Skip to main content

Six developer workflow commands for Claude Code: code review, security audit, test generation, test fixing, bug prediction, and documentation generation.

Project description

Attune Lite

Six developer workflow commands for Claude Code: code review, security audit, test generation, test fixing, bug prediction, and documentation generation. No dependencies required.

Commands

Command What it does
/code-review <path> Multi-pass code review (security, quality, performance, architecture)
/security-audit <path> OWASP-aligned vulnerability scan with remediation plan
/smart-test <path> Find test gaps and generate tests for uncovered code
/fix-test --lf Auto-diagnose and fix failing tests with retry loop (up to 3 attempts)
/bug-predict <path> Predict likely bug locations from patterns and complexity
/doc-gen <path> Generate documentation from source code

All commands default to the current working directory if no path is provided.

How It Works

Each command triggers a structured, multi-pass analysis skill. For example, /code-review runs four passes (security, quality, performance, architecture) and synthesizes findings into a single report with scores, file references, and prioritized fixes.

Skills are prompt-based -- they guide Claude through a systematic analysis process. No external tools, APIs, or package installations are needed.

Example

/code-review src/

Produces a report like:

## Summary
Score: 82/100 | Files reviewed: 24 | Issues: 11

## Security
| Severity | File       | Line | Issue              | Fix           |
|----------|------------|------|--------------------|---------------|
| HIGH     | auth.py    | 45   | Missing input validation | Add schema check |
| MEDIUM   | config.py  | 12   | Hardcoded secret   | Use env var   |

## Top Priorities
1. Add input validation to auth.py:45
2. Move secrets to environment variables
3. Add error handling to db.py:88

When to Use

  • Before opening a PR -- run /code-review to catch issues early
  • During security reviews -- run /security-audit for a structured vulnerability assessment
  • When adding features -- run /smart-test to generate tests for new code
  • When tests fail -- run /fix-test --lf to auto-diagnose and fix failures instead of manually reading each traceback
  • Before releases -- run /bug-predict to find high-risk areas
  • When onboarding -- run /doc-gen to generate documentation for unfamiliar code

Troubleshooting

Command not recognized: Make sure the plugin is installed. Run /plugins to verify attune-lite appears in the list.

Review seems incomplete: For large codebases, specify a narrower path (e.g., /code-review src/auth/ instead of /code-review .).

About

Attune Lite surfaces the best workflow patterns from attune-ai as native Claude Code skills. For the full framework with 15 workflows, CLI integration, and multi-agent orchestration:

pip install 'attune-ai[developer]'

License

Apache-2.0

Project details


Download files

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

Source Distribution

attune_lite-1.0.1.tar.gz (14.0 kB view details)

Uploaded Source

Built Distribution

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

attune_lite-1.0.1-py3-none-any.whl (6.9 kB view details)

Uploaded Python 3

File details

Details for the file attune_lite-1.0.1.tar.gz.

File metadata

  • Download URL: attune_lite-1.0.1.tar.gz
  • Upload date:
  • Size: 14.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.11

File hashes

Hashes for attune_lite-1.0.1.tar.gz
Algorithm Hash digest
SHA256 6c0bc3584334a1f35fff350141ae3e4752fbb099a9a606887bb580c2525987b1
MD5 55a8ffa47d9e1d24766d47de5fbe47f1
BLAKE2b-256 f5a6ef7d080562e3622778187381d1f4e3188bc35f1cf78b4f1dd94df8d95a5d

See more details on using hashes here.

File details

Details for the file attune_lite-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: attune_lite-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 6.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.11

File hashes

Hashes for attune_lite-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 4c471deb08703fed673b8cee9b154e4c5c11caeea3b1e90e8e5456f807104e63
MD5 d78679a4c36cd609aeca2411ffa224cf
BLAKE2b-256 64fbdefd3f5c363301473e47d51f07827f4097ba405a9d514220e3120d52d832

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