Claude Code mod

cassandra

Remembers the tool calls that already failed, and says so before your agent runs one again unchanged.

Memory & instructions modsValidates on Claude Code 2.1.316 Source

Install

From source
git clone https://github.com/AraneaDev/cassandra.git
claude --plugin-dir ./cassandra/.

The repo has no marketplace file, so load the plugin folder directly with --plugin-dir.

What it can access

Reach
L2Writes or runs: runs processes, writes files, drives Claude, reads files, reads env vars, reads mod state, draws
Sees
compaction, subagent spawns, ? calls
Draws in
Pane
Hooks
session.startsession.endsession.compactagent.spawnsession.appendcommand.runui.renderui.pressui.inputui.focustool.call

From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.

How Claude Code mods work

  • A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
  • It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
  • Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
  • Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Claude Code docs

Details

Folder
.
Author
AraneaDev
License
MIT
Last updated
1 November 2026

FAQ

What is cassandra?

Remembers the tool calls that already failed, and says so before your agent runs one again unchanged. It is a mod for Claude Code, from AraneaDev/cassandra on GitHub.

What can the cassandra mod access?

Its widest reach is "writes or runs" (runs processes, writes files, drives Claude, reads files, reads env vars, reads mod state, draws). It sees compaction, subagent spawns, ? calls. It draws in Pane. Like any mod, it runs with your permissions.

How do I install cassandra?

Clone AraneaDev/cassandra and start Claude Code with --plugin-dir pointing at the mod's folder (.).

More memory & instructions mods

auto-handoff

m2ai-portfolio/claude-mods

Writes a /next handoff automatically once a 1M-token session crosses 300k tokens and before every compaction, so the next session can /prime from it. Never blocks tool calls: goals and loops keep running (pair with autoCompactWindow: 300000). /auto-handoff on|off and threshold <n> are kept across sessions.

Memory & instructions mods

clean-code

ptrzptrz888-create/claude-mods

Setzt Clean-Code-Regeln als Hooks um: Lint-Hinweis nach Code-Änderungen, Referenzordner mit Quellcode der Bibliotheken und Schutz für CLAUDE.md, AGENTS.md und Skills.

Memory & instructions mods/plugin install

auto-handoff

dhrubo55/claude-mods

Writes a handoff by itself shortly before the prompt cache of an idle session expires, while the cache is still warm. Runs its own /auto-handoff:handoff skill and saves its answer under ~/.claude/handoffs, or another installed handoff command you pick once. Nothing in the handoff waits for approval: calls that would prompt are declined, never approved. A row above the prompt counts down; /auto-handoff opens a pane with the timeline, which command runs and why, and buttons to hand off now, pause, re-pick or copy the path.

Memory & instructions mods/plugin install

code-modernization

Borgerod/claude-files-office

Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).

Memory & instructions mods/plugin install

auto-handoff

Amel-DZRV/claude-code-auto-handoff

Shows a context bar with a red handoff mark, the prompt-cache countdown and per-request tokens. When context passes a threshold it writes a handoff summary, clears the session and loads the summary into the fresh one. /keepwarm pings the prompt cache while you are away (pings spend tokens).

Memory & instructions mods/plugin install

code-modernization

mrkhachaturov/ccode-personal-plugins

Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).

Memory & instructions mods

Browse the most popular Claude Code mods, all memory & instructions mods, or the skills and MCP server directories.