Agent Plugins Marketplace
← All plugins

claude-mini

v2.0.0

Core of the claude-mini harness: Conventional Commits check on git commit, read-only critics (adversarial, security, ADR), plan / ADR / Codex second-opinion skills. Enable per project (project or local scope), never at user scope.

Claude Code8 Skills

By LenivvenilLicense: MIT0 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
8 skill or MCP entries
Source updated
Sep 26, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install claude-mini for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install claude-mini@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/Lenivvenil/claude-mini

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugin/.

Plugin files

plugin/
├── .claude-plugin/plugin.json
├── skills/adr-author/SKILL.md
├── skills/backlog-review/SKILL.md
├── skills/codex-review/SKILL.md
├── skills/domain-discovery/SKILL.md
├── skills/feature/SKILL.md
├── skills/handoff/SKILL.md
├── skills/plan/SKILL.md
└── skills/project-health/SKILL.md

Included Skills8

adr-authorskills/adr-author/SKILL.md

Write an ADR in MADR 4.0 through a short interview. Use for /adr, "new decision", "architectural decision record", only for architecturally significant decisions by the project's own rules.

backlog-reviewskills/backlog-review/SKILL.md

Groom the project's open issues. Use when asked to review, groom or clean up the backlog ("что с бэклогом"). Runs the backlog-groomer agent, shows its report, and applies only the batch of commands the owner approves.

codex-reviewskills/codex-review/SKILL.md

Second-opinion code review by OpenAI Codex CLI over the whole branch against its base, plus uncommitted changes. Run before committing, opening or merging a PR.

domain-discoveryskills/domain-discovery/SKILL.md

Explore a new or unclear bounded context with the owner, DDD and Event Storming style. Use for "event storming", "new bounded context", "исследуем домен", "нужна Ubiquitous Language". Interviews the owner, then has domain-researcher draft the overview. Not for small changes inside an existing context (use plan).

featureskills/feature/SKILL.md

Take one issue from plan to an open pull request, then hand off. Use for "/feature N", "сделай задачу N", "take issue N". Calling it authorizes the whole cycle; it stops only for an owner decision or a blocking finding.

handoffskills/handoff/SKILL.md

Record where the work stands so a new session or a person can resume in minutes. Use at the end of a feature, before stopping unfinished work, or on "handoff", "сохрани состояние", "передай работу". Appends a journal entry, then replaces the snapshot. Writes only inside the project.

planskills/plan/SKILL.md

Plan a change against a GitHub issue before writing code. Writes plan.md with considered approaches, test strategy and risks; does not touch code.

project-healthskills/project-health/SKILL.md

Read-only health report for this project - pull request review time, open-issue age, ADRs awaiting decision, and AI spend from CodeBurn when enabled. Use for "project health", "метрики проекта", "сколько мы тратим".

Plugin manifests1

plugin/.claude-plugin/plugin.json
{
  "name": "claude-mini",
  "version": "2.0.0",
  "description": "Core of the claude-mini harness: Conventional Commits check on git commit, read-only critics (adversarial, security, ADR), plan / ADR / Codex second-opinion skills. Enable per project (project or local scope), never at user scope.",
  "author": {
    "name": "Lenivvenil"
  },
  "repository": "https://github.com/Lenivvenil/claude-mini",
  "license": "MIT"
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[claude-mini on Agent Plugins Marketplace](https://pluginsmp.com/plugins/claude-mini)