Start Debugging

Tag: claude-code

106 posts · Page 10 of 11

2026-05-08 claude-code ai-agents agent-skills

How to Write a Claude Code Subagent That Runs Browser Tests

Build a project-scoped Claude Code subagent that drives Playwright in a real browser, scoped to its own MCP server so the main session never sees the 25 browser_* tools. Covers the .claude/agents/browser-tester.md frontmatter, mcpServers inline definition, allowed tool list, isolation: worktree, the Playwright Test Agents init flow, and the Sonnet-vs-Haiku model choice.

2026-05-07 github-copilot agent-skills ai-agents

How to Give a Copilot Agent Skill Access to Your Repo Conventions

Turn the unwritten rules in your repo into a SKILL.md that GitHub Copilot loads on demand. Frontmatter, descriptions that route, file references, and how to verify it actually fires.

2026-05-05 claude-code ai-agents cli

Claude Code 2.1.128 Loads Plugins From .zip Archives and Stops Dropping Unpushed Commits

Claude Code v2.1.128 (May 4, 2026) ships --plugin-dir support for .zip archives, makes EnterWorktree branch from local HEAD, and stops the CLI from leaking its own OTLP endpoint into Bash subprocesses.

2026-05-05 mcp ai-agents ef-core

How to Expose an EF Core Database to an AI Agent via MCP

Wire an EF Core 10 DbContext into a Model Context Protocol server so Claude Code, Cursor, or any compliant client can run safe, scoped queries against your database. Covers IDbContextFactory lifetime, read-only projections, schema discovery tools, AsNoTracking, parameterised filters, row-level scoping, and the destructive-tool gates you need before letting an agent touch UPDATE.

2026-05-03 claude-code ai-agents cli

Claude Code 2.1.126 Adds `claude project purge` to Wipe All State for a Repo

Claude Code v2.1.126 ships claude project purge, a new CLI subcommand that deletes every transcript, task, file-history entry, and config block tied to a project path in a single shot. Includes --dry-run, --yes, --interactive, and --all.

2026-05-01 claude-code ai-agents github-actions

How to Run Claude Code in a GitHub Action for Autonomous PR Review

Wire up anthropics/claude-code-action@v1 so every pull request gets an autonomous Claude Code review with no @claude trigger. Includes the v1 YAML, claude_args for claude-sonnet-4-6 vs claude-opus-4-7, inline-comment tooling, path filters, REVIEW.md, and the choice between the self-hosted action and the managed Code Review research preview.

2026-04-30 claude-code ai-agents aws-bedrock

Claude Code 2.1.122 Lets You Pick a Bedrock Service Tier From an Env Var

Claude Code v2.1.122 adds the ANTHROPIC_BEDROCK_SERVICE_TIER environment variable, sent as the X-Amzn-Bedrock-Service-Tier header. Set it to flex for a 50 percent discount on agent calls or priority for faster responses, without touching SDK code.

2026-04-29 mcp claude-cowork claude-code

cowork-terminal-mcp: Host Terminal Access for Claude Cowork in One MCP Server

cowork-terminal-mcp v0.4.1 bridges Claude Cowork's sandboxed VM to your host shell. One tool, stdio transport, hard-pinned Git Bash on Windows.

2026-04-29 claude-code ai-agents cli

Export Claude Code Conversations to PDF With jsonl-to-pdf

A practical guide to turning the JSONL files Claude Code writes under ~/.claude/projects/ into shareable PDFs using jsonl-to-pdf, with sub-agent nesting, secret redaction, compact and dark themes, and CI-friendly batch recipes.

2026-04-29 llm ai-agents anthropic-sdk

How to Add Prompt Caching to an Anthropic SDK App and Measure the Hit Rate

Add prompt caching to a Python or TypeScript Anthropic SDK app, place cache_control breakpoints correctly, and read cache_read_input_tokens and cache_creation_input_tokens to compute a real hit rate. With pricing math for Claude Sonnet 4.6 and Opus 4.7.