What is claude-smart?

A memory and learning tool for coding agents that turns user corrections into saved preferences and reusable skills for a project or across projects.

It helps maintain personal preferences, project-specific instructions, and shared skills across Claude Code, Codex, and OpenCode.

It reduces repeated corrections by recording how the agent should work and applying that guidance later.

claude-smart — Plugin by ReflexioAI

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.

Claude Code

/plugin marketplace add ReflexioAI/claude-smart

agentmods

npx agentmods add plugins/reflexioai/claude-smart/plugin

Clone the repo

git clone --depth 1 https://github.com/ReflexioAI/claude-smart

Made for: Claude Code.

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. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

claude-smart 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 yesterday.

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.

plugin/.claude-plugin/plugin.json · 26 lines

What it actually says

{
  "name": "claude-smart",
  "version": "0.2.50",
  "description": "Self-improving Claude Code, Codex, and OpenCode plugin that turns corrections into Preferences, Project-specific skills, and Shared skills",
  "author": {
    "name": "Yi Lu"
  },
  "keywords": [
    "claude",
    "claude-code",
    "claude-code-plugin",
    "codex",
    "codex-plugin",
    "opencode",
    "opencode-plugin",
    "memory",
    "agent-memory",
    "plugin",
    "reflexio",
    "self-improvement",
    "self-improving-agents",
    "skills",
    "learning"
  ]
}

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.

yesterday First seen · 26 lines scan A 2da1401fe6c3

Subscribe to this mod's changes

claude-smart is a plugin published in the GitHub repository ReflexioAI/claude-smart (774 stars, last pushed 3d ago), licensed Apache-2.0. 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.

Memory and context ai-agents claude claude-code claude-code-plugin self-improvement self-improving-ai

claude-smart

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

robcsaszar-retrospective

retrospective

skill-evolution

skill-evolution

self-improve

self-improve