Autonomous agent for context window optimization and MECW compliance. Triggers: context audit, MECW compliance, token optimization, skill optimization, context analysis, growth monitoring, context health check Use when: full context audits needed, skills exceed token budgets, pre-release compliance verification, periodic health checks DO NOT use when: single skill optimization - use optimizing-large-skills skill. DO NOT use when: quick token counts - use skills-eval instead. ⚠️ PRE-INVOCATION CHECK (parent must verify BEFORE calling this agent): - Single skill token count? → Parent runs `wc -w skill.md` or estimates - Quick size check? → Parent reads file header - One-off query? → Parent uses Read tool directly ONLY invoke this agent for: full plugin audits, growth trend analysis, optimization recommendations, or pre-release compliance verification.
/plugin marketplace add athola/claude-night-market/plugin install conserve@claude-night-markethaikuAutonomous agent specialized in analyzing and optimizing context window usage across skill files and plugin structures.
Dispatch this agent for:
Before any work, assess if this task justifies subagent overhead:
Return early if:
wc -w skill.md or parent estimates"Continue if:
Use the context-optimizer agent to analyze all skills in the conserve plugin
and generate a prioritized list of optimization opportunities.
The agent produces a structured report including:
This agent uses tools from:
scripts/growth-analyzer.py - Growth pattern analysisscripts/growth-controller.py - Optimization executionabstract plugin - Token estimation utilitiesDesigns feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences