By mistakeknot
Plugin development toolkit — lifecycle management, structure validation, and troubleshooting for Claude Code plugins
Full plugin lifecycle — create, structure, test, and release Claude Code plugins. For skill/command authoring specifically, use /interskill:skill. For official plugin structure reference, use /plugin-dev:plugin-structure.
Use when a Claude Code plugin is not working — plugin not loading, skill not triggering, command not appearing, MCP server not starting, or hooks not firing. Provides systematic debug steps.
Use when verifying a plugin is correctly structured before testing or publishing — checks plugin.json schema, directory layout, hooks declaration, skill structure, and file permissions.
Plugin development toolkit for Claude Code.
interplug covers the full plugin lifecycle: scaffolding a new plugin, validating its structure, and troubleshooting when things don't work. Three focused skills instead of one monolithic guide.
The create skill walks through planning, directory creation, component wiring (skills, hooks, agents, commands, MCP servers), and release preparation. The validate skill checks everything a plugin needs to load correctly: plugin.json schema, path references, hook permissions, skill structure. The troubleshoot skill is a diagnostic guide for the three most common failure modes: plugin not loading, skill not triggering, hooks not firing.
First, add the interagency marketplace (one-time setup):
/plugin marketplace add mistakeknot/interagency-marketplace
Then install the plugin:
/plugin install interplug
Create a new plugin:
/interplug:create-plugin
Validate plugin structure:
/interplug:validate
Debug a broken plugin:
/interplug:troubleshoot
Or ask naturally:
"create a plugin for code formatting"
"why isn't my plugin loading?"
"check if my plugin.json is correct"
skills/
create/
SKILL.md Full lifecycle creation workflow
references/
plugin-structure.md Plugin manifest and directory conventions
common-patterns.md Hooks, MCP servers, skill patterns
polyglot-hooks.md Writing hooks in Python, Node, Go, etc.
troubleshooting.md Common failure modes and fixes
validate/
SKILL.md Structural validation checks
troubleshoot/
SKILL.md Diagnostic guide for common failures
interplug was extracted from interdev's developing-claude-code-plugins skill. The original monolithic skill covered plugins, skills, and Claude Code reference — now each concern has its own plugin.
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.
npx claudepluginhub mistakeknot/interagency-marketplace --plugin interplug[DEPRECATED — use intervoice] Analyze your writing style and adapt Claude's output to sound like you. Replaced by intervoice, which reads one global multi-register profile instead of per-project glob-routed files.
Recursive AGENTS.md generator with integrated Oracle critique, CLAUDE.md harmonization, incremental updates, diff previews, and smart monorepo scoping. Cross-AI compatible.
Token-efficient code reconnaissance for LLMs. Autonomous skills save 48-85% tokens via diff-context, semantic search, structural patterns, and symbol analysis. Includes MCP server for direct tool integration.
Self-improving agent rig: codifies product and engineering discipline into composable workflows from brainstorm to ship. Compounds knowledge, generates domain agents, monitors its own docs, and surfaces conservative update drift. Orchestrates Claude, Codex, and Oracle through 6 agents, 52 commands, 19 skills, 0 MCP servers. Factory substrate: CXDB turn DAG, scenario bank with satisfaction scoring, evidence pipeline, agent capability policies. Companions: interspect, interphase, interline, interflux, interpath, interwatch, interslack, interform, intercraft, interdev, interpeer, intertest.
Token efficiency benchmarking, session analytics, and API-equivalent cost analysis for agent workflows
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.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.