project-memory
by Noash · ★ 3 · updated yesterday
A repo's memory/ folder, shared through git: a Haiku agent reads it and returns only what the task needs, another one compacts it
Install
/plugin marketplace add noash-xrc/claude-tools/plugin install project-memory@noash-toolsThen run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.
What it hooks into
From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.
- Events
session.startprompt.composeagent.offer- API calls
$.fs.ancestors$.fs.list$.fs.read- Reach
- level 1 of 3 reads files
Origin
- How it got here
- Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
- Repository
- github.com/noash-xrc/claude-tools
- Path in repo
project-memory- Source commit
886a19dthe exact code the scan read- Author
- Noash @noash-xrc
- License
- MIT
- First published
- Last pushed
- First listed here
Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.
More from noash-xrc/claude-tools
auto-effort
noash-xrc/claude-tools
Picks low, medium or high effort for each prompt, keeping the prompt cache warm
context-meter
noash-xrc/claude-tools
Band above the prompt with model, effort, context fill, rate-limit windows and session cost, cache state
idle-compact
noash-xrc/claude-tools
Compacts an idle session with a large context just before its prompt cache expires, while the summary still reads from cache
output-trimmer
noash-xrc/claude-tools
Trims long Bash output to its start, end and error lines, and saves the full output to a file
reminders
noash-xrc/claude-tools
Claude records unfinished work in Docs/todos.md; /todos shows the open list.
savings-meter
noash-xrc/claude-tools
Keeps a ledger of what output-trimmer, subagent-router and auto-effort save, shown by /savings
subagent-router
noash-xrc/claude-tools
Runs search subagents on Haiku and general-purpose ones on Sonnet, and /orchestrate splits a big task across scout, worker and reviewer subagents