repowiserepowise

MCP server

github / spec-kit

πŸ’« Toolkit to help you get started with SDD or any other process!

β˜… 149,921stars on GitHubPythonMIT

This connects Repowise to github/spec-kit's code. It does not install spec-kit.

Repowise maps public repos from their source. Not affiliated with github. What is Repowise?

github.com/github/spec-kitIndexed at 08252af

What is spec-kit?

Spec Kit is an open source toolkit that gives AI coding agents structured processes, reusable templates, and documented outcomes for software work. It is for developers who want their coding agent to follow a defined process, such as building a feature from a specification, fixing a bug, or assessing an idea. The specify command-line tool sets up a project, and the coding agent then runs Spec Kit skills such as /speckit-specify in its chat. The project is written in Python. To install it, run git clone https://github.com/github/spec-kit.git and follow the steps below. Its code health is 7.7 out of 10 (Good), ranked #94 of 4,000+ indexed repos. The last commit to spec-kit was on Nov 10, 2026, and 83 people have contributed.

As of commit 08252af, indexed Nov 10, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.

For agentsspec-kit.md

Repo facts: type, license, health, rank, contributors
spec-kit facts
TypeMCP server
LicenseMIT
Code health7.7 / 10 (Good)
Health rank#94 of 4,000+ indexed repos
Last commitNov 10, 2026
Contributors83
Bus factor1
Size994 files, 225,066 lines

Install spec-kit

Commands copied from the README

  1. 1Clone the spec-kit repository.
    git clone https://github.com/github/spec-kit.git
  2. 2Move into the spec-kit folder.
    cd spec-kit
  3. 3Install the Specify CLI with uv.
    uv tool install specify-cli
  4. 4Create a project that uses GitHub Copilot as the coding agent.
    specify init my-project --integration copilot
  5. 5Change into the new project directory, then launch your coding agent there.
    cd my-project

Releases on GitHub (latest v1.4.3, Nov 19, 2026)

Full install notes on GitHub

Explore spec-kit

Ask about this code in your agent

This connects Repowise to spec-kit's code. It does not install spec-kit. To install spec-kit, use the install steps.

Useful if you want to change or fork spec-kit: your agent can ask how it is put together and get answers that cite its files.

Ask about spec-kit

Answers come from spec-kit's README and source, with the files they cite. Two free answers a day without an account.

Featured answer

Spec Kit is an open source toolkit that gives AI coding agents structured processes, reusable templates, and documented outcomes for work such as building a feature from a specification, fixing a bug, or assessing an idea, and it is written in Python. The specify command-line tool sets up a project, and the coding agent then runs skills such as /speckit-specify in its chat. The chart shows the layers by file count across the 994 files: CLI with 36, Application with 388, Config with 49, and Docs & Tooling with 149. The CLI entry point starts in src/specify_cli/init.py, and src/specify_cli/mcp_server/server.py exposes the same inventory to MCP clients. To go deeper, begin with src/specify_cli/artifacts, which lists the commands, hooks, presets, or extensions each project exposes, and scripts/bash, which prepares the folders and templates a spec-driven feature needs.

Files per layer in spec-kit4 layers.

Basis: Inferred Β· knowledge graphΒ· as of 08252af

Want this for your own codebase? Map your repo free

About this page

Get a page like this for your own codebase

Repowise built this map of github/spec-kit from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Free for 2 public repos, with a page like this one. No card. See how Repowise works

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub

github/spec-kit FAQ

What is Spec Kit?

Spec Kit is an open source toolkit that gives AI coding agents structured processes, reusable templates, and documented outcomes for software work. It works through the specify command-line tool and skills that run in the coding agent's chat.

How does Spec Kit work?

Spec Kit runs from the specify command in a project, and then the coding agent runs its /speckit skills in chat. For spec-driven development, the skills move work from a specification to a plan, tasks, and working code.

How do I install Spec Kit?

Spec Kit is installed with uv tool install specify-cli. You need Python 3.11+, uv, and a supported AI coding agent on Linux, macOS, or Windows. See the install steps

What language is Spec Kit written in?

Spec Kit is written in Python, and its repository also contains shell scripts.

How is the Spec Kit code organized?

Spec Kit keeps its command-line code in src/specify_cli, with an MCP server entry point in src/specify_cli/mcp_server/server.py. Tests are in the tests directory, and CI checks are in .github/scripts.

Who is Spec Kit for?

Spec Kit is for developers who want their AI coding agent to follow structured processes for building features, fixing bugs, or assessing ideas. It also lets teams adopt or create their own processes from reusable primitives.

What license does Spec Kit use?

Spec Kit is released under the MIT license.

Code health

7.6out of 10Good

Hotspots average 6.6, the place fixes pay off most.

On the leaderboards:#21 of 71 Python repos

Key features of spec-kit

  • Ready-made processes for spec-driven development, bug fixing, and idea assessment, with each process run through skills in the coding agent's chat.
  • Extensions, presets, and workflows let teams add commands, adapt templates, and automate prompts and shell tasks.
  • Integrations connect Spec Kit to a coding agent, and a project-local override can replace a template for one project.
  • Catalogs let users discover community components and let organizations host a private catalog of approved components.
  • An artifact inventory shows which layer, such as a preset or extension, supplies each command, template, or script.

How github/spec-kit works

The specify command-line tool is the entry point for users, and src/specify_cli/__init__.py is where that command starts. Running specify with no subcommand prints a banner and a pointer to --help. The src/specify_cli/mcp_server/server.py file is the second entry point, and it exposes the same inventory to MCP clients. The src/specify_cli/artifacts directory lists which commands, hooks, presets or extensions each project exposes, through specify artifact list and specify artifact info. The scripts/bash directory sets up and checks the folders and template files a spec-driven feature needs before work starts. The src/specify_cli/authentication directory fetches from private git hosts with stored tokens and installs the hooks that let a coding agent run Specify commands on its own events.

The codebase has 994 files and 12,521 symbols in 6 modules, led by Python and Shell. Code health is 7.6 out of 10, rated good.