claudemem-orchestration

Name: claudemem-orchestration
Availability: InStock
Author: MadAppGang

Coordinate parallel multi-agent code analyses by sharing claudemem outputs across sessions.

278|29|Updated Nov 4, 2025

Search Tags:#multi-agent #orchestration #consensus #parallel #session #claudemem

Ready to run

npx skills add https://github.com/MadAppGang/claude-code --skill claudemem-orchestration-madappgang

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: claudemem-orchestration
Source: https://github.com/MadAppGang/claude-code/tree/main/plugins/code-analysis/skills/claudemem-orchestration
Command: npx skills add https://github.com/MadAppGang/claude-code --skill claudemem-orchestration-madappgang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill coordinates multi-agent code analyses by sharing claudemem outputs across parallel agents, enabling parallel investigations and consensus-based prioritization while avoiding redundant claudemem runs.

Core Features & Use Cases

Single claudemem run: Run claudemem ONCE to get structural overview and index the codebase, then reuse the results across agents.
Shared output: Write output to a shared file in the session directory so all agents read from the same source.
Parallel investigations: Launch multiple agents in parallel, each reading the shared claudemem output.
Consensus consolidation: Consolidate results with ultrathink-style analysis into a final report.

Quick Start

Create a unique session directory for the orchestration.
Run claudemem --nologo map "query area" --raw to generate a structure map and save it to the shared file.
Launch agents in parallel that read the shared file and write individual analyses.
Consolidate findings into a final consolidated report in the session directory.

Frequently Asked Questions about claudemem-orchestration

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I coordinate multiple agents analyzing the same codebase without running claudemem repeatedly?▼

Multi-agent orchestration shares a single claudemem output across parallel agents through a shared session directory. Run claudemem once to index the codebase, write the structured output to a shared file, then launch agents in parallel to read from that file, eliminating redundant analysis and enabling consensus-based consolidation.

Can I run parallel code analyses with different agent roles on the same codebase?▼

Yes. Create a session directory, generate a shared claudemem map, then launch multiple agents in parallel with role-based prompts and commands. Each agent reads the shared output and writes individual analyses, which consolidate into a final prioritized report.

What's the best way to consolidate findings from multiple parallel agents investigating code?▼

Orchestration consolidates parallel agent findings using ultrathink-style analysis. After agents complete role-based investigations and write results to the session directory, merge findings into a single prioritized action list that reflects consensus across all parallel analyses.

Do I need to run claudemem separately for each agent in a multi-agent analysis?▼

No. Run claudemem once with the --raw flag to generate a structure map, save it to the shared session file, then all parallel agents read from that single output, avoiding redundant claudemem executions.

How does session-based orchestration handle parallel agent execution and result collection?▼

Orchestration establishes a unique session directory per analysis, writes structured claudemem output to shared files within it, launches agents in parallel to read shared data and write individual analyses, then consolidates results into a final report stored in the session directory.