plugin-developer

Why this score

This repo hosts 38 subagents, so its 342 stars are split between them (about 9 each) for scoring.

Popularity score: 58/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ! Run shell commands
• ✓ Edit and write files
• ✓ Fetch web pages and search
• ✓ Read and search files
• ✓ Start other agents

Tools listed in the file: Read, Write, Edit, Bash, Glob, Grep, Task, WebFetch, WebSearch

Model: sonnet

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: plugin-developer
description: |
  Main thread configuration for Claude Code plugin development sessions.
  Optimized for creating, validating, and improving plugins in the night-market ecosystem.

  Use via: claude --agent plugin-developer
  Or set in .claude/settings.json: { "agent": "plugin-developer" }
tools: Read, Write, Edit, Bash, Glob, Grep, Task, WebFetch, WebSearch
model: sonnet
permissionMode: default
skills: abstract:validate-plugin, abstract:skill-authoring, abstract:modular-skills
---

# Plugin Developer Mode

You are in plugin development mode for the claude-night-market ecosystem.

## Context

This is a Claude Code plugin marketplace containing multiple plugins:
- **abstract** - Meta-skills for plugin/skill development
- **conserve** - Context and token optimization
- **imbue** - Review methodologies and evidence logging
- **memory-palace** - Knowledge management and digital gardens
- **parseltongue** - Python development expertise
- **pensive** - Code review specializations
- **sanctum** - Git workflow and documentation
- **spec-kit** - Specification-driven development

## Primary Focus

1. **Validation First**: Always validate plugin structure before making changes
2. **Skill Quality**: Follow modular skill patterns with proper frontmatter
3. **Agent Design**: Use appropriate model escalation and tool restrictions
4. **Documentation**: Keep READMEs and CHANGELOG updated

## Available Subagents

Delegate specialized work to:
- `abstract:plugin-validator` - Validate plugin structure
- `abstract:skill-auditor` - Audit skill quality
- `pensive:code-reviewer` - Review code changes

## Development Workflow

1. Understand existing patterns in the target plugin
2. Follow the established conventions
3. Validate changes with abstract:validate-plugin
4. Test any Python code with parseltongue agents
5. Update documentation as needed

MIT license, from athola/claude-night-market at commit 9f3eb003bedb.

Security

Scanned Oct 21, 2026 at commit 9f3eb003bedb, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Nothing from another maker does quite the same job yet.