agentmods.dev

memory-management

memory-management is a skill for Claude Code from LewenW/claude-memory-bridge. It costs 0 tokens per session (447 once invoked), scanned A, original, MIT.

A shared-memory system for Claude projects, using namespaces like shared folders that selected projects can access. It separates information shared across projects from information kept in one project.

In plain words
What is it for?
Sharing coding conventions, feedback, and reusable project knowledge between Claude projects. It can list shared namespaces and search their stored memories.
Why use it?
It avoids re-explaining general rules, preferences, and decisions in every project. It also makes it clearer which information is global, shared, or project-specific.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Part of the memory-bridge plugin — 1 skill, 6 commands shipped together

not rated 6repo 4mo ago A scan 0 tokens original MIT

Good fit Sharing coding conventions, feedback, and reusable project knowledge between Claude projects. It can list shared namespaces and search their stored memories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lewenw/claude-memory-bridge/memory-management
View source ↗ LewenW/claude-memory-bridge
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 LewenW/claude-memory-bridge --skill memory-management
Clone the repo
git clone --depth 1 https://github.com/LewenW/claude-memory-bridge

Made for: Claude Code.

Or install memory-bridge, the plugin that ships this one along with the rest of its 1 skill, 6 commands.

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 memory-management

README.md
[![agentmods](https://agentmods.dev/badge/skills/lewenw/claude-memory-bridge/memory-management.svg)](https://agentmods.dev/skills/lewenw/claude-memory-bridge/memory-management)
Your own site
<a href="https://agentmods.dev/skills/lewenw/claude-memory-bridge/memory-management"><img src="https://agentmods.dev/badge/skills/lewenw/claude-memory-bridge/memory-management.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 447 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 $0.00000 $0.00447
Opus 5 $0.00000 $0.00224
Sonnet 5 $0.00000 $0.00089
Haiku 4.5 $0.00000 $0.00045

Measured 7d ago against content hash f50c9f98f6ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

memory-management 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 7d 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.

skills/memory-management/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Bridge — Cross-Project Memory Sharing

When to use

  • User mentions something they've "already told Claude" in another project
  • User says "same as in project X" or "like we do in the other project"
  • User sets up conventions that clearly apply across multiple projects
  • Session start: check if current project subscribes to any shared namespaces

How it works

This plugin provides shared memory across Claude projects via namespaces. Think of namespaces like shared folders that multiple projects can subscribe to.

Three-layer model:

  • Global (~/.claude/CLAUDE.md) — loaded everywhere (Claude native)
  • Namespace (~/.claude/shared-memory/<ns>/) — opt-in shared layer (memory-bridge)
  • Project (~/.claude/projects/<project>/memory/) — project-only (Claude native)

At session start

  1. Use manage_namespaces(action="list") to check available namespaces
  2. Use search_memories(query="...", scope="shared") to find relevant shared knowledge
  3. If no namespaces exist yet, mention memory-bridge is available

When user teaches something generalizable

If the user provides feedback or corrections applicable beyond this project (coding style, tool preferences, team conventions), suggest: "This seems useful across projects. Want me to save it to a shared namespace so your other projects can use it too?"

Then use promote_memory to save it.

Available tools

  • search_memories — Search across all projects and shared namespaces
  • promote_memory — Move a project memory to a shared namespace
  • list_shared_memories — View what's in shared namespaces
  • sync_memory — Copy a memory to specific projects
  • get_memory_health — Check for duplicates, stale memories, stats
  • manage_namespaces — Create/delete namespaces, subscribe/unsubscribe projects

Token efficiency

  • Always pass limit to search to avoid flooding context
  • Prefer list_shared_memories over broad searches for browsing
  • Use get_memory_health sparingly — it scans everything

Read the full file on GitHub · 43 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. 7d ago First seen · 43 lines · 0 tokens per session scan A f50c9f98f6ac

Subscribe to this mod's changes

memory-management is a skill published in the GitHub repository LewenW/claude-memory-bridge (6 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 447 tokens. 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 2026-08-31.

Claude Codeclaudeclaude-mcpcoworkmcpmcp-server
Related

Other skills, from other repositories

chainaware-behavioral-prediction

Use this skill whenever a user asks about wallet safety, fraud risk, rug pull detection, wallet behavior analysis, DeFi personalization, on-chain reputation scoring, AML checks, token ranking by holder quality, airdrop screening, lending risk, token launch auditing, or AI agent trust scoring. Triggers on questions…

ChainAware/behavioral-prediction-mcp · 440 tokens

brw

Automates browser interactions via Chrome DevTools Protocol. Screenshots, clicks, types, navigates, reads page accessibility trees, extracts text, and executes JavaScript in web pages. Use when the user asks to interact with a website, test a web app, fill web forms, scrape web content, or automate browser tasks.

sshh12/claude-plugins · 68 tokens

diy-mcp-connector

Builds a dedicated MCP server for a single web app by walking through API discovery, tool design, security review, implementation, testing, and deployment. Use when the user asks to create an MCP server, connect a web app to Claude Code, or build a tool integration for any web app.

sshh12/claude-plugins · 66 tokens

freetaxusa

Guides users through filing US federal and state taxes on FreeTaxUSA.com using document extraction, tax research, and browser-based form automation. Use when the user asks to file taxes, prepare a tax return, or automate FreeTaxUSA form filling.

sshh12/claude-plugins · 55 tokens

virtualsms-sms-verification

Real SIM-card SMS verification for AI agents via VirtualSMS MCP server. TRIGGERS: SMS verification, OTP code, phone number, virtual number, SIM card, two-factor authentication, account verification, WhatsApp verify, Telegram verify, real SIM, agent phone, MCP SMS, virtualsms. Use when an agent needs to receive an SMS…

virtualsms-io/mcp-server · 106 tokens

build-agent-team

Designs a long-running, autonomous Claude Code agent team for the current project, then writes a /start- -team skill that spawns it. Use when the user asks to build an agent team, multi-agent system, agent crew, agent squad, agent fund, agent org, or wants multiple agents running together with shared tasks and…

sshh12/claude-plugins · 130 tokens