Browsing Tag
Claude Code
23 posts
How to install Agent Skills for Claude Code safely
Install Agent Skills for Claude Code safely: Skill Advisor scores each skill out of 100 and checks it before writing. Free, MIT, built by our team.
Observal AI coding agent observability: sessions and traces
Observal AI coding agent observability: replayable sessions, hooks, install per the README, limits, missing evaluation and how to monitor the server.
AI Observer coding assistants: local costs and traces
AI Observer coding assistants: track tokens, costs and traces from Claude Code, Codex and Gemini locally with Docker, and lock down access.
Worktrunk git worktree: a CLI for parallel coding agents
Worktrunk git worktree: a Rust CLI to run coding agents in parallel, with installation, hooks, limits and what you can observe through its logs.
CLAUDE.md Karpathy: measuring its effect on a coding agent
CLAUDE.md Karpathy: the four-principle file for Claude Code, per its README, and how to measure tokens, iterations and test failures yourself.
Caveman reduce tokens: supervising the cost of an AI agent
Caveman reduce tokens: Apache-2.0 skill and proxy per its README, install steps, limits and the token metrics to supervise for AI agents.
claude-mem persistent agent memory: install and monitor
claude-mem persistent agent memory: install per the README, session compression, context re-injection, token cost and worker health.
ECC agent harness optimization: skills, hooks and security
ECC agent harness optimization: install this MIT repository from its README, cap injected context and measure tokens with OpenTelemetry.
Anthropic financial services agents: structure and monitoring
Anthropic financial services agents: explore the Apache 2.0 repository, its installation and document-reader isolation, with no financial advice given.
Knowledge work plugins Claude Cowork: install and audit
Knowledge work plugins Claude Cowork: install Anthropic's plugins, review their MCP connectors and trace tool calls with OpenTelemetry end to end.