Skill Claude CodeCodex
Drift detection + apply for a scaffolded harness. Re-renders the template with the same vars, computes added/removed/changed file plan, and applies with Git-style conflict markers or .rej files. Default is dry-run.
Skill Claude CodeCodex
Release-readiness umbrella check for a scaffolded harness — runs doctor, witness verify, hardcoded-path scan, MCP server config, and GCP Secret Manager validation in one shot. Exits non-zero if any sub-check fails.
Skill Claude CodeCodex
Verify the Ed25519 witness manifest of a scaffolded harness. Fast yes/no signature check that proves the publisher signed this exact file set — separate from the full release-readiness umbrella in validate-harness.
Plugin Claude Code
Repo-aware coding agent harness for kimi-k3-in-c — Kimi K3 (2.78T-param) inference in portable C99: one CPU, 8 GB RAM, no BLAS, no framework, no GPU.
Command Claude Code
Health-check the harness: kernel load, MCP wiring, memory backend, host adapter.
Command Claude Code
Review the current working diff for correctness, security, and reuse.
Settings file Claude Code
MCP configuration declaring 2 servers: kimi-k3-harness, codeindex.
Skill Claude CodeCodex
Evolve this harness with Darwin Mode — frozen model, evolving harness (real, sandboxed, safety-gated).
Skill Claude CodeCodex
Turn a feature request into a minimal, file-level implementation plan before any code.
Command Claude Code
Reviewed all command files in .claude/commands/analysis/ directory to ensure proper usage of.
Command Claude Code
Commands for analysis operations in Claude Flow.
Command Claude Code
Analyze performance bottlenecks in swarm operations and suggest optimizations.
Command Claude Code
Identify and resolve performance bottlenecks in your development workflow.
Command Claude Code
Generate comprehensive performance reports for swarm operations.
Command Claude Code
Reduce token consumption while maintaining quality through intelligent coordination.
Command Claude Code
Analyze token usage patterns and optimize for efficiency.
Command Claude Code
Automatically spawn and manage agents based on task requirements.
Command Claude Code
Automatically detect and recover from errors without interrupting your flow.
Command Claude Code
Maintain context and learnings across Claude Code sessions for continuous improvement.
Command Claude Code
Automatically spawn the right agents at the right time without manual intervention.
Command Claude Code
Intelligently spawn agents based on workload analysis.
Command Claude Code
Automatically select optimal workflow based on task type.
Command Claude Code
Command "benchmark" from ruvnet/ruv-FANN, covering performance benchmarking, mcp tool usage in claude code, parameters, examples and benchmark types.
Command Claude Code
Show Claude-Flow commands and usage.
At most 3 mods per repository are shown here — the rest are on their repository pages: