6 devtools
Utilities agentic engineers use around their agents: MCP tooling, context packing, specs, usage tracking.
- Rank 12
Gives coding agents structured processes for spec-driven builds, bug fixes and idea assessment
- score 85
- 141k stars
- pushed
- v1.2.0 on
- MIT
Install with uv and create a project
uv tool install specify-cli specify init my-project --integration copilotWhen to use it, when to skip it
Why you'd want it
The specify CLI installs skills or command files for your coding agent, which you then run in chat: constitution once per project, then specify, plan, tasks, implement and converge for each feature. Optional extensions add a bug-fixing flow (assess, fix, test) and an idea assessment flow that ends in a go, clarify or stop decision, with reports saved as Markdown under .specify/. It has integrations for dozens of agents, including GitHub Copilot, Claude Code, Codex CLI, Cursor, Gemini CLI and Zed, and you can customize it with extensions, presets and workflows.
Best for
- Teams that want a spec before code
- Keeping agent work reviewable step by step
- Using one process across several coding agents
Use it when
You want a coding agent to work from a written specification, plan and task list rather than one prompt, with artifacts you review at each step.
Skip it if
Your changes are small enough that a single prompt does the job. The CLI needs Python 3.11+ and uv.
- Rank 16
Provides Anthropic's example Agent Skills, the document skills behind Claude, and the skills spec
- score 83
- 181k stars
- pushed
- Mixed license
Add as a Claude Code plugin marketplace
/plugin marketplace add anthropics/skills /plugin install document-skills@anthropic-agent-skills /plugin install example-skills@anthropic-agent-skillsWhen to use it, when to skip it
Why you'd want it
Skills are folders with a SKILL.md file of instructions and metadata, plus optional scripts and resources, that Claude loads dynamically for specialized tasks. This repo collects Anthropic's examples across creative, technical and enterprise work (for example mcp-builder, webapp-testing, skill-creator and frontend-design), the docx, pdf, pptx and xlsx skills that power Claude's document features, a skill template and the Agent Skills specification. In Claude Code you can add the repo as a plugin marketplace and install document-skills or example-skills.
Best for
- Learning how to write a skill
- Adding document skills to Claude Code
- Starting a new skill from a template
Use it when
You are writing your own skills and want working patterns to copy, or you want Anthropic's document and example skills in Claude Code.
Skip it if
You want production-ready behavior: Anthropic says these skills are for demonstration and education and may differ from what Claude does. The document skills' license forbids copying them outside Anthropic's services or making derivative works.
- Rank 19
Builds MCP servers, clients and interactive apps in Python from plain decorated functions
- score 82
- 28.1k stars
- pushed
- v4.1.0 on
- Apache-2.0
Install with pip
pip install fastmcpWhen to use it, when to skip it
Why you'd want it
You declare a tool as a Python function and FastMCP generates the schema, validation and documentation; when you connect to a server by URL, it handles transport negotiation, authentication and the protocol lifecycle. Besides servers and clients it supports apps, which give tools interactive UIs rendered in the conversation. FastMCP 1.0 was incorporated into the official MCP Python SDK in 2024, and Prefect maintains a TypeScript counterpart.
Best for
- Python developers writing MCP servers
- Calling MCP servers from Python code
- Tools that need an interactive UI in chat
Use it when
You are writing an MCP server or client in Python and want schemas, transports and auth handled for you.
Skip it if
Your server is not written in Python; the TypeScript version lives in a separate repo, PrefectHQ/fastmcp-ts.
- Rank 29
Tests and debugs MCP servers from a web UI, a scriptable CLI or a terminal UI
- score 79
- 11.1k stars
- pushed
- 2.11.0 on
- Mixed license
Run with npx
npx @modelcontextprotocol/inspectorWhen to use it, when to skip it
Why you'd want it
The Inspector is the reference developer tool from the MCP project for testing and debugging servers. One npx package gives you a web client that shows the JSON-RPC exchange as you call tools, a CLI with JSON output for CI, shell pipelines and coding agents, and a terminal UI; all three share the same transports, config files and OAuth state. It also installs mcpdo, an experimental client that keeps one connection open across many commands.
Best for
- MCP server authors
- Smoke-testing MCP servers in CI
- Letting a coding agent check its own MCP server from the shell
Use it when
You are building or debugging an MCP server and want to list and call its tools directly, interactively or from a script.
Skip it if
You only use MCP servers and never build one. It needs Node 22.19.0 or newer, and on machines without an OS keychain it stores secrets in an unencrypted file unless you supply a key.
- Rank 49
Reports token usage and costs for Claude Code, Codex and other coding agent CLIs from local data
- score 67
- 19k stars
- pushed
- v20.0.33 on
- MIT
Run with npx
npx ccusage@latestWhen to use it, when to skip it
Why you'd want it
ccusage reads the usage data that coding agent CLIs store locally and turns it into daily, weekly, monthly and session reports, with per-model breakdowns and separate cache token counts. One report covers Claude Code, Codex, OpenCode, Gemini CLI, GitHub Copilot CLI and more than a dozen other tools, and there are Claude Code extras such as 5-hour billing window reports and a status line integration. Output is a table or JSON, and an offline mode uses cached pricing data.
Best for
- Tracking spend across several coding agents
- Claude Code users watching 5-hour usage windows
- Exporting usage as JSON for your own dashboards
Use it when
You want to see how many tokens and dollars your coding agent sessions use, by day, model, session or project.
Skip it if
You need team-wide spend tracking: it only reads local data on the machine where it runs. Costs are calculated from LiteLLM pricing data, not read from your provider bill.
- Rank 54
Packs a repository into one AI-friendly file in XML, Markdown, JSON or plain text
- score 66
- 28.8k stars
- pushed
- v1.18.1 on
- MIT
Run with npx
npx repomix@latestWhen to use it, when to skip it
Why you'd want it
Repomix reads a local or remote repository, respects .gitignore and .repomixignore, uses Secretlint to leave out files that match known credential formats, and writes one file with a summary, directory structure and file contents, plus token counts per file. The --compress option uses Tree-sitter to keep key code elements with fewer tokens, and large outputs can be split into parts. It also runs as an MCP server (repomix --mcp) and can generate Claude Agent Skills from a codebase.
Best for
- Feeding a whole codebase to a chat model
- Checking token counts before sending context
- Packing a remote GitHub repo for reference
Use it when
You want to hand an LLM a full or filtered snapshot of a repository in one file, or let an agent pack repos through MCP.
Skip it if
Your coding agent already reads files in your workspace and you have no need for a single packed file. By default the MCP server can read any path the host user can, so use --sandbox with untrusted clients.