No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by hermes-labs-ai · Agent Tool · ★ 135
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is lintlang safe to install? View the security audit →
lintlang lintlang is a static linter for AI agent configs, tool descriptions, and system prompts that runs zero-LLM quality gating in CI. 7 structural detectors (H1–H7), 6 HERM v1.1 scoring dimensions, validated against 28 comparison files. 154 tests (including a CI-mechanical doc-consistency gate), 0 LLM calls per scan, 2ms per file. Reproduce: flags 4-of-4 known-bad samples and passes 1-of-1 clean — same input, same output, every run. 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. catches those language-level failures before they hit CI, runtime, or human review — without calling a model. "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." How it differs from LLM-based config review Most agent-config "review" tools call
| Stars | 135 |
| Forks | 14 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 71.8781693246348/100 |
| Open Issues | 7 |
| Last Updated | 2026-10-03 |
| Created | 2026-02-28 |
| Platforms | claude-code, cli, gemini, python |
| Est. Tokens | ~16k |
These tools work well together with lintlang for enhanced workflows:
Looking for a lintlang alternative? If you're comparing lintlang with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before ag
One config to rule all your AI agents: portable (every project, every session), effective (curated writing, ro
The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readin
Help your AI agent finish the job: solve the right problem, keep changes focused, and show what was verified.
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman
Run LLM prompts from your shell
Explore other popular agent tool tools:
lintlang is Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions, missing stop conditions, and schema gaps before they reach runtime. Zero-LLM, determinist. It is categorized as a Agent Tool with 135 GitHub stars.
lintlang is primarily written in Python. It covers topics such as agent-config, agent-linter, agent-skills.
You can find installation instructions and usage details in the lintlang GitHub repository at github.com/hermes-labs-ai/lintlang. The project has 135 stars and 14 forks, indicating an active community.
lintlang is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to lintlang on Agent Skills Hub include promptguard, anywhere-agents, agents-shipgate. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: