---
title: "ravn-core"
description: "Core Ravn agent plugin. Bundles reusable skills and MCP server configuration."
canonical: https://agentpluginsdirectory.com/plugins/ravn-core
last-updated: 2026-10-21
---

# ravn-core
Core Ravn agent plugin. Bundles reusable skills and MCP server configuration.
- Slug: ravn-core
- Publisher: Ravn AI Enablement Team
- Repository: https://github.com/ravnhq/ravn-core
- Manifest: plugins/agent/ravn-core/plugin.json
- Version: 0.13.0
- License: MIT
- Category (editorial): other
- Skills: 31 (agent-readiness, ask-ravn, babysit, blast-radius, bug-fix, codebase-design, create-verification-skill, domain-modeling, explain-change, grill-me, grilling, how, improve-codebase-architecture, maintain-verification-skill, pause-safely, pr, principle-boundary-discipline, principle-explain-the-number, principle-fix-root-causes, principle-guard-the-context-window, principle-make-operations-idempotent, principle-prove-it-works, principle-separate-before-serializing-shared-state, principle-type-system-discipline, research, session-pickup, ship, show-me-your-work, typescript-best-practices, why, writing-for-agents)
- MCP servers: 0
- Stars: 2
- Repository created: 2026-10-15
- Repository last pushed: 2026-10-20
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/ravn-core
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What ravn-core does, in the publisher's words

Ravn's agent plugins, open source under the MIT license.

- ravn-core packages the engineering workflows Ravn uses with coding agents: an idea-to-PR flow (ship), code archaeology (how, why), verification, design vocabulary, and handoffs. It runs in Claude Code, Codex, Cursor, and Pi.
- skill-nudge is a Claude Code mod. A background Haiku watches the session and suggests one of your installed skills above the prompt when it fits.

Run /plugin marketplace update ravn to pick up new versions.

Codex reads.agents/plugins/marketplace.json. Add the catalog from GitHub, then install ravn-core and start a new session:

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/ravnhq/ravn-core/HEAD/README.md

## Skills

- agent-readiness: Audit and fix how well a coding agent can work in the current repository. Trigger for "is this repo agent-ready", "why do agents struggle here", "make this repo easier for agents". Skip for code review, a single failing test, or feature work.
- ask-ravn: Find the ravn-core skill or flow that fits your work.
- babysit: Bring the supplied GitHub PR or stack of PRs to merge-ready, merged when the user asks for the merge, or an evidenced blocker. Discover repository gates; verify fixes before pushing; batch review work.
- blast-radius: Find what a change could break outside its diff, and prove the one fact it is safe because of by running real code. Use for "blast radius of X", "what could this break", or a small diff you don't trust yet.
- bug-fix: Reproduce a reported bug, find its cause with runtime evidence, and ship the smallest fix as a PR whose history shows the failure before the fix.
- codebase-design: Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
- create-verification-skill: Generate a project-local verification skill that drives your app the way a user does, any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\", or when a project has no scripted way to prove UI/CLI/service behavior.
- domain-modeling: Build and sharpen a project's domain model. Use when discussing codebase terminology, writing a GLOSSARY.md or ADR, or choosing structures for stateful logic, scattered branches, or repeated shape assumptions.
- explain-change: Teach a code change with text diagrams and a quiz. Use when asked to explain, walk through, or teach a diff, branch, commit, or PR.
- grill-me: A relentless interview to sharpen a plan or design.
- grilling: Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
- how: Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.
- improve-codebase-architecture
- maintain-verification-skill
- pause-safely
- pr
- principle-boundary-discipline
- principle-explain-the-number
- principle-fix-root-causes
- principle-guard-the-context-window
- principle-make-operations-idempotent
- principle-prove-it-works
- principle-separate-before-serializing-shared-state
- principle-type-system-discipline
- research
- session-pickup
- ship
- show-me-your-work
- typescript-best-practices
- why
- writing-for-agents

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.