Speclint logo

Speclint

Paid
Inputs: textOutputs: text
Starting Price
$9/mo
Type
Saas
Company
Speclint

About 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

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.

Key Features

  • 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

Use Cases

  • Score user stories before handing them to AI coding agents
  • Add spec quality gates to CI/CD pipelines
  • Rewrite vague requirements into agent-ready specs
  • Audit backlog quality across a sprint

Key Features

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

Pros & Cons

Pros
  • Fully deterministic scoring eliminates variability and ensures reliability
  • Specifically optimized for specs used with AI coding agents, addressing hallucination risks
  • Multiple deployment formats (CLI, GitHub Action, MCP Server, REST API) for flexible integration
  • Open-source core allows customization and self-hosting
  • Affordable paid plans starting at $9/month for unlimited usage
  • Quick feedback loop with regex-based checks for high efficiency
Cons
  • Free tier restricted to only 5 lints per day, limiting heavy users
  • Regex-only scoring may overlook semantic nuances in complex specs
  • AI rewrite feature introduces potential costs and non-determinism
  • Pricing details listed as 'contact' despite mentioned $9/mo plans, creating uncertainty
  • Primarily focused on spec linting, lacking broader requirements management features

Best For

Score user stories before handing them to AI coding agentsAdd spec quality gates to CI/CD pipelinesRewrite vague requirements into agent-ready specsAudit backlog quality across a sprint

Alternatives to Speclint

FAQ

What are the five scoring dimensions in Speclint?
Measurable Outcomes (20pts), Testable Criteria (25pts), Constraints (20pts), No Vague Verbs (20pts), and Verification Steps (15pts).
Is the scoring process deterministic?
Yes, core linting uses pure regex pattern matching with no LLM involvement; only the optional rewrite uses AI.
What integrations does Speclint support?
CLI (npx speclint lint), GitHub Action, MCP Server (3 tools), and REST API.
What is the free tier limit?
5 lints per day; paid plans start at $9/month for unlimited linting and rewrites.
Why is Speclint important for AI coding agents?
Specs scoring below 70 lead to agent hallucinations; Speclint ensures high-quality inputs first.
Is Speclint open source?
Yes, licensed under MIT; GitHub repo at https://github.com/speclint-ai/speclint.