Menu
Audit connected MCP servers for token overhead, redundancy, and security. Use when sessions feel slow or before adding new MCPs.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | mcp-audit |
| description | Audit connected MCP servers for token overhead, redundancy, and security. Use when sessions feel slow or before adding new MCPs. |
Analyze MCP server overhead and recommend cleanup.
Use when:
Each MCP server adds ALL its tool descriptions to every API request. A server with 20 tools adds ~2K-4K tokens per request, regardless of whether you use those tools.
Check all MCP configurations:
cat .claude/settings.json 2>/dev/null | grep -A 50 "mcpServers"
cat ~/.claude/settings.json 2>/dev/null | grep -A 50 "mcpServers"
For each server, estimate token overhead:
Questions to ask:
Disable servers that:
Keep servers that:
MCP AUDIT
Active servers: [N]
Total tools: [N]
Estimated overhead: ~[N]K tokens per request
Server Analysis:
[name] — [N] tools, ~[N] tokens
Status: KEEP / DISABLE / REVIEW
Reason: [why]
Recommendations:
Disable: [list]
Keep: [list]
Review: [list]
Projected savings: ~[N]K tokens per request (~$X.XX per session)
disabledMcpjsonServers to avoid re-recommending already-disabled serversSkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.
Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.
Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials.
Complete AI coding workflow system. Orchestration patterns, 18 hook events, 5 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.
Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.
Render a self-contained HTML viewer for a pro-workflow wiki. Pages, sources, claims, seed queue, page-link graph and full-text search all in one file. No external dependencies, no JS framework, S3-uploadable. Use when the user wants to browse a wiki visually, share its current state with someone, audit research progress, or hand off a knowledge base. Inspired by Thariq Shihipar's "Unreasonable Effectiveness of HTML" — favors information density and shareability over markdown-only outputs.