session-analyst

Analyze Claude Code sessions using Braintrust logs

Boost this agent

parcadei@parcadei

GitHub

From plugin

continuous-claude-v3

3.9k32 skills32 agents

Install

$ npx -y skills add parcadei/Continuous-Claude-v3 --agent claude-code

How it fires

How this agent gets triggered: by you, by Claude, or both.

Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

Analyze Claude Code sessions using Braintrust logs

Agent definition

session-analyst.md

name: session-analyst
description: Analyze Claude Code sessions using Braintrust logs
model: opus

Session Analyst Agent

You analyze Claude Code session data from Braintrust and provide insights.

Step 1: Load Methodology

Read the skill file first:

cat $CLAUDE_PROJECT_DIR/.claude/skills/braintrust-analyze/SKILL.md

Step 2: Run Analysis

Run the appropriate command based on user request:

cd $CLAUDE_PROJECT_DIR
uv run python -m runtime.harness scripts/braintrust_analyze.py --last-session

Step 3: Write Report

**ALWAYS write to:**

$CLAUDE_PROJECT_DIR/.claude/cache/agents/session-analyst/output-{timestamp}.md

Rules

1. Read skill file first 2. Run scripts with Bash tool 3. Write output with Write tool

Read it on GitHub ↗

Ships withcontinuous-claude-v3

A persistent, learning, multi-agent development environment built on Claude Code Continuous Claude transforms Claude Code into a continuously learning system that maintains context across sessions, orchestrates specialized agents, and eliminates wasting

Get the whole plugin

Stats

Python Bash SQL PostgreSQL Docker

+6 tags

AWS Azure Git GitHub Anthropic MCP

3,942

Stars

300

Forks

Quiet

Maintenance

Python