Promote Sign in Sign up

Code assistant

Speclint

Speclint scores your specs 0-100 across 5 dimensions before any AI agent touches them. Deterministic regex scoring — no AI hallucination in the diagnosis. CLI, GitHub Action, and MCP Server.

Source rating 5.0 (84) 0 views 0 saves Freemium
DEVELOPER TOOLS spec linting AI coding
More categories (3)
MCP Code quality open-source
Visit website Sign in to save

Free + from Lite: $9/mo unlimited linting + rewrites.

Verdict

A quick read before you dig into the full page.

Best if
Speclint scores your specs 0-100 across 5 dimensions before any AI agent touches them. Deterministic regex scoring — no AI hallucination in the diagnosis…
Skip if
You need enterprise SLAs or a fully managed team plan right away
Pick this when
Freemium · Free + from Lite: $9/mo unlimited linting + rewrites.

Overview

Speclint is an open-source spec linter that scores user stories and requirements on a 0-100 scale across 5 dimensions: Measurable Outcomes (20pts), Testable Criteria (25pts), Constraints (20pts), No Vague Verbs (20pts), and Verification Steps (15pts).

The scoring is fully deterministic — pure regex pattern matching, no LLM involved. AI is only used for the optional rewrite feature, which rewrites failing specs to pass all checks.
Available as: CLI (npx speclint lint), GitHub Action, MCP Server (3 tools), and REST API.

Free tier: 5 lints/day. Paid plans start at $9/mo for unlimited linting and rewrites. Open source (MIT).

Built for teams shipping to AI coding agents — if your spec scores below 70, the agent will hallucinate. Fix the spec first.

Speclint screenshot

Access & connections

Where you can use Speclint, and what it plugs into.

Platforms

CLI

Integrations

GitHub MCP

API

Public API available

Browse other tools with an API

Capabilities

What this tool accepts, produces, and is strongest at.

Highlights

  • Deterministic 0-100 scoring across 5 dimensions
  • CLI, GitHub Action, and MCP Server
  • AI-powered spec rewrite to fix failing specs
  • Agent-ready threshold scoring (70+)
  • Open source (MIT) with paid tiers

FAQ 5

What is Speclint?
Speclint is an open-source spec linter that scores user stories and requirements on a 0-100 scale across 5 dimensions: Measurable Outcomes (20pts), Testable Criteria (25pts), Constraints (20pts), No Vague Verbs (20pts), and Verification Steps (15pts).

The scoring is fully deterministic — pure regex pattern matching, no LLM involved. AI is only used for the optional rewrite feature, which rewrites failing specs to pass all checks.
Available as: CLI (npx speclint lint), GitHub Action, MCP Server (3 tools), and REST API.

Free tier: 5 lints/day. Paid plans start at $9/mo for unlimited linting and rewrites. Open source (MIT).

Built for teams shipping to AI coding agents — if your spec scores below 70, the agent will hallucinate. Fix the spec first.
How to use Speclint?
Run npx speclint lint in your terminal, paste a user story, and get a 0-100 score instantly. Or add the GitHub Action to score specs on every PR. Or connect the MCP Server to Claude, Cursor, or any AI coding agent — it auto-lints specs before the agent writes code.
Is Speclint open source?
Yes, Speclint is MIT licensed. The CLI and scoring engine are fully open source on GitHub. Paid tiers add unlimited usage, AI rewrites, and API access.
How is the score calculated?
Pure regex pattern matching across 5 dimensions — no AI involved in scoring. This makes results deterministic and reproducible, unlike LLM-based tools.
What is the MCP Server?
MCP (Model Context Protocol) lets AI coding agents like Claude and Cursor auto-lint specs before writing code. Install the server and your agent gets 3 tools: lint, score, and rewrite.
Speclint Free + from Lite: $9/mo unlimited linting + rewrites.
Visit website