security hardening, bug fixes, and documentation improvements.

What's Changed

Security

  • Harden validation scripts against bypass attacks (#164)
  • Prevent command injection in test-hook.sh (#148)
  • Use jq for safe JSON output in example hooks (#149)
  • Document security scope and trust model (#165)

Fixed

  • Remove deprecated mode parameter from claude-pr-review workflow (#171)
  • Resolve shellcheck SC1087 errors in validate-hook-schema.sh (#168)
  • Replace unofficial cc alias with official claude CLI command
  • Issue/PR template improvements and labels configuration fixes
  • Workflow reliability and documentation improvements

Changed

  • Use ERE instead of BRE in grep patterns for clarity (#159)

Documentation

  • Comprehensive documentation improvements across README, CLAUDE.md, and skills
  • Added prerequisites section for utility script dependencies (#157)
  • Added shellcheck guidance to CONTRIBUTING.md (#160)
  • Documented secure mktemp pattern and [BANG] workaround

Dependencies

  • Bump anthropics/claude-code-action (#170)
  • Bump EndBug/label-sync (#169)
  • Update GitHub Actions to latest versions

Full Changelog: v0.2.0...v0.2.1

v0.2.0

13 Dec 01:57
1af7555

Choose a tag to compare

Summary

New entry point command for guided plugin/marketplace development workflows.

What's Changed

Added

  • /plugin-dev:start command - New primary entry point that guides users to choose between creating a plugin or marketplace (#145)
    • Uses disable-model-invocation: true to route cleanly to specialized workflows
    • Recommends plugin creation for most users

Fixed

  • Enable router invocation of workflow commands - workflow commands can now be invoked by other commands (#145)
  • Replace ! with [BANG] placeholder in skill documentation to prevent shell interpretation issues (#142)

Documentation

  • Fix component counts and update documentation accuracy across README, CONTRIBUTING, CLAUDE.md, and marketplace.json

Full Changelog: v0.1.0...v0.2.0

v0.1.0

11 Dec 23:30
2e0779e

Choose a tag to compare

Summary

Initial release of the Plugin Development Toolkit - a comprehensive toolkit for developing Claude Code plugins.

What's Included

Core Plugin Features

  • 8 specialized skills with progressive disclosure architecture:

    • hook-development - Event-driven automation with prompt-based hooks
    • mcp-integration - Model Context Protocol server configuration
    • plugin-structure - Directory layout and manifest configuration
    • plugin-settings - Configuration via .claude/plugin-name.local.md files
    • command-development - Slash commands with frontmatter
    • agent-development - Autonomous agents with AI-assisted generation
    • skill-development - Creating skills with progressive disclosure
    • marketplace-structure - Plugin marketplace creation and distribution
  • 3 validation agents:

    • plugin-validator - Validates entire plugin structure and marketplace.json
    • skill-reviewer - Reviews skill quality and triggering reliability
    • agent-creator - Generates new agents from natural language descriptions
  • 2 guided workflow commands:

    • /plugin-dev:create-plugin - 8-phase guided workflow for plugin creation
    • /plugin-dev:create-marketplace - 8-phase guided workflow for marketplace creation

Infrastructure

  • 14 CI/CD workflows for validation, linting, and automation
  • Utility scripts for agent, command, hook, and settings validation
  • Comprehensive documentation (README, CLAUDE.md, CONTRIBUTING.md)

Attribution

Based on original plugin by Daisy Hollman at Anthropic, expanded with enhanced skills, additional utilities, and CI/CD infrastructure.

Full Changelog: https://github.com/sjnims/plugin-dev/commits/v0.1.0