Build Interactive 3D Worlds With GPT-6 & Blender
Inspect Claude Code transcripts to see which files, tools, and tokens are filling the context window.

Status
In Progress
Tier
Free
Platform
Web
Host
ctx.developersdigest.tech
Inspect Claude Code transcripts to see which files, tools, and tokens are filling the context window. Built and maintained by Developers Digest, ctx-peek is part of a larger ecosystem of 91 AI agent tools, Claude Code tools, MCP servers, and developer agents.
Anthropic shipped Claude Opus 5.5 on September 22, 2026: Fable 5.1-level performance on most work at $4/$20 per million tokens (40% cheaper than Opus 5), cache reads down 60% to $0.20, output 30% faster. Benchmarks, decision guide, and the OpenCode setup.
Agent Retrieval Bench isolates the part of coding-agent work most evals hide: did the agent find the right repository files before it started editing?
An audit of three deployed AI scribes found one note in three carries a verified failure, and the dominant error is omission: information the clinician encounter established that the note never records. The standard fix, an LLM judge reading the note against the transcript, is near coin-flip at detecting exactly that class - judges verify presence, not absence. The fix is not a better judge. It is a restructured task: enumerate the facts, then check each one.
TypeSafe's Jev is the first 'System One' model: no text generation, typed decisions with calibrated probabilities, 70-500ms responses, and $0.042 per million input tokens. Benchmarks, pricing, and the API.
Every coding agent in one window. Stop alt-tabbing between Claude, Codex, and Cursor.
See exactly what your agent did, locally. No cloud, no signup.
One CLI to install, configure, and update every DD tool.
Turn a one-liner into a working Claude Code skill. From idea to installed in a minute.