What is project-memory?
project-memory is a Claude Code mod by noash-xrc that a repo's memory/ folder, shared through git: a Haiku agent reads it and returns only what the task needs, another one compacts it. It is listed under Context & memory and has 3 GitHub stars.
| Type | Claude code mod |
|---|---|
| Author | noash-xrc |
| Repository | noash-xrc/claude-tools |
| Popularity | 3 GitHub stars |
| Category | Context & memory |
| Security | Low risk (100/100) |
| Rank | #847 of 5,272 Claude Code mods; #98 in Context & memory |
| License | MIT |
| Last commit | 2026-10-11 |
| Hooks | 3 events |
| Sees | only the events it hooks |
| Draws on | nothing |
Is project-memory safe to install?
project-memory scores 100/100 on the MCPMods security check: Low risk. No checks raised a concern. It passed 8 of 8 checks.
Mod footprints come from claude plugin validate, which lists every event a mod hooks and every API call it makes without running it.
| Check | Result |
|---|---|
| No network access | Pass |
| Starts no processes | Pass |
| Writes no files or config | Pass |
| Doesn't read environment variables | Pass |
| Only sees the events it hooks | Pass |
| Doesn't drive Claude | Pass |
| Passes claude plugin validate | Pass |
| Has an open-source license | Pass |
API calls in its code
| Call | What it means |
|---|---|
$.fs.ancestors | reads files |
$.fs.list | reads files |
$.fs.read | reads files |
How do I install project-memory?
- Check your Claude Code version. Mods need Claude Code 2.1.287 or later and are on by default.
claude --version
- Read its footprint. This lists every event it hooks and every API call it makes, without running it.
git clone https://github.com/noash-xrc/claude-tools claude plugin validate ./claude-tools/project-memory
- Install it. Run this in your terminal, then /reload-plugins in an open session.
claude plugin marketplace add noash-xrc/claude-tools && claude plugin install project-memory@noash-tools
Or ask Claude to set it up
Paste this into Claude Code and it installs project-memory for you:
Install the "project-memory" Claude Code mod from https://github.com/noash-xrc/claude-tools/tree/main/project-memory. Run claude plugin validate on it first and show me what it can access before you enable it.
More from noash-xrc/claude-tools
This repository has 8 Claude Code mods on MCPMods.
- auto-effort: Picks low, medium or high effort for each prompt, keeping the prompt cache warm (Low risk)
- context-meter: Band above the prompt with model, effort, context fill, rate-limit windows and session cost, cache state (Review before installing)
- idle-compact: Compacts an idle session with a large context just before its prompt cache expires, while the summary still reads from c (Review before installing)
- output-trimmer: Trims long Bash output to its start, end and error lines, and saves the full output to a file (Review before installing)
- reminders: Claude records unfinished work in Docs/todos.md; /todos shows the open list. (Review before installing)
- savings-meter: Keeps a ledger of what output-trimmer, subagent-router and auto-effort save, shown by /savings (Low risk)
- subagent-router: Runs search subagents on Haiku and general-purpose ones on Sonnet, and /orchestrate splits a big task across scout, work (Low risk)