By mishagin-dev
Claude Code workflow machinery: lifecycle hooks (br/git-flow/idea/review gates), workflow skills, and prime/plan-feature/merge commands. Install once, enable per project.
Finalize work on a branch: verify docs + tree are clean, then ship. In **Git Flow repos** `/merge` is verify-only and hands the actual finish to the `git-flow` skill (manual merges to the production branch are blocked by the git-flow enforcement gate). In **plain repos** it merges to main directly. Supports both standard `git checkout -b` branches and `git worktree` flows — all auto-detected at pre-flight.
Plan a feature with parallel research and a Gemini second opinion before exiting plan mode. Designed to run inside Plan Mode (toggle with Shift+Tab).
Load core context for the project.
Remove backgrounds from images using local AI (rembg). Use when removing backgrounds from character art, mascot images, photos, or any image that needs a transparent background.
Test and deploy changes safely. Runs tests as a pre-deploy gate, deploys, then runs post-deploy verification. This is a TEMPLATE — customize the commands and checks for your specific deployment pipeline.
Edit images with precision — crop, resize, mirror, rotate, trim, and reframe. Use this skill whenever the user asks to crop, resize, trim, mirror, flip, rotate, reframe, or otherwise manipulate an image. Also use for creating square crops, portraits/headshots from full-body images, icon sizes, or any image transformation. Even if the request sounds simple, this skill prevents common pitfalls and ensures correct results on the first try.
Generate character art and image variations using AI image generation (Google Gemini) with reference images for style and character consistency. Use this skill when the user asks to generate new character poses, mascot variations, art assets, illustrations, or any AI-generated images — especially when maintaining consistency with an existing character or style.
Review uncommitted code changes using parallel Claude sub-agents with specialized roles (Bug Hunter, Rules Auditor). Spawns multiple focused reviewers for large diffs (50+ lines), single reviewer for smaller changes. Checks for bugs, security issues, CLAUDE.md compliance, and test coverage gaps. Use after completing substantial implementation work, or when the Stop hook requests it. Also invocable manually with /review-work.
Executes bash commands
Hook triggers when Bash tool is used
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.
Personal Claude Code toolkit — a fork of the Claude Code Development Kit repackaged as a plugin + local marketplace. Install the machinery once; enable it per project.
.claude-plugin/marketplace.json # local marketplace exposing the `apogee` plugin
plugins/apogee/ # THE PLUGIN (machinery — installed once, linked per project)
├── hooks/ # lifecycle gates: br/git-flow/idea/review + core advisory + lang guard
├── skills/ # workflow skills: update-docs, review-work, second-opinion, deploy, image-*
└── commands/ # /apogee:prime, /apogee:plan-feature, /apogee:merge
scaffold/ # project CONTENT (copied per project, gitignored in the host)
├── CLAUDE.md GEMINI.md # convention files (Claude + agy)
└── docs/apogee/ # working-memory docs (spec, project-structure, progress, ...)
setup.sh # scaffold content (copy) + enable plugin (link)
sync.sh # re-scaffold new template files into an installed project
apogee plugin. It is installed
once and merely enabled per project via enabledPlugins — never copied. Update once → every
enabled project gets it.CLAUDE.md, GEMINI.md, docs/apogee/*) is copied into each project by setup.sh
and owned by that project. docs/apogee/ is added to the host project's .gitignore.~/.claude/settings.json — they can't be delivered per project./path/to/Apogee/setup.sh /path/to/your-project # enable globally (default)
/path/to/Apogee/setup.sh /path/to/your-project --per-project
Then, once, in an interactive Claude session:
/plugin marketplace add /path/to/Apogee
/plugin install apogee@apogee
/reload-plugins
Bump plugins/apogee/.claude-plugin/plugin.json version, then in any session:
/plugin marketplace update apogee
/reload-plugins
Every hook no-ops unless its trigger is present (.beads/, .idea/ + a running JetBrains IDE, or
git-flow config), so enabling the plugin globally is safe — the machinery only engages in real
projects. Escape hatches: BR_GATE_OFF=1, REVIEW_GATE_OFF=1, IDEA_GATE_OFF=1, TOOL_LANG_OFF=1.
Built and statically validated (manifests, hook scripts, scaffold). Pending: live plugin
validation in a real session (/plugin marketplace add → install → /reload-plugins), then stripping
the legacy global hooks block from ~/.claude/settings.json (do this LAST), then cleaning up the old
Maestro/ bootstrap folder.
npx claudepluginhub mishagin-dev/apogee --plugin apogeeHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.