Stats
Actions
Tags
From governor
Audits specified paths or common context files (CLAUDE.md, .claude/rules, etc.), estimates recurring context usage, identifies largest/duplicate files, and suggests top three optimizations.
How this command is triggered — by the user, by Claude, or both
Slash command
/governor:auditThe summary Claude sees in its command listing — used to decide when to auto-load this command
# Governor Audit Audit paths from `$ARGUMENTS`. If no arguments are provided, audit common memory files such as `CLAUDE.md`, `.claude/CLAUDE.md`, `.claude/rules`, `AGENTS.md`, Cursor rules, and Windsurf rules. Run: Summarize: - total recurring-context estimate - largest context files - duplicate/oversized files - top three recommendations Prefer low-friction recommendations before governance: 1. compress always-loaded memory 2. split long details into on-demand skills/reference files 3. filter noisy test/build/search output 4. use `/clear` when task changes 5. use `/compact` only wh...
Audit paths from $ARGUMENTS. If no arguments are provided, audit common memory
files such as CLAUDE.md, .claude/CLAUDE.md, .claude/rules, AGENTS.md,
Cursor rules, and Windsurf rules.
Run:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/governor.py" audit $ARGUMENTS
Summarize:
Prefer low-friction recommendations before governance:
/clear when task changes/compact only when continuing the same taskKeep recommendations helpful, not bossy. Do not require planning unless the user explicitly asks or the task is broad and risky.
npx claudepluginhub 0xhimanshu/governor --plugin governor/contextAnalyzes Claude Code's context configuration for optimization opportunities and applies improvements. Also supports resetting to defaults.
/audit-contextAudits project context and agent config files (CLAUDE.md, AGENTS.md, settings.json, etc.) for structure, relevance, conventions, and improvements, with optional additional instructions.
/cc-budgetCalculates remaining context window after fixed overhead from CLAUDE.md, rules, skills, and MCP schemas. Shows budget summary table and top consumers. Also supports audit, optimize, anchor-plan, simulate.
/contexteRuns built-in /context command to fetch real token metrics, analyzes usage patterns for inefficiencies, and provides tailored optimization recommendations.
/context-optimizerDiagnoses context window usage issues, audits MCPs and CLAUDE.md, applies fixes like compaction and disabling unused tools, sets auto-compaction, and reports optimized state.
/context-budgetAudits fixed and dynamic context overhead in the current session — scans CLAUDE.md, agents, MCP servers, rules, skills, and history — estimates tokens per component, reports budget usage and headroom, and issues alerts for oversized components or overflow risk.