Skip to content

Claudescope

v0.11.0 Breaking

This release includes breaking changes for platform teams planning a safe upgrade.

Published 21d AI Coding Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-agents ai-analytics ai-cost-tracking analytics antigravity antigravity-cli
+10 more
claude claude-code codex copilot duckdb julie local-first opencode pi transcripts

Summary

AI summary

Analytics overhaul introduces Overview, Efficiency scorecard, and week‑in‑review Digest views.

Full changelog

0.11.0 — agent-facing access + analytics overhaul

  • claudescope mcp: MCP server over stdio — agents search and read their own
    transcript history (register: claude mcp add claudescope -- claudescope mcp)
  • New read-only CLI subcommands: search, sessions, session, projects,
    analytics, digest — all with --json
  • Analytics reorganized into three views: Overview (+ prompt streak),
    Efficiency (per-agent scorecard: cost, tokens/response, cache, tool-error
    rate, interrupts — n/a instead of fake 0s — plus a per-session grain), and
    a week-in-review Digest with copy-as-Markdown
  • New code-impact index: LOC added/removed per file from every agent's edits
  • Session API: windowed reads, tool-payload caps, plain-text search snippets
View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track Claudescope

Get notified when new releases ship.

Sign up free

About Claudescope

Local, read-only CLI that serves a web UI to browse, search, and analyze AI coding-agent transcripts across Claude Code, Codex, Junie, pi, opencode, and Copilot CLI — sessions merged by working directory, with full-text search and token-cost analytics. npm, cross-platform. MIT.

All releases →

Related context

Beta — feedback welcome: [email protected]