Key fact
No upload endpoint
The transcript pages use browser APIs to read files locally. They do not require accounts or server storage.
Free local tools
Inspect Claude transcripts in your browser.
Convert local JSONL into a readable timeline, estimate token usage with a dated pricing table, or export an agent-run audit note. No backend, no signup, no transcript upload.
claude code session logs, jsonl transcript viewer
Claude Code Session Log Viewer
Drop a Claude Code JSONL transcript and turn it into a readable local timeline of messages, tool calls, tool results, and token fields.
- Input
- Claude Code .jsonl transcript file
- Output
- Readable timeline, record summary, usage totals, and Markdown export
claude code token usage
Claude Code Token Usage Analyzer
Estimate Claude Code transcript token usage and cost by turn with a dated model pricing table and CSV export.
- Input
- Claude Code .jsonl transcript file with usage fields
- Output
- Token totals, estimated cost, top expensive turns, and CSV export
agent observability checklist
Agent Run Audit Checklist
Run an interactive agent-session audit checklist and export a concise Markdown note for PRs, incidents, and handoffs.
- Input
- Session metadata, reviewer notes, and checklist answers
- Output
- Risk score, unresolved findings, and exportable audit note
Related guide pages
Foundation
Session Logs
A source-grounded explanation of Claude Code and Agent SDK session logs, what they contain, and what they do not prove.
Field guide
Transcript Anatomy
How to read Claude JSONL transcript artifacts, hook transcript paths, subagent transcript paths, and stream-json output without mixing them up.
Telemetry
Observability
A practical map of Claude Code and Agent SDK telemetry: traces, metrics, logs, identity attributes, and event analysis.
Controls
Hook Audits
How Claude Code hooks create reliable capture points for prompts, tool calls, stop events, subagents, and policy decisions.