Interlint — AI skill for Claude Code
Make your AI coding agent fix the rules it breaks before it moves on.
How to install Interlint
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open RuloGB/interlint and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Interlint does
Make your AI coding agent fix the rules it breaks before it moves on. Runs your existing ArchUnit, Checkstyle and PMD checks inside Claude Code and OpenCode.
Alternatives in AI
- OpenContext — A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC 1.1k ★
- Module Feature — Add a new feature (model + service + controller + views + routes + tests) to an existing module 407 ★
- SoloDawn — Catches and repairs AI hallucinations before delivery: three quality gates, 31 built-in rules, a self-healing 312 ★
README
Interlint runs the checks your project **already has**, such as ArchUnit, inside the agent's session. When the agent breaks a rule, it hears about it right away and fixes it in the same session, not in CI and not by hand.
**Works with [Claude Code](docs/claude-code.md) and [OpenCode](docs/opencode.md)**, on Maven projects that use ArchUnit, Checkstyle or PMD.
**Status:** 1.4.2. Stable for Maven projects, including multi-module projects and workspaces of several projects.
The problem
Your code rules live in two places that never meet:
- As text in
AGENTS.md. The agent may forget it, and nobody enforces it. - As checks (ArchUnit tests, Checkstyle, PMD). The agent only hears about them when someone builds or CI fails.
By then the agent's session is over, and someone has to fix the code by hand.
What Interlint does
- After each edit, fast checks run and any violation goes straight back to the agent. This needs `mvnd`.
- At task end, the full checks run, for the projects the agent changed. If a rule is broken, the agent cannot finish until everything is green.
This is what the agent sees when it puts infrastructure code in the domain:
✗ architecture · ARCH-01: domain depends on nothing outside domain
Method calls constructor ()> in (Order.java:27)
at src/main/java/com/acme/domain/Order.java:27
Fix these problems before continuing.
The agent reads the rule, removes the dependency and carries on.
Why teams use it
- No new rules to write. Interlint has no rules and no analysis engine of its own. Your existing checks stay the single source of truth.
- Deterministic. Your own build decides, not a prompt the agent may ignore
Related Skills
Apex Optimizer Skills
AI-native code review and optimization skills for Claude Code, Cursor, and agent IDEs. Audits Salesforce Apex,
Duet
Two AI models build it; the harness checks the rules. fix/add/refactor/build/plan where tests are replayed aga
Agentkeel
Governed agent platform on Amazon Bedrock and AgentCore. Seats own the rules, goldens and thresholds; only a s
Codeblast
Know what breaks before you merge — mutation-tested code graph with architecture, change & impact maps. Eviden
Local Exact Match Domain Research
Local exact-match domain (EMD) research skill for Claude, Codex, OpenCode & other AI agents — validate, score
Auto Guard
A cached auto command review guard for AI coding agents — rules, memory and LLM verdicts (allow/deny/ask) befo
Related Agents
Opencode
Coding subagent that runs inside opencode, on any provider and model opencode supports (OpenAI, Google, Moonsh
Teibto Agent
Hand ONE well-scoped code or text edit inside a git repo to the machine's coding-agent CLI (OpenCode or Cline,
Figure Critic
Reviews a generated or existing figure (data plot or diagram) against figure-quality rules before it goes in t