Skip to main content

Unified CLI for the Agent Quality Toolkit (agentmd, coderace, agentlint, agentreflect)

Project description

agentkit-cli

One install to rule them all.

pip install agentkit-cli

Get the full Agent Quality Toolkit pipeline in a single command — no more juggling four separate pip install steps.


What is it?

agentkit-cli is a unified meta-CLI that wraps the Agent Quality Toolkit quartet:

Tool Purpose
agentmd Generate CLAUDE.md context files
agentlint Lint AI context files and git diffs
coderace Benchmark AI coding performance
agentreflect Generate reflection reports from failures

Pipeline Overview

agentkit run
    │
    ├── 1. agentmd generate        → produces CLAUDE.md
    ├── 2. agentlint check-context → lints CLAUDE.md
    ├── 3. agentlint (diff)        → lints recent changes
    ├── 4. coderace benchmark      → (opt-in via --benchmark)
    └── 5. agentreflect generate   → reflection on failures

Zero to full pipeline in 30 seconds.


Installation

pip install agentkit-cli

Install the quartet tools too:

pip install agentmd agentlint coderace agentreflect

Usage

agentkit init

Initialize agentkit in a project. Checks which tools are installed and creates .agentkit.yaml.

agentkit init
agentkit init --path /my/project

Creates .agentkit.yaml:

tools:
  coderace: true
  agentmd: true
  agentlint: true
  agentreflect: true
defaults:
  min_score: 80
  context_file: CLAUDE.md

agentkit run

Run the full quality pipeline sequentially.

agentkit run
agentkit run --path /my/project
agentkit run --skip generate
agentkit run --skip lint
agentkit run --skip benchmark
agentkit run --skip reflect
agentkit run --benchmark        # include benchmark step
agentkit run --json             # emit summary as JSON
agentkit run --notes "regression after refactor"

Missing tools are skipped automatically with a warning — you don't need all four installed.


agentkit status

Quick health check: tool versions, config presence, last run summary.

agentkit status
agentkit status --path /my/project
agentkit status --json

Links


License

MIT

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agentkit_cli-0.1.0.tar.gz (10.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agentkit_cli-0.1.0-py3-none-any.whl (11.0 kB view details)

Uploaded Python 3

File details

Details for the file agentkit_cli-0.1.0.tar.gz.

File metadata

  • Download URL: agentkit_cli-0.1.0.tar.gz
  • Upload date:
  • Size: 10.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for agentkit_cli-0.1.0.tar.gz
Algorithm Hash digest
SHA256 d876c0f6845ca28f4780db04186005a1ffc6be3d7c0e362e83ef445e6543c1e8
MD5 652a2373fc52b6748f255f60d8e44f86
BLAKE2b-256 91b3a0c667f38383fc318e864578d026b4a2c3b115a5b972ca3a1077ce468799

See more details on using hashes here.

File details

Details for the file agentkit_cli-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: agentkit_cli-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 11.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for agentkit_cli-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 048a8edf2cfb59267dd431a5a76d6bba9261e8c50fde08a236b644d36c5d3c7b
MD5 a08f45aa2ebd912854aca46d3d8bad11
BLAKE2b-256 8537b17c7f762cddefdb9b3223c3864582fe459ecad83ec975324e87fb189053

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page