# lintlang

> Static linter for AI agent tool descriptions, system prompts, and configs. Context engineering quality gate. Zero LLM calls. One dependency. Runs in CI.

lintlang catches language-level failures before they cause agent misbehavior: vague tool descriptions, missing constraints, schema mismatches, unbounded retry loops, role sequencing errors. It uses 7 structural detectors (H1-H7) with a three-layer exemption system that distinguishes safety constraints from style issues.

Install with `pip install lintlang` (Python 3.10+). Use as CLI (`lintlang scan config.yaml`) or library (`from lintlang import scan_file`). Supports YAML, JSON, and plain text. Output as terminal, markdown, or JSON. CI integration via `--fail-on fail|review`.

## Documentation

- [README](https://github.com/roli-lpci/lintlang/blob/main/README.md): Install, usage, detectors, CI integration
- [Changelog](https://github.com/roli-lpci/lintlang/blob/main/CHANGELOG.md): Version history
- [AGENTS.md](https://github.com/roli-lpci/lintlang/blob/main/AGENTS.md): AI agent integration guide
- [llms-full.txt](https://github.com/roli-lpci/lintlang/blob/main/llms-full.txt): Full technical reference

## Optional

- [License](https://github.com/roli-lpci/lintlang/blob/main/LICENSE): Apache 2.0
- [PyPI](https://pypi.org/project/lintlang/): Package page
