memory-status — Claude skill: check agent memory health
Reports how full your project memory is, which topic files exist, and which references point at files that are gone. Useful once the agent starts losing context.
/plugin marketplace add alirezarezvani/claude-skills
/plugin install self-improving-agent@claude-code-skillsWhat memory-status does
The skill walks every memory location in a project: MEMORY.md under the auto-memory directory, CLAUDE.md in the repo root and in ~/.claude/, plus the file count in .claude/rules/. It counts lines, lists topic files, and checks each path referenced in MEMORY.md — missing files get flagged as stale.
Capacity comes with thresholds. Under 120 lines in MEMORY.md is healthy, 120–180 is a warning, past 180 is critical. For CLAUDE.md the marks are 150 and 200. A --brief flag prints a single line, handy for a quick check.
Worth installing if you run long-lived projects in Claude and memory keeps filling up — this tells you what to clean. On a short project with no memory setup, skip it.
What it helps with
- check how many lines MEMORY.md is using
- find references to files that no longer exist
- see which topic files the agent created
- gauge how full CLAUDE.md and project rules are
- get a one-line summary of memory state
Example prompts for the agent
- /si:memory-status
- /si:memory-status --brief
- how full is the project memory right now?
How to install memory-status
1Plugin marketplace
/plugin marketplace add alirezarezvani/claude-skills/plugin install self-improving-agent@claude-code-skillsThis installs the whole self-improving-agent plugin with all its skills
2Skills CLI (Vercel)
npx skills add alirezarezvani/claude-skills --skill memory-status -a claude-code3Manually: put the files in place
~/.claude/skills/memory-status/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/memory-status/
Manually: put the files in place
.agents/skills/memory-status/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/memory-status/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install alirezarezvani/claude-skills memory-status2Manually: put the files in place
.github/skills/memory-status/SKILL.mdPlatform CLI
gemini skills install https://github.com/alirezarezvani/claude-skills --path engineering-team/self-improving-agent/skills/memory-statusManually: put the files in place
.devin/skills/memory-status/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set349
The whole set →Similar
Questions about memory-status
How do I install memory-status in Claude?
Through the plugin marketplace: /plugin marketplace add alirezarezvani/claude-skills, then /plugin install self-improving-agent@claude-code-skills. Or run npx skills add alirezarezvani/claude-skills --skill memory-status -a claude-code.
What does memory-status do?
It gathers memory file stats, counts lines, looks for stale references and duplicates, then reports capacity and recommendations.
What do the status colors mean?
Green is under 60% capacity — plenty of room. Yellow is 60–90%, so run /si:memory-review. Red is above 90%, where auto-memory may start dropping older entries.
Source text
SKILL.md · MIT
---
name: "memory-status"
description: "Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations. Use when the user runs /si:memory-status or asks how full or healthy the agent memory is."
---
# /si:memory-status — Memory Health Dashboard
Quick overview of your project's memory state across all memory systems.
## Usage
```
/si:memory-status # Full dashboard
/si:memory-status --brief # One-line summary
```
## What It Reports
### Step 1: Locate all memory files
```bash
# Auto-memory directory
MEMORY_DIR="$HOME/.claude/projects/$(pwd | sed 's|/|%2F|g; s|%2F|/|; s|^/||')/memory"
# Count lines in MEMORY.md
wc -l "$MEMORY_DIR/MEMORY.md" 2>/dev/null || echo "0"
# List topic files
ls "$MEMORY_DIR/"*.md 2>/dev/null | grep -v MEMORY.md
# CLAUDE.md
wc -l ./CLAUDE.md 2>/dev/null || echo "0"
wc -l ~/.claude/CLAUDE.md 2>/dev/null || echo "0"
# Rules directory
ls .claude/rules/*.md 2>/dev/null | wc -l
```
### Step 2: Analyze capacity
| Metric | Healthy | Warning | Critical |
|--------|---------|---------|----------|
| MEMORY.md lines | < 120 | 120-180 | > 180 |
| CLAUDE.md lines | < 150 | 150-200 | > 200 |
| Topic files | 0-3 | 4-6 | > 6 |
| Stale entries | 0 | 1-3 | > 3 |
### Step 3: Quick stale check
For each MEMORY.md entry that references a file path:
```bash
# Verify referenced files still exist
grep -oE '[a-zA-Z0-9_/.-]+\.(ts|js|py|md|json|yaml|yml)' "$MEMORY_DIR/MEMORY.md" | while read f; do
[ ! -f "$f" ] && echo "STALE: $f"
done
```
### Step 4: Output
```
📊 Memory Status
Auto-Memory (MEMORY.md):
Lines: {{n}}/200 ({{bar}}) {{emoji}}
Topic files: {{count}} ({{names}})
Last updated: {{date}}
Project Rules:
CLAUDE.md: {{n}} lines
Rules: {{count}} files in .claude/rules/
User global: {{n}} lines (~/.claude/CLAUDE.md)
Health:
Capacity: {{healthy/warning/critical}}
Stale refs: {{count}} (files no longer exist)
Duplicates: {{count}} (entries repeated across files)
{{if recommendations}}
💡 Recommendations:
- {{recommendation}}
{{endif}}
```
### Brief mode
```
/si:memory-status --brief
```
Output: `📊 Memory: {{n}}/200 lines | {{count}} rules | {{status_emoji}} {{status_word}}`
## Interpretation
- **Green (< 60%)**: Plenty of room. Auto-memory is working well.
- **Yellow (60-90%)**: Getting full. Consider running `/si:memory-review` to promote or clean up.
- **Red (> 90%)**: Near capacity. Auto-memory may start dropping older entries. Run `/si:memory-review` now.
## Tips
- Run `/si:memory-status --brief` as a quick check anytime
- If capacity is yellow+, run `/si:memory-review` to identify promotion candidates
- Stale entries waste space — delete references to files that no longer exist
- Topic files are fine — Claude creates them to keep MEMORY.md under 200 lines
© Alireza Rezvani · MIT · alirezarezvani/claude-skills