#linter

Senior-developer discipline for AI coding agents. A commit gate that counts unchecked as failing, quality controllers that refuse to call unfinished work done, and a lessons loop that closes each escaped bug's class. One Go binary, no runtime deps, works with 20+ agents.

Design intelligence engine for AI coding tools (Claude Code, Cursor, Windsurf). Deterministic anti-AI-slop linter with 152 rules, 160 brand specs, a 7-axis synthesizer, an MCP server (18 tools), 25 commands, 17 IDEs. Offline, never calls an LLM. MIT.

Detect AI-generated language patterns in your codebase with this Claude Code skill to ensure human-quality prose.

In a battle against Claudlish, this just might be a pretty good defense.

Organize, validate, and deploy AI agent skills (SKILL.md) at scale — lint rules, token budgets, secrets governance, and one-tree deploys to Claude Code, Codex, Gemini CLI, and Cursor.

Pine Script v6 skills and MCP tooling for coding agents — backed by a real validator, not prose.

VSCode + VSCodium extension for Ollama Modelfiles. Syntax highlighting, 18-rule linter (unknown PARAMETERs, missing FROM, bad MESSAGE roles, quoting errors), hovers, autocomplete, and 26 snippets. Works in vscode.dev, Cursor, and Windsurf.

Find the safety rules your AI agent prompt forgot. Offline linter — 23 controls, CLI + Action + browser. No API key.

Keeps a project's roadmap, changelog, improvements and strategy files to one format - a schema at the point of insertion, not a linter after the fact. Python CLI + Claude Code plugin.

Lint Your Prompts, Ship Better Agents – Prompt Refiner 2026 Rule Engine

Open-source Claude Code plugin marketplace framework and distribution CLI deploying fast quality guardrails (ruff, pyright, biome, clippy), MCP tools, and language packs.

Lint Claude Code skills before you ship them. Catches broken frontmatter, name drift, weak triggers. Zero runtime deps, Python 3.10+.

Writing tools for long-form work: lint prose for AI tells, audit structure for unnumbered figures and broken cross-references. Runs standalone or as agent skills.

Structural checks for an agent memory archive: size budget, frontmatter, per-line provenance, perishable state, personal data, and suppression instructions. Six detectors, one CLI, no network calls.

Static cross-agent portability linter for agent skills — will your SKILL.md work on Claude Code, Codex, and Cursor?

Lint the documentation & metadata quality of VGI (Vector Gateway Interface) data workers — descriptions, column comments, tags, and example queries — with a quality score, per-version baselines, and agent-friendly output.

A linter for the belief state of agent instruction files — finds retracted rules that came back. Local, deterministic, no model; signed receipts verify offline.

Deterministic, zero-dependency detector for AI-generated 'slop' tells in prose.

Your documentation makes claims. This checks whether they are still true, against git and the filesystem. Dead commit references, false merge claims, broken links, tags that never shipped, files that contradict each other. Works on the README you already have.

One AGENTS.md, every AI coding agent. Sync the rules files (Claude Code, Cursor, Copilot, Windsurf, Gemini, Cline +10 more) and lint them before they rot.

A least-privilege linter for Claude Code agent policies: proves whether an agent can reach credential egress with no gate crossed, or hands back the exact witness. Zero-dependency, deterministic, offline.

If you want to sound more human, or really, more like me: a writing linter tuned to my voice, as a Claude Code skill

Strip AI tells from prose: a linter, scorer and prompt builder measured on 1.9M words of human vs. Claude writing

Universal quality and safety guard plugin for OpenCode AI agents (Dual-Mode: v1 & v2)

Check an MCP server against Claude Connectors Directory and ChatGPT app directory rules before you submit: annotations, read/write split, tool poisoning, OAuth discovery.

Repère les tics d'écriture IA dans vos textes en français et propose une correction. Déterministe, hors ligne, skill pour Claude Code, Codex, Cursor, Gemini, Grok.

AI writing skill and zero-dependency CLI linter for producing authentic, human-sounding articles and technical guides without robotic clichés, em dashes, or fabricated claims. 34 languages supported.

Causal A/B harness: tool descriptions cost up to -28.9pp

Style and quality linter for Norwegian and English text - MCP server for agents, with TypeSafe's Jev as the judgment layer. Reports findings, never authorship verdicts.

Find the deprecated and retired LLM models your code still calls. CLI, pre-commit hook and GitHub Action that fail your build before an OpenAI or Anthropic model is retired.