ワンクリックで
session-logs
Search and analyze your own session logs (older/parent conversations) using jq.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Search and analyze your own session logs (older/parent conversations) using jq.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Generate comprehensive tests for code - unit tests, edge cases, error conditions. Targets 70%+ coverage using Vitest.
Interact with GitHub using the gh CLI. Use gh issue, gh pr, gh run, and gh api for issues, PRs, CI runs, and advanced queries.
Track and summarize per-model usage costs for AI models. Useful for monitoring spending across Claude, GPT, and other providers.
| name | session-logs |
| description | Search and analyze your own session logs (older/parent conversations) using jq. |
| metadata | {"emoji":"📜","category":"debugging","tags":["logs","history","search"],"requires":[{"name":"jq"},{"name":"rg"}]} |
Search your complete conversation history stored in session JSONL files. Use this when a user references older/parent conversations or asks what was said before.
Use this skill when the user asks about prior chats, parent conversations, or historical context that isn't in memory files.
Session logs live at: ~/.endiorbot/sessions/
sessions.json - Index mapping session keys to session IDs<session-id>.jsonl - Full conversation transcript per sessionEach .jsonl file contains messages with:
type: "session" (metadata) or "message"timestamp: ISO timestampmessage.role: "user", "assistant", or "toolResult"message.content[]: Text, thinking, or tool calls (filter type=="text" for human-readable content)message.usage.cost.total: Cost per responsefor f in ~/.endiorbot/sessions/*.jsonl; do
date=$(head -1 "$f" | jq -r '.timestamp' | cut -dT -f1)
size=$(ls -lh "$f" | awk '{print $5}')
echo "$date $size $(basename $f)"
done | sort -r
for f in ~/.endiorbot/sessions/*.jsonl; do
head -1 "$f" | jq -r '.timestamp' | grep -q "2026-02-22" && echo "$f"
done
jq -r 'select(.message.role == "user") | .message.content[]? | select(.type == "text") | .text' <session>.jsonl
jq -r 'select(.message.role == "assistant") | .message.content[]? | select(.type == "text") | .text' <session>.jsonl | rg -i "keyword"
jq -s '[.[] | .message.usage.cost.total // 0] | add' <session>.jsonl
for f in ~/.endiorbot/sessions/*.jsonl; do
date=$(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
jq -s '{
messages: length,
user: [.[] | select(.message.role == "user")] | length,
assistant: [.[] | select(.message.role == "assistant")] | length,
first: .[0].timestamp,
last: .[-1].timestamp
}' <session>.jsonl
jq -r '.message.content[]? | select(.type == "toolCall") | .name' <session>.jsonl | sort | uniq -c | sort -rn
rg -l "phrase" ~/.endiorbot/sessions/*.jsonl
head/tail for samplingsessions.json index maps chat providers to session IDs.deleted.<timestamp> suffixjq -r 'select(.type=="message") | .message.content[]? | select(.type=="text") | .text' ~/.endiorbot/sessions/<id>.jsonl | rg 'keyword'