Why it matters
Profile
Static linter for AI agent configs and prompts with HERM v1.1 scoring. Catches config mistakes that silently degrade agent behavior.
setup mediumintegration mediuminterface cli
Provenance
Signals
Listed in the awesome-hermes-agent README
Sources: 2 / Surfaces: 1
Fast skim
What the upstream surface says
Short excerpt only, so you can decide whether to click out.
AI agent configs fail for language reasons long before they fail for code reasons: vague tool descriptions, missing stop conditions, and schema fields that say nothing useful.
lintlang is a static linter for agent configs, system prompts, and tool definitions that catches those language-level failures before they hit CI, runtime, or human review.
lintlang scan samples/badtooldescriptions.yaml
lintlangInstallQuick StartScan a single fileScan a directory (finds .yaml, .json, .txt, .md, .prompt)JSON output for CIFail CI on CRITICAL/HIGH findingsFail CI on any MEDIUM+ findings
- "My agent picks the wrong tool because the tool descriptions all sound the same."
- "We only catch prompt and config drift after the agent starts looping."
- "I want a prompt linter or agent-config linter that runs in CI with no model calls."
- "Our YAML is valid, but the instructions inside it are still bad."
- name: Lint agent configs
- YAML (.yaml, .yml) — OpenAI function-calling format, tool definitions
- JSON (.json) — OpenAI and Anthropic tool schemas, message arrays
- Plain text (.txt, .md, .prompt) — System prompts, instruction docs