What is Braintrust Analysis for Claude Code sessions?

It analyzes your Claude Code sessions using Braintrust tracing data to reveal tool usage, patterns, and opportunities for improvement.

What setup is required?

You need BRAINTRUST_API_KEY configured in ~/.claude/.env or project .env and Braintrust tracing enabled via the braintrust-claude-plugin.

Which commands should I start with?

Start with --last-session for a summary, then explore --weekly-summary, --token-trends, --detect-loops, or --replay for specifics.

braintrust-analyze

Scanned

npx machina-cli add skill parcadei/Continuous-Claude-v3/braintrust-analyze --openclaw

Files (1)

SKILL.md

2.7 KB

Braintrust Analysis

Analyze your Claude Code sessions for patterns, issues, and insights using Braintrust tracing data.

When to Use

After completing a complex task (retrospective)
When debugging why something failed
Weekly review of productivity patterns
Finding opportunities to create new skills
Understanding token usage trends

Commands

Run from the project directory:

# Analyze last session - summary with tool/agent/skill breakdown
uv run python -m runtime.harness scripts/braintrust_analyze.py --last-session

# List recent sessions
uv run python -m runtime.harness scripts/braintrust_analyze.py --sessions 5

# Agent usage statistics (last 7 days)
uv run python -m runtime.harness scripts/braintrust_analyze.py --agent-stats

# Skill usage statistics (last 7 days)
uv run python -m runtime.harness scripts/braintrust_analyze.py --skill-stats

# Detect loops - find repeated tool patterns (>5 same tool calls)
uv run python -m runtime.harness scripts/braintrust_analyze.py --detect-loops

# Replay specific session - show full sequence of actions
uv run python -m runtime.harness scripts/braintrust_analyze.py --replay <session-id>

# Weekly summary - daily activity breakdown
uv run python -m runtime.harness scripts/braintrust_analyze.py --weekly-summary

# Token trends - usage over time
uv run python -m runtime.harness scripts/braintrust_analyze.py --token-trends

Options

--project NAME - Braintrust project name (default: agentica)

What You'll Learn

Session Analysis

Tool usage breakdown
Agent spawns (plan-agent, debug-agent, etc.)
Skill activations (/commit, /research, etc.)
Token consumption estimates

Loop Detection

Find sessions where the same tool was called repeatedly, which may indicate:

Stuck in a search loop
Inefficient approach
Opportunity for better tooling

Usage Patterns

Which agents you use most
Which skills get activated
Daily/weekly activity trends

Examples

Quick Retrospective

# What happened in my last session?
uv run python -m runtime.harness scripts/braintrust_analyze.py --last-session

Output:

## Session Analysis
**ID:** `92940b91...`
**Started:** 2025-12-24T01:31:05Z
**Spans:** 14

### Tool Usage
- Read: 4
- Bash: 2
- Edit: 2
...

Find Loops

uv run python -m runtime.harness scripts/braintrust_analyze.py --detect-loops

Weekly Review

uv run python -m runtime.harness scripts/braintrust_analyze.py --weekly-summary

Requirements

BRAINTRUST_API_KEY in ~/.claude/.env or project .env
Braintrust tracing enabled (via braintrust-claude-plugin)

Source

git clone https://github.com/parcadei/Continuous-Claude-v3/blob/main/.claude/skills/braintrust-analyze/SKILL.mdView on GitHub

Overview

Braintrust-analyze scans Claude Code sessions to surface patterns, issues, and insights from Braintrust tracing data. It supports retrospectives, debugging, weekly productivity reviews, and discovering opportunities to create new skills. By aggregating tool usage, agent activations, and token trends, it helps optimize workflows.

How This Skill Works

It ingests Braintrust tracing data from Claude Code sessions to produce structured analyses, including tool usage breakdowns, agent spawns, skill activations, and token estimates. You run predefined harness commands (e.g., --last-session, --weekly-summary, --token-trends) from the project directory to generate reports. The results help detect loops and uncover optimization opportunities.

When to Use It

After completing a complex task (retrospective)
When debugging why something failed
Weekly review of productivity patterns
Finding opportunities to create new skills
Understanding token usage trends

Quick Start

Step 1: Ensure BRAINTRUST_API_KEY is configured in ~/.claude/.env or project .env
Step 2: Run a report, e.g., uv run python -m runtime.harness scripts/braintrust_analyze.py --last-session
Step 3: Review the output to identify patterns and opportunities

Best Practices

Ensure BRAINTRUST_API_KEY is configured in ~/.claude/.env or project .env
Enable Braintrust tracing via braintrust-claude-plugin
Start with --last-session for a quick read, then --weekly-summary for trends
Use --detect-loops to identify repeated tool patterns
Review outputs and map findings to concrete skill improvements

Example Use Cases

Quick Retrospective: Analyze last session with --last-session to see a full session breakdown.
Find Loops: Run --detect-loops to identify repetitive tool usage patterns.
Weekly Review: Use --weekly-summary to track daily/weekly activity trends.
Token Trends: Inspect --token-trends to visualize token usage over time.
Replay a Session: Use --replay <session-id> to show the full sequence of actions.

Frequently Asked Questions

Add this skill to your agents