Skip to main content
command CX Codex

memory · hoangsonww — Claude Code command: what it does, how to install

Lists file-based memory stores and CLAUDE.md files grouped by project via the Agent Monitor dashboard.

MIT ★ 1,198 updated 2026-10-23

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor
/plugin install ccam-config@claude-code-agent-monitor-plugins
Open on GitHub

What memory does

The command queries the Agent Monitor Config Explorer API at http://localhost:4820/api/cc-config/memory. It checks user-level and project-level CLAUDE.md files, displaying their sizes in kilobytes and modification timestamps while flagging truncated entries.

It then organizes auto-memory notes by project slug, displaying index files such as MEMORY.md before individual fact files with frontmatter descriptions. Supplying an optional argument filters the project list. The command requires an active dashboard on port 4820; if unreachable, start it using npm start from the repository root.

What it helps with

  • inspect user and project CLAUDE.md file sizes
  • filter auto-memory notes by project name
  • review modification dates of project MEMORY.md index files

Example prompts for the agent

  • /memory
  • /memory backend-service
  • List all auto-memory records using /memory

How to install memory

1Plugin marketplace

/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor
/plugin install ccam-config@claude-code-agent-monitor-plugins

2Manually: put the files in place

.claude/commands/ccam-config-memory.md

The built-in /memory overrides a file with the same name, so the file is renamed. Call it with /ccam-config-memory. For all projects use ~/.claude/commands/

Questions about memory

How to install memory in Claude Code?

Run /plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor first, followed by /plugin install ccam-config@claude-code-agent-monitor-plugins.

What does the memory command do?

It fetches data from http://localhost:4820 and prints a structured view of CLAUDE.md configs and project-specific auto-memory files.

Why does the memory command report an unreachable dashboard?

The tool reads data directly from the local API on port 4820. Start the server by executing npm start from the repository root.

Source text

memory.md · MIT
---
description: List the file-based memory store grouped by project (auto-memory) plus the CLAUDE.md files.
argument-hint: "[project-filter]"
---

List the user's file-based memory store from the Agent Monitor Config Explorer
at `http://localhost:4820`. If **$ARGUMENTS** is given, treat it as a
project-slug filter and show only matching auto-memory groups.

```bash
curl -s http://localhost:4820/api/cc-config/memory
```

The response is `{ items: [...] }`. Two kinds of entry:
- **CLAUDE.md** — `{ scope:"user"|"project", file, size, mtime, preview }`.
- **Auto-memory facts** — `{ scope:"auto-memory", project, name, isIndex, file,
  size, mtime, frontmatter, preview }`.

Print in two parts:

1. **CLAUDE.md** — one line per entry: `scope`, `size` (KB), last-modified.
   Flag any with `truncated: true` as oversized.

2. **Auto-memory, grouped by `project`** — for each project (filtered by
   `$ARGUMENTS` if provided), list the index file (`isIndex: true`, usually
   `MEMORY.md`) first, then each per-fact file with `name`,
   `frontmatter.description` (or start of `preview`), `size` (KB), and `mtime`.

```
Memory store
  CLAUDE.md
    user ..... 8.2 KB   modified 3d ago
    project .. 1.1 KB   modified 1h ago

  Project: -Users-david-WebstormProjects-foo   (4 files)
    MEMORY.md (index) ......... 0.6 KB
    feature_x_decision.md ..... 0.3 KB  — "why we chose X over Y"
    api_quirk.md .............. 0.2 KB  — "endpoint Z returns 200 on error"
```

Cite only fields the API returned — never invent facts, names, or sizes. Note
that auto-memory files are editable via `PUT`/`DELETE /api/cc-config/file`
(a backup is taken automatically) but this command is read-only. If the
dashboard is unreachable, say so and tell the user to start it with `npm start`
from the repo root.

© Son Nguyen · MIT · hoangsonww/Claude-Code-Agent-Monitor

Similar slash commands

All slash commands for Agent setup: memory, context, orchestration →

memory by other authors comes first.

memory 0xSteph Updates the .claude/PROJECT_MEMORY.md file with session decisions and pending tasks without losing past context. CX Codex +1 ★ 2,482repo stars memory sametcelikbicak memory is a Claude Code command for reading, creating, or compacting project memory. It works with files under .team/memory/. CX Codex +1 ★ 71repo stars deep-agents-memory langchain-ai deep-agents-memory — a skill that maps where a Deep Agent keeps its files: thread state, a persistent store, or the real disk. Useful once the agent starts dropping context. CX Codex +1 20,000installs memory-spring-cleaning davila7 memory-spring-cleaning walks through CLAUDE.md and markdown docs, checks the rules written there against the actual code, and drops what no longer holds. CX Codex +1 391installs memory-discipline rohitg00 memory-discipline — a skill for Claude Code, Cursor and other platforms that retrieves prior context at task start, stores decisions the moment they settle, and learns from corrections. CX Codex +1 4,900installs memory-md-management giuseppe-trisciuoglio The memory-md-management skill scans project memory files such as CLAUDE.md, scores them against six criteria and proposes targeted edits. CX Codex +1 3,700installs parallel-memory parallel parallel-memory — a skill that pulls past Parallel Task, Monitor and FindAll runs out of memory when they can help, and removes them on request. CX Codex +1 2,900installs OMEGA Memory omega-memory OMEGA Memory — an MCP server that gives a coding agent long-term memory for decisions, mistakes and task checkpoints, found later by meaning or through the graph. CX Codex +1 2,862installs

From the same set155

The whole set →
workflow workflow pulls one session's stats, complexity score and most frequent tool sequences from the local Agent Monitor dashboard and prints a short summary. CX Codex +1 ★ 1,198repo stars anomalies anomalies spots outlier agent sessions with unusual token spikes or dollar costs using z-score calculations. CX Codex +1 ★ 1,198repo stars insights The insights command reads Agent Monitor data and reports three high-impact findings about Claude Code usage. Use it to spot activity shifts, cache patterns, or API errors. CX Codex +1 ★ 1,198repo stars audit-config audit-config counts what sits in your Claude config per surface and prints one compact table with a short verdict on where things have grown. CX Codex +1 ★ 1,198repo stars compare Compare two sessions by cost and workflow metrics. Use the command to find differences in token use, tool activity, and subagent results. CX Codex +1 ★ 1,198repo stars dag-map dag-map renders the multi-agent orchestration graph for a session: parent-child relationships, depth layers, and fan-out. Use it to understand how agents branch and nest within a session. CX Codex +1 ★ 1,198repo stars productivity-coach productivity-coach reviews Claude Code session patterns via Agent Monitor data to deliver actionable advice on token efficiency and costs. CX Codex ★ 1,198repo stars concurrency-report The concurrency-report skill examines agent concurrency in a session, including lane usage, peak parallel width, and work that ran in sequence. Use it to see how a multi-agent run was scheduled. CX Codex +1 ★ 1,198repo stars

Project sponsors

Companies that keep this analytics open