
Session Log Search
Search and analyze your past agent conversation logs using jq and ripgrep
- Repository
- spinabot/brigade
- Stars
- 11,367
- Licence
- MIT
- Files
- 1 file
What it does
This skill teaches an AI agent how to dig through the saved transcripts of its earlier conversations, stored as JSONL files on your machine. When you ask about something said in an older or parent chat that isn't in the agent's memory files, the agent runs command-line queries to find the right session, pull out the human-readable messages, search for keywords, and summarize things like message counts, tool usage, and per-session or daily cost.
Great for
- Developers running the Brigade agent who want to audit or recall past conversations
- People who need to find an earlier decision or phrase that was discussed in a previous chat
- Anyone tracking how much their agent sessions cost over time
Skip it if
- Users who do not keep local session logs, since the skill only reads files already on disk
- Sharing or reviewing sensitive chats casually, because the logs contain full conversation text and the agent will read it all
- Non-Brigade agent setups, since the paths and log structure are specific to the Brigade state directory
Try asking
- “Find what we decided about the database migration in our older conversations”
- “Show me the total cost of my sessions from last week”
- “Which tools did the agent use most in session abc123?”
- “Search all my past sessions for the phrase 'API rate limit'”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
session-logs.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip session-logs.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip session-logs.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Name the agent or chat provider (e.g. Discord) and rough date so the agent can narrow the search before reading whole files
- Ask for a short summary rather than raw transcripts when sessions are large, since files can be several MB
- Review any command the agent proposes before approval, because it runs shell commands that read your conversation history
What's inside
- SKILL.md
Redistributed unmodified from spinabot/brigade under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.