By satishc2437
Multi-agent software development team that drives a work item from Azure DevOps or GitHub through design, parallel implementation, code review, and PR creation.
Use this agent when the team-lead has a candidate implementation across one or more worktrees and needs a go/no-go gate before opening a PR. The agent re-runs tests and linters, reads the diff, and returns a structured verdict.
Use this agent when the team-lead delegates a single implementation task. The agent works inside a designated git worktree, implements the change, and runs the project's tests and linters until they pass.
Use this agent when starting work on an Azure DevOps User Story/Bug or a GitHub issue. The agent fetches the work item, designs the implementation, decomposes it into parallel tasks, dispatches `software-developer` subagents, gates the result through `code-reviewer`, and opens the PR.
A curated collection of self-contained Model Context Protocol (MCP) tools/servers. Each tool lives in its own folder, is its own Python project, and can be used independently.
requires-python).mcp-tools/
├── agent-memory/
├── pdf-reader/
└── xlsx-reader/
Open this repository in the dev container to get a consistent environment. See .devcontainer/README.md for details.
From the repository root:
uv run pdf-reader
uv run xlsx-reader
uv run agent-memory
Run all tests:
uv sync --dev --all-packages
uv run pytest
Run a specific tool’s tests (example):
uv run pytest mcp-tools/pdf-reader -v
Run docstring lint (pydocstyle D* rules via ruff, Google convention) over the
repo’s in-scope sources:
uv run ruff check --select D mcp-tools/*/src
Notes:
mcp-tools/*/src/**.main.py exists, include it in the command.uvx (from GitHub)Each tool’s README provides a copy/paste snippet intended for MCP client
configuration that runs the tool via uvx directly from GitHub.
General pattern (placeholders):
uvx --from "git+https://github.com/<owner>/<repo>.git@<ref>#subdirectory=mcp-tools/<tool-folder>" \
python -m <tool_module>
Notes:
<ref> with a tag/commit for reproducibility.mcp-tools/<tool-name>/ with its own pyproject.toml.mcp-tools/<tool-name>/README.md, including the uvx snippet.Project development is governed by the constitution in docs/Constitution.md.
uv sync in a WorkspaceThis repo is a uv workspace (multiple independent Python projects under mcp-tools/).
If you want to run the root test suite (which imports all tools), use:
uv sync --dev --all-packages
uv run pytest -q
If you run uv sync at the repo root without --all-packages, uv may remove dependencies that belong to individual tools (because it is syncing the environment to just the root project). That can lead to import errors like missing openpyxl, mcp, pypdf, or tool packages such as pdf_reader.
For per-tool work, cd mcp-tools/<tool> and run:
uv sync --dev
uv run pytest
Uses power tools
Uses Bash, Write, or Edit tools
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 satishc-dev/maruti --plugin dev-teamDesigns and generates new custom subagents, skills, slash commands, chat modes, and prompt files for Claude Code and GitHub Copilot.
Designs decision-ready MCP tool architectures and emits durable spec/guardrails/success-criteria docs.
Multi-agent product management team that gathers intent, produces feature specs, gates them through a reviewer, opens a spec PR, and on approval seeds the Azure DevOps or GitHub Kanban board with work items for handoff to dev-team.
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.
Complete developer toolkit for Claude Code
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams