A session-memory add-on for AI coding agents that remembers decisions, fixes, and known pitfalls across Claude Code, Cursor, and Codex, and checks them against Git.

Use it to carry coding decisions, bug fixes, and project-specific warnings between sessions in supported coding agents.

It reduces the need to repeat project context after starting a new session. Git checks help keep remembered information tied to the code history.

claude-rem — Plugin for Claude Code by jatingargiitk: A session-memory add-on for AI coding agents that remembers…

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 jatingargiitk/claude-rem

agentmods

npx agentmods add plugins/jatingargiitk/claude-rem/claude-rem

Clone the repo

git clone --depth 1 https://github.com/jatingargiitk/claude-rem

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/jatingargiitk/claude-rem/claude-rem.svg)](https://agentmods.dev/plugins/jatingargiitk/claude-rem/claude-rem)

Your own site

<a href="https://agentmods.dev/plugins/jatingargiitk/claude-rem/claude-rem"><img src="https://agentmods.dev/badge/plugins/jatingargiitk/claude-rem/claude-rem.svg" alt="Measured on agentmods" 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. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

claude-rem 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 4d 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 · 22 lines

What it actually says

{
  "name": "claude-rem",
  "version": "0.3.3",
  "description": "Session memory for AI coding agents: decisions, fixes, and gotchas remembered across Claude Code, Cursor & Codex, verified against git.",
  "author": {
    "name": "Jatin Garg"
  },
  "repository": "https://github.com/jatingargiitk/claude-rem",
  "homepage": "https://github.com/jatingargiitk/claude-rem#readme",
  "license": "Apache-2.0",
  "keywords": [
    "claude",
    "claude-code",
    "cursor",
    "codex",
    "memory",
    "brain",
    "context",
    "compiled-memory"
  ]
}

Contents

What it installs

The manifest is a name and a version. 2 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.

marketplace.json 440 B

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.

4d ago First seen · 22 lines scan A 1a8dcaa51ada

Subscribe to this mod's changes

claude-rem is a plugin published in the GitHub repository jatingargiitk/claude-rem (4 stars, last pushed 11d 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 2026-08-31.

Memory and context ai-memory claude claude-code claude-code-plugin claude-plugin codex

engram

Durable, local-first graph memory for AI coding assistants: decisions with reasons, gotchas, conflicts — inspectable and editable in a graph pane.

techtheist/engram · not measured

axme-code

(Alpha) Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context — stack, decisions, patterns, safety rules, and a handoff from the previous session.

AxmeAI/axme-code · not measured

memex

Collaborative memory for human-AI work — persistent, searchable, interconnected.

linxule/memex-plugin · not measured

mnemonic

Pure filesystem-based memory system for Claude Code with custom ontology support.

modeled-information-format/mnemonic · not measured

mn

Persistent memory layer for Claude Code and Codex via Obsidian — 7 skills for vault health, knowledge search, verified cross-runtime project recall, connection discovery, session continuity, memory routing, skill-aware session review, and interactive setup. Bundled JSON-stdin atomic vault writer, argv-safe indexed…

jojoprison/mnemo · not measured

second-brain

Agentic workflow with memory and tribal knowledge. Transforms Claude from goldfish to elephant with persistent knowledge across sessions.

sxhmilyoyo/sundayhao-plugins · not measured