feat(skills): add session-logs skill for searching conversation history
Adds jq-based queries for: - Listing sessions by date/size - Searching user/assistant messages - Extracting costs per session and daily totals - Tool usage breakdowns - Cross-session keyword search
This commit is contained in:
95
skills/session-logs/SKILL.md
Normal file
95
skills/session-logs/SKILL.md
Normal file
@@ -0,0 +1,95 @@
|
||||
---
|
||||
name: session-logs
|
||||
description: Search and analyze your own conversation history from session log files using jq.
|
||||
metadata: {"clawdbot":{"emoji":"📜","requires":{"bins":["jq"]}}}
|
||||
---
|
||||
|
||||
# session-logs
|
||||
|
||||
Search your complete conversation history stored in session JSONL files. Use this when you need to recall something not in your memory files.
|
||||
|
||||
## Location
|
||||
|
||||
Session logs live at: `~/.clawdbot/agents/main/sessions/`
|
||||
|
||||
- **`sessions.json`** - Index mapping session keys to session IDs
|
||||
- **`<session-id>.jsonl`** - Full conversation transcript per session
|
||||
|
||||
## Structure
|
||||
|
||||
Each `.jsonl` file contains messages with:
|
||||
- `type`: "session" (metadata) or "message"
|
||||
- `timestamp`: ISO timestamp
|
||||
- `message.role`: "user", "assistant", or "toolResult"
|
||||
- `message.content[]`: Text, thinking, or tool calls
|
||||
- `message.usage.cost.total`: Cost per response
|
||||
|
||||
## Common Queries
|
||||
|
||||
### List all sessions by date and size
|
||||
```bash
|
||||
for f in ~/.clawdbot/agents/main/sessions/*.jsonl; do
|
||||
date=$(head -1 "$f" | jq -r '.timestamp' | cut -dT -f1)
|
||||
size=$(ls -lh "$f" | awk '{print $5}')
|
||||
echo "$date $size $(basename $f)"
|
||||
done | sort -r
|
||||
```
|
||||
|
||||
### Find sessions from a specific day
|
||||
```bash
|
||||
for f in ~/.clawdbot/agents/main/sessions/*.jsonl; do
|
||||
head -1 "$f" | jq -r '.timestamp' | grep -q "2026-01-06" && echo "$f"
|
||||
done
|
||||
```
|
||||
|
||||
### Extract user messages from a session
|
||||
```bash
|
||||
jq -r 'select(.message.role == "user") | .message.content[0].text' <session>.jsonl
|
||||
```
|
||||
|
||||
### Search for keyword in assistant responses
|
||||
```bash
|
||||
jq -r 'select(.message.role == "assistant") | .message.content[]? | select(.type == "text") | .text' <session>.jsonl | grep -i "keyword"
|
||||
```
|
||||
|
||||
### Get total cost for a session
|
||||
```bash
|
||||
jq -s '[.[] | .message.usage.cost.total // 0] | add' <session>.jsonl
|
||||
```
|
||||
|
||||
### Daily cost summary
|
||||
```bash
|
||||
for f in ~/.clawdbot/agents/main/sessions/*.jsonl; do
|
||||
date=$(head -1 "$f" | jq -r '.timestamp' | cut -dT -f1)
|
||||
cost=$(jq -s '[.[] | .message.usage.cost.total // 0] | add' "$f")
|
||||
echo "$date $cost"
|
||||
done | awk '{a[$1]+=$2} END {for(d in a) print d, "$"a[d]}' | sort -r
|
||||
```
|
||||
|
||||
### Count messages and tokens in a session
|
||||
```bash
|
||||
jq -s '{
|
||||
messages: length,
|
||||
user: [.[] | select(.message.role == "user")] | length,
|
||||
assistant: [.[] | select(.message.role == "assistant")] | length,
|
||||
first: .[0].timestamp,
|
||||
last: .[-1].timestamp
|
||||
}' <session>.jsonl
|
||||
```
|
||||
|
||||
### Tool usage breakdown
|
||||
```bash
|
||||
jq -r '.message.content[]? | select(.type == "toolCall") | .name' <session>.jsonl | sort | uniq -c | sort -rn
|
||||
```
|
||||
|
||||
### Search across ALL sessions for a phrase
|
||||
```bash
|
||||
grep -l "phrase" ~/.clawdbot/agents/main/sessions/*.jsonl
|
||||
```
|
||||
|
||||
## Tips
|
||||
|
||||
- Sessions are append-only JSONL (one JSON object per line)
|
||||
- Large sessions can be several MB - use `head`/`tail` for sampling
|
||||
- The `sessions.json` index maps chat providers (discord, whatsapp, etc.) to session IDs
|
||||
- Deleted sessions have `.deleted.<timestamp>` suffix
|
||||
Reference in New Issue
Block a user