agentmods.dev

memory-nexus

memory-nexus is a skill for Claude Code from MemoryNexus/memory-nexus-plugins. It costs 0 tokens per session (445 once invoked), scanned A, original, MIT.

A shared memory service for keeping project context between coding-agent sessions. It can store information, search it by meaning, remove saved items, and produce a project briefing.

In plain words
What is it for?
Use it to save decisions and background information, search for earlier project knowledge, and load a briefing with current objectives and instructions.
Why use it?
It reduces the need to repeat project details when starting a new session or switching coding platforms. It also gives you a way to manage and remove stored context.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument; mentions Claude Code; mentions Codex.

Part of the Memory Nexus plugin — 1 skill, 1 hook, 1 MCP server shipped together

not rated 0repo 7mo ago A scan 0 tokens original MIT

Good fit Use it to save decisions and background information, search for earlier project knowledge, and load a briefing with current objectives and instructions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/memorynexus/memory-nexus-plugins/memory-nexus
View source ↗ MemoryNexus/memory-nexus-plugins
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 MemoryNexus/memory-nexus-plugins --skill memory-nexus
Clone the repo
git clone --depth 1 https://github.com/MemoryNexus/memory-nexus-plugins

Made for: Claude Code.

Or install Memory Nexus, the plugin that ships this one along with the rest of its 1 skill, 1 hook, 1 MCP server.

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-nexus

README.md
[![agentmods](https://agentmods.dev/badge/skills/memorynexus/memory-nexus-plugins/memory-nexus/github.svg)](https://agentmods.dev/skills/memorynexus/memory-nexus-plugins/memory-nexus)
Your own site
<a href="https://agentmods.dev/skills/memorynexus/memory-nexus-plugins/memory-nexus"><img src="https://agentmods.dev/badge/skills/memorynexus/memory-nexus-plugins/memory-nexus/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for memory-nexus

Your own site · 80×15
<a href="https://agentmods.dev/skills/memorynexus/memory-nexus-plugins/memory-nexus"><img src="https://agentmods.dev/badge/skills/memorynexus/memory-nexus-plugins/memory-nexus.svg" alt="Reviewed on agentmods" width="80" 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 445 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 $0.00445
Opus 5.5 $0.00000 $0.00178
Sonnet 5.5 $0.00000 $0.00089
Haiku 4.5 $0.00000 $0.00044

Measured 2mo ago against content hash 5949607e1dbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

memory-nexus 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 2mo 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-nexus/SKILL.md · 67 lines

What it actually says

Memory Nexus

Store context, retrieve briefings, and maintain continuity across sessions with Memory Nexus.

Commands

/memory-nexus status

Check your Memory Nexus account status, including active tier and remaining quota.

/memory-nexus status

/memory-nexus search [query]

Search your stored memories by semantic meaning.

/memory-nexus search "how to set up authentication"

/memory-nexus forget [id]

Delete a stored memory by ID.

/memory-nexus forget memory-12345

/memory-nexus briefing

Get a structured briefing including directives, objectives, and contextual knowledge for your current project.

/memory-nexus briefing

/memory-nexus account

Manage your account, view tier, and billing information.

/memory-nexus account

How It Works

When you start a new Claude Code session:

  1. Automatic Detection: The plugin detects your git project and generates a unique hash
  2. Session Start: Memory Nexus retrieves your project's knowledge and context
  3. Briefing Injection: Structured directives, objectives, and knowledge are injected as context
  4. Seamless Continuity: Switch between Claude, Codex, or any other platform using the same API key

Pricing

Tier Cost Monthly Quota
Solo $7/month 50 memories, 10 briefings
Crew $49/month 500 memories, 100 briefings
Fleet $199/month 5000 memories, 1000 briefings

No free tier. No free trial.

Getting Started

  1. Create an account at memory-nexus.org
  2. Generate an API key from your account dashboard
  3. Set MEMORY_NEXUS_API_KEY environment variable
  4. Optionally set MEMORY_NEXUS_API_BASE (defaults to https://api.memory-nexus.org)
  5. Start a new Claude Code session — Memory Nexus will automatically load your project context
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. 2mo ago First seen · 67 lines · 0 tokens per session scan A 5949607e1dbb

Subscribe to this mod's changes

memory-nexus is a skill published in the GitHub repository MemoryNexus/memory-nexus-plugins (0 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 445 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.

Memory and context
Related

memory-nexus compared with skills from other repositories

memory-nexus next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
memory-nexusMemoryNexus/memory-nexus-pluginsSkill07mo agoMITA0Claude Code
knowledge-ingestopenclaw/openclawSkill394ktodayMITA80Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0Skill69k2d agoApache-2.0A217Claude Code, Codex
forgetasgeirtj/system_prompts_leaksSkill71ktodayCC0-1.0A0Claude Code, Codex
Cortexdanielmiessler/LifeOSSkill20k3d agoMITA184Claude Code
memoryopensquilla/opensquillaSkill7.1k2d agoApache-2.0A44Claude Code, Codex
ha-data-storesshiwenwen/hope-agentSkill1.9ktodayMITA115Claude Code, Codex