plugins/plugin-manager/skills/plugin-remover/SKILL.md
Interactively select and uninstall agent plugins and skills from the local .agents/ environment.
npx skillsauth add richfrem/agent-plugins-skills plugin-removerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill orchestrates the safe, interactive removal of plugins from the local agent environment and updates the canonical tracking registries (plugin-sources.json and skills-lock.json).
By relying on the plugin_remove.py TUI, this skill ensures that no ghost files, orphaned symlinks, or stale hook registrations remain after a plugin is uninstalled.
plugin_remove.py. Do NOT attempt to manually rm -rf plugin directories directly from .agents/..agents/skills, .agents/workflows, .claude/, .gemini/, etc.skills-lock.json and plugin-sources.json to keep auto-update loops synchronized.Whenever the user asks to "remove a plugin", "uninstall a skill", or "delete a plugin", guide them to use the interactive TUI or run headless via flags.
# Interactive TUI — lists all plugins tracked in plugin-sources.json
uvx --from git+https://github.com/richfrem/agent-plugins-skills plugin-remove
# Headless: remove a specific plugin without prompting
uvx --from git+https://github.com/richfrem/agent-plugins-skills plugin-remove --plugins agent-loops --yes
# Headless: remove all tracked plugins
uvx --from git+https://github.com/richfrem/agent-plugins-skills plugin-remove --all --yes
# Interactive TUI from local clone
uvx --from . plugin-remove
# Headless: remove a specific plugin
uvx --from . plugin-remove --plugins agent-loops --yes
# Or run the underlying Python script directly:
python plugins/plugin-manager/scripts/plugin_remove.py
python plugins/plugin-manager/scripts/plugin_remove.py --plugins agent-loops --yes
python plugins/plugin-manager/scripts/plugin_remove.py --dry-run
For each selected plugin, the uninstaller:
.agents/skills/, .agents/workflows/, .agents/agents/, .agents/hooks/, .claude/, .gemini/, etc.plugin-sources.json (auto-update registry).skills-lock.json.plugin-sources.json must exist and contain tracked plugins. Run plugin-add first.data-ai
Task management agent. Auto-invoked for task creation, status tracking, and kanban board operations using Markdown files across lane directories. V2 enforces Kanban Sovereignty constraints preventing manual task file edits.
development
Create, audit, repair, and document cross-platform symlinks that work correctly on both Windows and macOS/Linux. Use this skill whenever the user mentions symlinks, symbolic links, junction points, .gitconfig symlinks, broken links after git pull, cross-platform path issues, or needs help with ln -s equivalents on Windows. Also trigger when the user reports that files are missing or wrong after switching between Mac and Windows machines using Git. This skill solves the common problem where symlinks committed on macOS show up as plain text files on Windows (and vice versa) because of Git's core.symlinks setting or missing Developer Mode / elevated permissions. **IMPORTANT FOR WINDOWS USERS:** Developer Mode must be enabled before creating symlinks. Without it, Git will check out symlinks as plain-text files or hardlinks, breaking cross-platform workflows.
development
Interactively prepares a targeted Red Team Review package. It conducts a brief discovery interview to determine the threat model, generates a strict security auditor prompt, compiles a manifest of relevant project files, and bundles them into a single Markdown artifact or ZIP archive ready for an external LLM (like Grok, ChatGPT, or Gemini) or a human reviewer.
tools
Reduces AI agent context bloat across three dimensions: (1) duplicate skill deduplication — clears stale agent directory copies since the IDE already reads from plugins/ directly; (2) instruction file optimization — rewrites CLAUDE.md, GEMINI.md, or .github/copilot-instructions.md to under ~80 lines, keeping only rules that directly change agent behaviour; (3) session token efficiency — guidance on cheap subagent delegation, context compounding across turns, and session hygiene. Trigger with "optimize context", "reduce context bloat", "deduplicate skills", "trim CLAUDE.md", "trim GEMINI.md", "fix my context usage", "why are my skills loading twice", "how do I reduce token usage", or "clean up agent directories".