memory-audit
Skill4 starsChanged 4 months agoMITView on GitHub
Самоаудит памяти и состояния агента. Используй когда: (1) user пишет «аудит памяти», «проверь память», «memory-audit», (2) после крупных изменений. Проверяет: memory backend, личную память, скиллы, cron, heartbeat.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- nightscout/AndroidAPStheir own version, first seen Nov 1, 2026
- shakhruz/mila-coretheir own version, first seen Nov 1, 2026
- AcKeskin/contexturetheir own version, first seen Nov 1, 2026
- adamlinscott/claude-skillstheir own version, first seen Oct 30, 2026
- AdityaRon/claude-code-harnesstheir own version, first seen Oct 29, 2026
- baberarjumand/agentic_markdown_memory_agent-skilltheir own version, first seen Oct 13, 2026
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- FastLED/FastLED★ 7.5ksame name
- nightscout/AndroidAPS★ 1.2ksame name
- AdityaRon/claude-code-harness★ 14same name
- mfang0126/openclaw-skills★ 4same name
- adamlinscott/claude-skills★ 3same name
- shakhruz/mila-core★ 3same name
- AcKeskin/contexture★ 2same name
- andreijirohdev-labs/gen-ai-labs★ 1same name
- brenbuilds1/skills★ 1same name
- kaiitunnz/claude-skills★ 1same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository43 other files it gives its agents.
- agent-browserSkill
- agent-introspectionSkill
- agentos-contentSkill
- carousel-instagramSkill
- chat-archiveSkill
- codex-imageSkill
- content-engineSkill
- cross-reviewSkill
- datawrapperSkill
- dev-pipelineSkill
- excalidrawSkill
- fast-loop-codingSkill
- groq-voiceSkill
- higgsfield-generateSkill
- higgsfield-marketplace-cardsSkill
- higgsfield-product-photoshootSkill
- higgsfield-soul-idSkill
- instagram-superpowerSkill
- learningsSkill
- loop-codingSkill
- markdown-newSkill
- mcp-api-buildSkill
- mcp-builderSkill
- miro-boardSkill
- perplexity-researchSkill
- presentSkill
- reel-radarSkill
- reels-analytics-for-brokersSkill
- reelsSkill
- remote-agent-desktopSkill
- security-auditSkill
- senior-brainstormSkill
- seo-tuneSkill
- server-doctorSkill
- telegram-chipSkill
- threads-contentSkill
- topic-monitorSkill
- transcriptSkill
- twitterSkill
- workshopSkill
- youtube-producerSkill
- youtube-thumbnailSkill
- yt-researchSkill
The file
Files
Memory Audit -- Самоаудит (memory backend V2)
DEPRECATED 2026-05-17 — memory backend cutover. Этот скилл построен на your memory backend (your-memory-cli). После hard cutover на gbrain MCP координация переехала в
dashi-gbrain-{tasks,swarm,memory,recall}MCP. Используй MCP tools вместо команд из этого файла. Полный rewrite/удаление — в отдельном wave (см. task #7 staging server). Если ты попал сюда автоматически по триггеру — игнорируй тело и иди вdashi-gbrain-tasks.task_list()/dashi-gbrain-swarm.list_my_pending().
Проверяй факты через shell-команды. Не полагайся на допущения.
Раздел А: memory backend -- единый источник правды
echo "=== memory backend connectivity ==="
# Check memory system health && echo "OK memory backend" || echo "FAIL memory backend"
echo ""
echo "=== Inbox ==="
# Check inbox via your memory system | python3 -c "
import json, sys
data = json.load(sys.stdin)
if isinstance(data, dict):
print(f'{len(data)} сообщений в inbox')
else:
print('inbox пуст или ошибка')" 2>/dev/null
echo ""
echo "=== My tasks ==="
# List tasks via your task system | python3 -c "
import json, sys
tasks = json.load(sys.stdin)
active = [(t.get('status','?'), t.get('title','?'))
for t in tasks.values()
if isinstance(t, dict) and t.get('assignee') == 'your-coordinator'
and t.get('status') not in ('done', None)]
print(f'{len(active)} активных задач')
for s, title in active[:5]:
print(f' [{s}] {title}')" 2>/dev/null
echo ""
echo "=== Agent status ==="
# Get agent status via your memory system | python3 -c "
import json, sys
a = json.load(sys.stdin)
print(f'Status: {a.get(\"status\", \"?\")}')
print(f'LastSeen: {a.get(\"lastSeen\", \"?\")}')
print(f'Heartbeat: {a.get(\"heartbeat\", \"?\")}')" 2>/dev/nullРаздел Б: Личная память (локальная)
WS="~/.claude"
echo "=== Local memory files ==="
for f in \
"$WS/MEMORY.md" \
"$WS/SOUL.md" \
"$WS/memory/hot/HOT_MEMORY.md" \
"$WS/memory/warm/WARM_MEMORY.md" \
"$WS/memory/warm/WATCHLIST.md" \
"$WS/memory/warm/LEARNINGS.md"
do
if [ -f "$f" ]; then
SIZE=$(wc -c < "$f")
echo "OK $(basename $f) -- ${SIZE} bytes"
[ "$SIZE" -gt 8192 ] && echo " WARN: >8KB, approaching rotation"
[ "$SIZE" -gt 10240 ] && echo " CRITICAL: >10KB, flush blocked!"
else
echo "MISSING: $f"
fi
done
echo ""
echo "=== memory backend memory files ==="
for f in "$WS/firebase-mirror/"*.md; do
[ -f "$f" ] && echo "OK $(basename $f)" || echo "MISSING firebase memory"
doneРаздел В: Скиллы -- актуальность
echo "=== Skills referencing deprecated paths ==="
grep -rl "shared-dark-lady\|agent-memory/shared" \
"~/.claude/skills/" 2>/dev/null \
| grep -v ".backup" \
| while read f; do echo "WARN: deprecated path in $f"; done
echo ""
echo "=== Key skills check ==="
for skill in shared-memory firebase-ops claude-code-bridge task-system; do
F="~/.claude/skills/$skill/SKILL.md"
if [ -f "$F" ]; then
if grep -q "your-memory-cli" "$F"; then
echo "OK $skill (uses your-memory-cli)"
else
echo "WARN $skill (no your-memory-cli reference -- outdated?)"
fi
else
echo "MISSING: $skill"
fi
doneРаздел Г: Obsidian sync и cron
echo "=== Cron jobs ==="
crontab -l 2>/dev/null | grep -v "^#" | grep -v "^$"
echo ""
echo "=== Obsidian sync ==="
SYNC="$HOME/scripts/firebase-to-obsidian.sh"
[ -f "$SYNC" ] && echo "OK sync script exists" || echo "MISSING sync script"
HC="$HOME/scripts/firebase-obsidian-healthcheck.sh"
[ -f "$HC" ] && echo "OK healthcheck exists" || echo "MISSING healthcheck"
LOG="$HOME/.logs/obsidian-sync.log"
if [ -f "$LOG" ]; then
LAST=$(tail -1 "$LOG")
echo "Last sync: $LAST"
else
echo "WARN: no sync log"
fi
echo ""
echo "=== Obsidian vault ==="
VAULT="$HOME/Obsidian/<your-vault>"
[ -d "$VAULT/Agents" ] && echo "OK Agents/" || echo "MISSING Agents/"
[ -d "$VAULT/Tasks" ] && echo "OK Tasks/" || echo "MISSING Tasks/"
[ -d "$VAULT/Projects" ] && echo "OK Projects/" || echo "MISSING Projects/"
[ -d "$VAULT/Reference/Backups" ] && echo "OK Backups/" || echo "MISSING Backups/"Раздел Д: Heartbeat
echo "=== Update heartbeat ==="
# Update heartbeat via your memory system \
'{"lastSeen":"'"$(date -Iseconds)"'","status":"online"}' \
&& echo "OK heartbeat updated" || echo "FAIL heartbeat"Финальный отчёт
После выполнения всех проверок составь отчёт:
# Memory Audit Report -- your-coordinator -- YYYY-MM-DD
| Раздел | Статус | Детали |
|--------|--------|--------|
| A. memory backend | OK/WARN/FAIL | connectivity, inbox, tasks |
| Б. Личная память | OK/WARN/FAIL | files, sizes |
| В. Скиллы | OK/WARN | deprecated paths |
| Г. Obsidian sync | OK/WARN/FAIL | cron, vault |
| Д. Heartbeat | OK/FAIL | last update |Если найдены CRITICAL -- сообщи user немедленно.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

