neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
See what your coding agents cost in tokens: skills, context, tools and instruction files, measured where the client reports it and estimated where it does not.
Developer toolsRust · TypeScriptGitHub @GravionLabsOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Analyze local coding-agent sessions (Claude Code, OpenCode, GitHub Copilot): skill usage and token cost, context overhead, cost and efficiency
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
Analyze the local session data of coding agents (Claude Code, OpenCode, GitHub Copilot CLI and Copilot Chat in VS Code) and answer questions such as:
• Which installed skills are actually used, and how many tokens do they cost?
• How much context do tool definitions, MCP servers and instruction files add to every request?
• What do sessions cost per project, branch or issue, and how do the clients compare?Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
Analyze the local session data of coding agents (Claude Code, OpenCode, GitHub Copilot CLI and Copilot Chat in VS Code) and answer questions such as:
• Which installed skills are actually used, and how many tokens do they cost?
• How much context do tool definitions, MCP servers and instruction files add to every request?
• What do sessions cost per project, branch or issue, and how do the clients compare?Read the full README ↗