From laconic
Audit enabled Claude Code plugins for token cost. Lists each plugin's footprint (tools/skills/hooks/MCP servers), flags candidates to disable, asks user before editing settings. Use when user says "audit plugins", "what plugins cost me tokens", or invokes /laconic audit.
How this skill is triggered — by the user, by Claude, or both
Slash command
/laconic:auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Goal: help the user reduce per-turn token spend by disabling plugins they don't use.
Goal: help the user reduce per-turn token spend by disabling plugins they don't use.
~/.claude/settings.json → list enabledPlugins (only true entries).~/.claude/plugins/installed_plugins.json to find its installPath.installPath, read plugin.json for description; enumerate: skills (skills/*/SKILL.md), agents (agents/*.md), commands (commands/*.md), hooks (entries in plugin.json), MCP servers (mcpServers in plugin.json).name: + description: only (body loads on invoke — exclude).description: block in frontmatter.description:.SessionStart output bytes (read first line of hook script if shell, else 50 token default).est_tokens per plugin per turn. Compute total across all enabled plugins.~tokens descending — biggest savings first.~/.claude/settings.json to set enabledPlugins.<name> = false. Do not uninstall — disable is reversible.extraKnownMarketplaces or installed_plugins.json.plugin skills agents cmds hooks mcp ~tokens rec
caveman 3 0 1 1 0 420 disable (overlaps laconic)
figma 0 0 0 0 1 340 disable (web MCP covers)
gitkraken-hooks 0 0 0 2 0 120 disable (no recent git ops)
laconic 2 0 0 1 0 180 keep
total ~tokens/turn: 1060 → disable 3 → save ~880/turn
Then: "Disable [caveman, figma, gitkraken-hooks]? (y/n)"
npx claudepluginhub brillcp/laconic --plugin laconicCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.