claude-subconscious

claude-subconscious is a plugin for Claude Code from letta-ai/claude-subconscious. Its token cost is not measured, scanned A, original, MIT.

A Claude Code plugin that uses a Letta agent as an additional memory layer. It observes coding sessions, stores accumulated context, and sends guidance back to Claude Code.

In plain words
What is it for?
Use it to add asynchronous memory and guidance to Claude Code sessions through Letta. The input does not describe its exact setup or commands.
Why use it?
It provides background context from earlier work so the coding assistant can receive reminders or suggestions based on the session history.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions Claude Code.

Good fit Use it to add asynchronous memory and guidance to Claude Code sessions through Letta. The input does not describe its exact setup or commands.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add letta-ai/claude-subconscious/plugin install claude-subconscious
About the project

Claude Subconscious is a demonstration application that runs a background agent alongside Claude Code, reading session transcripts and project files to build memory and provide guidance. It is intended for experimenting with persistent, behind-the-scenes assistance in coding sessions rather than production use. Its catalogue add-ons extend the Claude Code workflow with hooks and a plugin.

letta-ai/claude-subconscious · 2,888 stars · on GitHub · docs.letta.com

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.

Clone the repo
git clone --depth 1 https://github.com/letta-ai/claude-subconscious

Made for: Claude Code.

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 claude-subconscious

README.md
[![agentmods](https://agentmods.dev/badge/plugins/letta-ai/claude-subconscious/claude-subconscious/github.svg)](https://agentmods.dev/plugins/letta-ai/claude-subconscious/claude-subconscious)
Your own site
<a href="https://agentmods.dev/plugins/letta-ai/claude-subconscious/claude-subconscious"><img src="https://agentmods.dev/badge/plugins/letta-ai/claude-subconscious/claude-subconscious/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 claude-subconscious

Your own site · 80×15
<a href="https://agentmods.dev/plugins/letta-ai/claude-subconscious/claude-subconscious"><img src="https://agentmods.dev/badge/plugins/letta-ai/claude-subconscious/claude-subconscious.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
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.
Security

Grade A, and why

claude-subconscious 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 10d 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.

.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "claude-subconscious",
  "version": "2.1.1",
  "description": "A subconscious for Claude Code. A Letta agent watches your sessions, accumulates context, and whispers guidance back.",
  "author": {
    "name": "Letta",
    "url": "https://letta.com"
  },
  "homepage": "https://github.com/letta-ai/claude-subconscious",
  "repository": "https://github.com/letta-ai/claude-subconscious",
  "license": "MIT",
  "keywords": [
    "letta",
    "subconscious",
    "memory",
    "multi-agent",
    "async",
    "deliberation"
  ]
}
Contents

What it installs

The manifest is a name and a version. 4 hooks travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 20 lines scan A 4a3174474a38

Subscribe to this mod's changes

claude-subconscious is a plugin published in the GitHub repository letta-ai/claude-subconscious (2,888 stars, last pushed 14d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.