By Tim-Pohlmann
Custom static analysis powered by Opengrep. Generate rules with Claude, run them in CI.
Custom static code analysis powered by Opengrep, integrated with Claude Code.
This repo is a vibe coded side project and therefore full of AI Slop.
You have a mature codebase with a defined architecture and coding style and you don't want AI agents to ruin it? Dolphin will slap AI agents (and sloppy developers) in the face and force them to follow your rules!
Dolphin helps you generate and enforce Opengrep rules. It comes in two major components:
/plugin marketplace add Tim-Pohlmann/Dolphin
/plugin install Dolphin@Dolphin
/generate-rules
The plugin provides:
generate-rules skill for interactive rule generationdolphin CLI binary.dolphin/rules.yaml after every Write/Edit and prints diagnostics directly in Claude Code (no additional install required)Download the binary from Releases and run it:
dolphin check
It will run all rules and print out a report. If any violation with severity ERROR is found, the tool emits exit code 1, which can be used to block your CI.
Admin access level
Server config contains admin-level keywords
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
npx claudepluginhub tim-pohlmann/dolphin --plugin dolphinHybrid agent-harness sensor for Claude Code. Computational + inferential rule lanes, subagent context firewall, scoped feedforward, session-aware verification.
Deterministic linting hooks, semantic code validators, and a multi-LLM advisory council. Enforces coding rules mechanically — not by suggestion.
Generate comprehensive analysis and documentation of entire codebase
Runs code reviews using external LLM CLIs (OpenAI Codex, Google Gemini) on uncommitted changes, branch diffs, or specific commits. Bundles Codex's built-in MCP server for direct tool access.
This skill should be used when the model needs to ensure code quality through comprehensive linting and formatting. It provides automatic linting workflows for orchestrators (format → lint → resolve via concurrent agents) and sub-agents (lint touched files before task completion). Prevents claiming "production ready" code without verification. Includes linting rules knowledge base for ruff, mypy, and bandit, plus the linting-root-cause-resolver agent for systematic issue resolution.
Automated code review with severity levels and actionable feedback