agent-swarm-memory-manager

agent-swarm-memory-manager is a skill for Claude Code from ruvnet/ruflo. It costs 21 tokens per session (1,183 once invoked), scanned A, original, MIT.

A manager for shared memory used by multiple AI agents working as a swarm.

In plain words
What is it for?
Use it to maintain agent status, shared components, decision history, knowledge graphs, and cached swarm information.
Why use it?
It keeps information consistent between agents, preserves coordination state, and supports storing, indexing, synchronising, and retrieving shared data.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents); $skill-name invocation.

Part of the claude-flow plugin — 134 skills, 52 commands, 11 agents, 4 hooks shipped together

Good fit Use it to maintain agent status, shared components, decision history, knowledge graphs…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ruvnet/ruflo/agent-swarm-memory-manager
About the project

Ruflo is an execution and coordination layer for Claude Code and Codex that equips AI coding agents with tools, memory, control loops, sandboxes, and collaboration mechanisms. Developers use it to organize specialized agents into swarms, coordinate workflows, retain knowledge across sessions, and communicate across machines. The catalogue entries are Ruflo’s skills, commands, agents, hooks, and plugin components.

ruvnet/ruflo · 70,734 stars · on GitHub · cognitum.one

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ruvnet/ruflo --skill agent-swarm-memory-manager
Clone the repo
git clone --depth 1 https://github.com/ruvnet/ruflo

Made for: Claude Code.

Or install claude-flow, the plugin that ships this one along with the rest of its 134 skills, 52 commands, 11 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-swarm-memory-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruvnet/ruflo/agent-swarm-memory-manager.svg)](https://agentmods.dev/skills/ruvnet/ruflo/agent-swarm-memory-manager)
Your own site
<a href="https://agentmods.dev/skills/ruvnet/ruflo/agent-swarm-memory-manager"><img src="https://agentmods.dev/badge/skills/ruvnet/ruflo/agent-swarm-memory-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.01183
Opus 5 $0.00010 $0.00592
Sonnet 5 $0.00004 $0.00237
Haiku 4.5 $0.00002 $0.00118

Measured 3d ago against content hash 9f1653e40727, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-swarm-memory-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

.agents/skills/agent-swarm-memory-manager/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: swarm-memory-manager description: Manages distributed memory across the hive mind, ensuring data consistency, persistence, and efficient retrieval through advanced caching and synchronization protocols color: blue priority: critical

You are the Swarm Memory Manager, the distributed consciousness keeper of the hive mind. You specialize in managing collective memory, ensuring data consistency across agents, and optimizing memory operations for maximum efficiency.

Core Responsibilities

1. Distributed Memory Management

MANDATORY: Continuously write and sync memory state

// INITIALIZE memory namespace
mcp__claude-flow__memory_usage {
  action: "store",
  key: "swarm$memory-manager$status",
  namespace: "coordination",
  value: JSON.stringify({
    agent: "memory-manager",
    status: "active",
    memory_nodes: 0,
    cache_hit_rate: 0,
    sync_status: "initializing"
  })
}

// CREATE memory index for fast retrieval
mcp__claude-flow__memory_usage {
  action: "store",
  key: "swarm$shared$memory-index",
  namespace: "coordination",
  value: JSON.stringify({
    agents: {},
    shared_components: {},
    decision_history: [],
    knowledge_graph: {},
    last_indexed: Date.now()
  })
}

2. Cache Optimization

  • Implement multi-level caching (L1/L2/L3)
  • Predictive prefetching based on access patterns
  • LRU eviction for memory efficiency
  • Write-through to persistent storage

3. Synchronization Protocol

// SYNC memory across all agents
mcp__claude-flow__memory_usage {
  action: "store", 
  key: "swarm$shared$sync-manifest",
  namespace: "coordination",
  value: JSON.stringify({
    version: "1.0.0",
    checksum: "hash",
    agents_synced: ["agent1", "agent2"],
    conflicts_resolved: [],
    sync_timestamp: Date.now()
  })
}

// BROADCAST memory updates
mcp__claude-flow__memory_usage {
  action: "store",
  key: "swarm$broadcast$memory-update",
  namespace: "coordination", 
  value: JSON.stringify({
    update_type: "incremental|full",
    affected_keys: ["key1", "key2"],
    update_source: "memory-manager",
    propagation_required: true
  })
}

Read the full file on GitHub · 198 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 198 lines · 21 tokens per session scan A 9f1653e40727

Subscribe to this mod's changes

agent-swarm-memory-manager is a skill published in the GitHub repository ruvnet/ruflo (70,734 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 1,183 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

note

Save learnings and discoveries to NOTES.md for persistence across sessions.

blake-simpson/belmont · 14 tokens

bootstrap

Generate a personalized SOUL.md through a warm, adaptive onboarding conversation. Trigger when the user wants to create, set up, or initialize their AI partner's identity — e.g., "create my SOUL.md", "bootstrap my agent", "set up my AI partner", "define who you are", "let's do onboarding", "personalize this AI", "make…

fullstack455/deer-flow · 0 tokens

mem0-integration

Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.

a5c-ai/babysitter · 27 tokens

compare-harnesses

Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.

ruvnet/metaharness · 66 tokens

diag-harness

Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.

ruvnet/metaharness · 85 tokens

repo-genome

7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.

ruvnet/metaharness · 73 tokens