Braintrust Tracing
This hooks into Claude Code's event system to trace every session, turn, and tool call to Braintrust for debugging and analysis. It captures the full hierarchy of LLM calls, tool executions, and token usage, with special handling for sub-agents (though those currently create orphaned traces you'll need to correlate manually via session IDs). The hook architecture is comprehensive, there are Python scripts to query traces, and the documentation is refreshingly honest about what works and what doesn't. If you're trying to understand why Claude Code made certain decisions or optimize token usage across complex sessions with nested agents, this gives you the visibility you need. The state management is file-based, so you can inspect everything without touching the API.
- skills.sh installs
- 498
- GitHub stars
- 3.9K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add parcadei/continuous-claude-v3 --skill braintrust-tracing --agent claude-codeInstalls into .claude/skills of the current project.
Files
Braintrust Tracing for Claude Code
Comprehensive guide to tracing Claude Code sessions in Braintrust, including sub-agent correlation.
Architecture Overview
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/parcadei/continuous-claude-v3
- Categories
- Code Review & Quality, AI & Agent Building, Debugging
- First seen
- Jun 3, 2026
More from parcadei/continuous-claude-v3
All 108- Opc Architecture497
- Shapely Compute497
- Workflow Router497
- Math Router495
- Recall495
- Mcp Scripts494
- Help493
- Firecrawl Scrape492
- Morph Search492
- Cli Reference491
- Completion Check491
- Idempotent Redundancy491
- Search Tools491
- Skill Upgrader491
- Slash Commands491
- Build490
- Morph Apply489
- Onboard488
- Skill Developer488
- Skill Development488
- Braintrust Analyze487
- Complete Skill487
- Loogle Search487
- Research487
Recommended
More Code Review & Quality
chaos-engineeringalirezarezvani/claude-skillsUse when planning, running, or learning from chaos engineering experiments. Triggers on "chaos experiment", "fault injection", "gameday", "resilience test", "bl497skills.sh installs
research-ideationevoscientist/evoskillsEnd-to-end research ideation pipeline: literature grounding → multi-track idea generation (3 personas: innovator/pragmatist/critic) → iterative refinement → ELO497skills.sh installs
longbridge-performance-attributionlongbridge/skillsPortfolio performance attribution via Longbridge Securities — Brinson industry attribution (allocation / selection / interaction effects), factor alpha/beta dec497skills.sh installs
resolve-agent-reviewspbakaus/agent-reviewsResolve PR review bot findings on current PR. Fetches unanswered bot comments, evaluates each finding, fixes real bugs, dismisses false positives, replies to ev497skills.sh installslongbridge-portfolio-diagnosislongbridge/skillsPortfolio diagnosis via Longbridge — concentration risk (top-5 weight), sector/industry distribution, currency exposure, factor exposure (large/small-cap, value496skills.sh installs
pandocplinde/claude-pluginsThis skill should be used when converting documents between formats (Markdown, DOCX, PDF, HTML, LaTeX, etc.) using pandoc. Use for format conversion, document g495skills.sh installs