LintLang v0.8.3 — Better agent-file discovery and diagnostics

Find more of the instructions your agents rely on. Get clearer feedback when something needs fixing.

LintLang is a local, deterministic static linter for AI agent instructions, prompts, and tool definitions. This release improves file discovery, configuration diagnostics, and developer integrations.

What's new

Cursor project-rule discovery

LintLang now recognizes .cursor/rules/*.mdc files in supported instruction-file discovery workflows, including pre-commit.

Clearer YAML tool diagnostics

Invalid YAML tool names now receive more precise diagnostic context, making findings easier to locate and correct.

Integrations and developer experience

• Refined Claude Code and Cursor plugin metadata and setup guidance.
• Documented which CrewAI and AutoGen-style shapes are inspected and which return a coverage error.
• Improved documentation with real scan output and verified field examples.
• Dependency and compatibility maintenance.

Contributors

Thank you to:

• @Soham-o for Cursor project-rule discovery
  (#170) and clearer YAML
  tool-name diagnostics
  (#174).
• @yunaremaia for the original contribution
  behind the bounded NUL-density input-integrity guard
  (#179, refined in
  #180).

Try it

Run without a global installation:

uvx --from lintlang==0.8.3 lintlang scan .

Or install with pip:

python -m pip install -U lintlang==0.8.3
lintlang scan .

No LLM calls during scanning. Findings are advisory by default; CI enforcement is opt-in.

Resources

• Documentation: https://lintlang.ai/
• PyPI: https://pypi.org/project/lintlang/
• Source and integrations: https://github.com/hermes-labs-ai/lintlang
• Full changelog: v0.8.2...v0.8.3