claude-optimize

Plugin claude-optimize from marketplace btcd-cc-marketplace in BTCDlabs/btcd-cc-marketplace. Commands read from the repo's manifest — 6 days ago.

Skills (9)

• claude-md-manager

  Use when running /optimize:init, /optimize:audit, or /optimize:context to assess CLAUDE.md quality, generate templates, and suggest improvements. Scores files using a weighted rubric covering commands, architecture, patterns, conciseness, currency, and actionability. Do NOT trigger on general file e

• codebase-analyzer

  Use when running /optimize:init or /optimize:audit to detect project type, language, framework, package manager, CI/CD system, and existing Claude Code configuration. Triggers on codebase analysis for optimization, project detection for Claude Code setup, or environment assessment. Do NOT trigger on

• context-optimizer

  Use when running /optimize:context to analyze and reduce token consumption in Claude Code configuration. Measures CLAUDE.md token count, skill description bloat, MCP tool count, and recommends compaction strategies. Triggers on context optimization, token reduction, or CLAUDE.md bloat analysis. Do N

• discover-analyzer

  Use when running /optimize:discover to cross-reference session usage data against the current environment inventory. Detects gaps (repeated manual work that could be automated), bloat (unused skills, MCP servers, agents), and calculates tooling balance. Do NOT trigger on general coding tasks or othe

• hook-recommender

  Use when running /optimize:hooks to analyze existing hooks for health issues, detect missing hooks based on project type, and recommend new hooks with implementations. Triggers on hook analysis, hook creation for optimization, or hook health checking. Do NOT trigger on general hook development or co

• mcp-advisor

  Use when running /optimize:mcp to analyze MCP server configuration, recommend new servers based on detected project stack, perform health checks, and assess security. Triggers on MCP server optimization, MCP recommendations, or MCP health checking. Do NOT trigger on MCP server development or general

• memory-manager

  Use when running /optimize:memory to analyze memory file hygiene, detect stale entries, find duplicates, identify migration candidates to CLAUDE.md, and suggest reorganization. Triggers on memory optimization, memory cleanup, or memory hygiene analysis. Do NOT trigger on general coding tasks or file

• security-auditor

  Use when running /optimize:security or /optimize:init to audit Claude Code security posture including permissions, deny rules, MCP server trust, hook safety, and prompt injection vectors. Triggers on security hardening, permission auditing, or deny rule analysis for Claude Code. Do NOT trigger on ap

• session-analyzer

  Use when running /optimize:audit, /optimize:skills, /optimize:hooks, or /optimize:discover to analyze recent Claude Code session logs for tool usage patterns, error frequency, repeated workflows, and automation opportunities. Do NOT trigger on general coding tasks.

Slash commands (12)

• /claude-optimize:audit

  Full environment health check with scored dimensions

• /claude-optimize:context

  Token/context optimization - reduce bloat and waste

• /claude-optimize:discover

  Reflect on usage patterns to discover new capabilities and prune unused ones

• /claude-optimize:help

  Show all optimize modes and usage

• /claude-optimize:hooks

  Hook analysis - health, coverage gaps, recommendations

• /claude-optimize:init

  First-run setup - detect project, create CLAUDE.md, security

• /claude-optimize:loop

  Guided autonomous optimization loop

• /claude-optimize:mcp

  MCP server management - health, security, recommendations

• /claude-optimize:memory

  Memory hygiene - staleness, duplicates, migration

• /claude-optimize:report

  Comprehensive scored report across all dimensions

• /claude-optimize:security

  Security hardening - permissions, deny rules, MCP trust

• /claude-optimize:skills

  Skill lifecycle - inventory, trigger quality, gaps

Subagents (6)

• codebase-skills-analyzer

  Use this agent to analyze codebase alignment and skill quality when running /optimize:report. Returns scores for codebase_alignment, skill_quality, and claude_md_quality dimensions. Do NOT use for general coding tasks. - Read - Grep - Glob - Bash(python3:*)

• context-measurer

  Use this agent for token counting and context efficiency analysis when running /optimize:context or /optimize:report. Measures CLAUDE.md token load, skill description sizes, MCP tool counts, and compaction resilience. Returns efficiency metrics. Do NOT use for general file analysis or coding tasks.

• discovery-proposer

  Use this agent to generate typed improvement proposals from session reflection data when running /optimize:discover. Receives usage analysis, environment inventory, codebase profile, and gap/bloat analysis. Returns prioritized proposals with security assessments, evidence citations, and implementati

• hooks-memory-mcp-analyzer

  Use this agent to analyze hook health, memory hygiene, and MCP configuration when running /optimize:report. Returns scores for hook_coverage, memory_hygiene, and mcp_health dimensions. Do NOT use for general coding tasks. - Read - Grep - Glob - Bash(python3:*)

• report-aggregator

  Use this agent to aggregate results from multiple optimization analyses into a single weighted report when running /optimize:report. Merges scores from security, context, hook, skill, memory, and MCP dimensions with prioritized action items. Do NOT use for general reporting or coding tasks. - Read -

• security-scanner

  Use this agent for deep security analysis of Claude Code environments when running /optimize:security or /optimize:report. Performs permission auditing, MCP trust assessment, hook injection scanning, and deny rule analysis. Returns a security scorecard. Do NOT use for application security reviews or

Hooks (1)

• Stop

  ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/stop-hook.sh

Similar plugins