---
title: "agent-kit"
description: "Portable agent skills for software development workflows"
canonical: https://agentpluginsdirectory.com/plugins/agent-kit
last-updated: 2026-10-21
---

# agent-kit
Portable agent skills for software development workflows
- Slug: agent-kit
- Publisher: Raka Adinugraha
- Repository: https://github.com/rakaadi/agent-kit
- Manifest: plugin.json
- Version: 2.2.4
- License: MIT
- Category (editorial): agent-tooling
- Skills: 11 (art-of-comment, delegation-assessment, execute-plan, fix-repository-diagnostics, meaning, program-design, review-code-complexity, review-implementation, subagent-dispatch, writing-plan, writing-unit-test)
- MCP servers: 0
- Stars: 1
- Repository created: 2026-01-10
- Repository last pushed: 2026-10-13
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/agent-kit
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What agent-kit does, in the publisher's words

Agent Kit packages reusable skills for coding agents. Its root manifest and portable components follow the Agent Plugins standard.

Agent Plugins clients discover each immediate skills/ child that contains a SKILL.md. The agents/ and instructions/ directories are authoring resources rather than portable Agent Plugins components.

I built this plugin to customize my own coding agents, to better suit my everyday development workflow.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/rakaadi/agent-kit/HEAD/README.md

## Skills

- art-of-comment: Guide for editing existing and writing inline comments and JSDoc. Use when generating comments for documenting new components or functions, non-obvious code behaviour, or complex logic.
- delegation-assessment
- execute-plan: Execute or resume an attached or referenced implementation plan through repository inspection, implementation, verification, sequential spec-compliance and code-quality review, and human-authorized architectural review when warranted. Use for full or partial plan execution, including free-form inst…
- fix-repository-diagnostics: Close repository diagnostic findings from TypeScript, ESLint, and React Doctor. Use when asked to verify or fix project-wide tsc errors, ESLint violations, React Doctor findings, or a scoped batch from any of those tools.
- meaning: Stop. That last message did not land, restate the last message in plain human language, with no jargon.
- program-design: Design the code shape before implementation for substantial features or refactors that introduce or reshape modules, interfaces, types, file layout, or control flow. Use before writing code when meaningful structural choices remain; skip small fixes and mechanical edits.
- review-code-complexity
- review-implementation
- subagent-dispatch: Dispatch subagents for bounded independent work. Use whenever Codex is about to delegate or spawn a subagent, or when the user asks for parallel agents, context isolation, specialist work, or an independent review. Decide whether delegation helps, select an available agent, write an outcome-first c…
- writing-plan: Use when you have a spec or requirements for a multi-step task, before touching code. Supports either Markdown plans or review-oriented HTML plan artifacts.
- writing-unit-test: Guide for writing a unit test. Use when writing a unit test for functions or components, and when fixing a bug in existing code.

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