session-report
Generate an explorable HTML report of Claude Code session usage from local transcripts.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for session-report, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Anthropic's official session-report plugin. It reads local ~/.claude/projects transcripts and produces an explorable HTML report of token usage, cache efficiency, subagents, skills, and the most expensive prompts. Surface is a command that parses local transcript files and writes an HTML artifact.
Key features and capabilities
- Parses local ~/.claude/projects transcripts
- Reports tokens and cache efficiency
- Breaks down subagents and skills
- Highlights most expensive prompts
Use cases
- Understand where a session's token spend went
- Audit cache efficiency across a project