By edjchapman
Automates developer workflows with specialized agents for debugging, CI/CD, database migrations, code reviews, and security audits, plus commands that aggregate daily standups and weekly reviews from Git, GitHub, Jira, and Notion.
Prepare end-of-week review notes summarizing the full week's work activity across all sources (Git, GitHub, Jira, Notion).
Create a new "Later" backlog item (Learn / Research / Do / Read) from a configurable template.
Prepare technical analysis for backlog refinement meetings.
Prepare a standup document summarizing recent work activity across Git, GitHub, Jira, and Notion.
Capture a quick status update and append it to today's daily log.
Use this agent when you encounter a bug, error, or unexpected behavior that needs investigation and resolution. This includes runtime errors, failed tests, incorrect outputs, performance issues, or any situation where code isn't behaving as expected. <example> Context: User reports a failing test. user: "The test test_create_user is failing with an assertion error" assistant: "I'll use the bug-resolver agent to investigate this failing test and determine the root cause." </example> <example> Context: User encounters an unexpected error in production. user: "Users are getting a 500 error when they try to upload files larger than 10MB" assistant: "Let me launch the bug-resolver agent to deep-dive into this file upload issue and trace the error." </example> <example> Context: User notices incorrect behavior in a feature. user: "The report is showing duplicate entries that shouldn't be there" assistant: "I'll use the bug-resolver agent to investigate why duplicate entries are appearing." </example>
Use this agent to investigate CI/CD pipeline failures, flaky tests, and environment-related build issues. This includes GitHub Actions, Jenkins, CircleCI, and other CI systems. <example> Context: User's CI pipeline is failing. user: "Our GitHub Actions build has been failing for the last 3 runs. Can you investigate?" assistant: "I'll use the ci-debugger agent to investigate the CI failures and identify the root cause." </example> <example> Context: User has a flaky test. user: "The test_payment_processing test passes locally but fails intermittently in CI" assistant: "Let me launch the ci-debugger agent to investigate the flaky test and environment differences." </example> <example> Context: User's build suddenly broke. user: "Our build started failing after merging the auth PR but all tests pass locally" assistant: "I'll use the ci-debugger agent to compare the CI environment with your local setup." </example>
Use this agent when you need help with database schema design, migration planning, query optimization, or data modeling. This includes schema reviews, index strategies, migration safety analysis, and data architecture decisions. <example> Context: User is designing a new feature that needs database changes. user: "I need to add multi-tenancy support to our database. How should I structure it?" assistant: "I'll use the database-architect agent to design a multi-tenancy schema that balances isolation, performance, and complexity." </example> <example> Context: User has a complex migration to plan. user: "We need to split this table into two. How do we do it safely without downtime?" assistant: "Let me use the database-architect agent to plan a zero-downtime migration strategy." </example> <example> Context: User wants to review their schema design. user: "Can you review our database schema for the new inventory system?" assistant: "I'll use the database-architect agent to review your schema for normalization, indexing, and scalability." </example>
Use this agent for dependency audits, outdated package management, license compatibility checks, and upgrade planning. Works with npm, pip, uv, go modules, and other package managers. <example> Context: User wants to audit their dependencies. user: "Can you check our dependencies for security vulnerabilities?" assistant: "I'll use the dependency-manager agent to audit your dependencies for vulnerabilities and outdated packages." </example> <example> Context: User needs to upgrade a major dependency. user: "We need to upgrade React from 17 to 18. What's involved?" assistant: "Let me launch the dependency-manager agent to analyze the upgrade path and identify breaking changes." </example> <example> Context: User wants to clean up dependencies. user: "We have a lot of unused packages. Can you help identify them?" assistant: "I'll use the dependency-manager agent to find unused and redundant dependencies." </example>
Use this agent when you need help with infrastructure, CI/CD pipelines, containerization, or deployment processes. This includes Docker/Kubernetes optimization, CI/CD pipeline review, infrastructure as code, monitoring setup, and deployment safety. <example> Context: User wants to improve their CI/CD pipeline. user: "Our CI pipeline takes 30 minutes. Can you help optimize it?" assistant: "I'll use the devops-engineer agent to analyze and optimize your CI/CD pipeline." </example> <example> Context: User is setting up Kubernetes deployment. user: "We're moving to Kubernetes. Can you review our deployment configs?" assistant: "Let me use the devops-engineer agent to review your Kubernetes configurations for best practices." </example> <example> Context: User needs help with monitoring. user: "We need better observability. What should we monitor and alert on?" assistant: "I'll use the devops-engineer agent to design a monitoring and alerting strategy for your system." </example>
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
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.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Reusable agents, commands, and permission templates for Claude Code.
Claude Code stores configuration in ~/.claude/ (global) and .claude/ (per-project). Managing this across multiple projects and machines becomes tedious:
This repo solves that by providing:
There are two ways to consume this repo: as a plugin (recommended; uses Claude Code's plugin loader) or as a symlinked global config (legacy path, still supported).
# From inside Claude Code:
/plugin marketplace add edjchapman/claude-code-config
/plugin install claude-code-config
Then add per-project permissions only:
cd ~/my-django-project
~/Development/claude-code-config/scripts/setup-project.sh django # for settings.local.json + .mcp.json
# 1. Clone (or fork if you want to customize)
git clone https://github.com/edjchapman/claude-code-config.git ~/claude-code-config
# 2. Set up global config
~/Development/claude-code-config/scripts/setup-global.sh
# 3. Set up a project (from your project directory)
cd ~/my-django-project
~/Development/claude-code-config/scripts/setup-project.sh django
# 4. Start using Claude Code - agents and commands are now available
claude
Both modes coexist — the hook command paths in settings.json use ${CLAUDE_PLUGIN_DIR:-<readlink fallback>}, so they resolve correctly whether loaded as a plugin (CLAUDE_PLUGIN_DIR set by the loader) or via symlink (readlink resolves the symlinked settings.json back to the repo).
Tip: Add an alias for easier use:
# Add to ~/.bashrc or ~/.zshrc
alias claude-setup='~/Development/claude-code-config/scripts/setup-project.sh'
# Then use it like:
claude-setup django react
Global setup (setup-global.sh) creates symlinks in ~/.claude/:
~/.claude/
├── agents -> ~/Development/claude-code-config/agents
├── commands -> ~/Development/claude-code-config/commands
├── skills -> ~/Development/claude-code-config/skills
├── rules -> ~/Development/claude-code-config/rules
└── settings.json -> ~/Development/claude-code-config/settings.json
Project setup (setup-project.sh) creates in your project:
your-project/
├── .mcp.json (MCP server config, if applicable)
└── .claude/
├── agents -> ~/Development/claude-code-config/agents
├── commands -> ~/Development/claude-code-config/commands
├── skills -> ~/Development/claude-code-config/skills
├── rules -> ~/Development/claude-code-config/rules
├── settings.json -> ~/Development/claude-code-config/settings.json
└── settings.local.json (generated from templates)
settings.json (symlinked): Plugin enablement, hooks configuration, and model selectionsettings.local.json (generated): Permissions - what bash commands and tools Claude can use in your projectEverything in this repo falls into two categories:
| Active (you invoke) | Passive (auto-activates) | |
|---|---|---|
| What | Specialist agents, Commands, CLI scripts | Skills, Rules, Hooks |
| How | @name, /name, or shell command | Triggered by file patterns or lifecycle events |
| Example | @bug-resolver, /commit, daily-report.sh | testing-patterns skill activates on test_*.py |
Active tools — you choose when to use them:
@bug-resolver, @test-engineer, etc.) provide deep expertise in a single domain/commit, /pr, /standup, etc.) run focused, single-purpose workflowsreview-changes.sh, daily-report.sh, etc.) run headless — no interactive session needednpx claudepluginhub edjchapman/claude-code-configHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Real-time statusline HUD for Claude Code - context health, tool activity, agent tracking, and todo progress
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation