A practical walkthrough of the claude-code-hint protocol. When CLAUDECODE is set, have your CLI write a self-closing tag to stderr; Claude Code strips the line before it reaches the model and shows a one-time prompt to install your plugin — but only for plugins in the official Anthropic marketplace.
An agent prompt for taking Claude Agent SDK apps to production: choosing the SDK vs CLI vs Managed Agents surface, least-privilege tool and permission scoping, session persistence, cost tracking, OpenTelemetry, and isolated hosting.
An agent prompt for curating an organization's Agent Skills: reviewing each SKILL.md name and description, scope (personal, project, or plugin) and precedence, per-skill allowed-tools, and whether Claude or the user invokes it.
A practical walkthrough of using Agent Skills in the Claude Agent SDK: how skills are discovered from the filesystem via settingSources, the skills option to enable or filter them, tool access, and troubleshooting discovery.
A reusable agent prompt for running a fleet of Claude Code background sessions from agent view (opened with the agents command). It triages which sessions need input, which are still working, and which have finished, then decides what to dispatch next, which to answer, and which to stop.
A practical walkthrough of building and distributing a Claude Code plugin marketplace.
A practical walkthrough of defining in-process custom tools for the Claude Agent SDK with createSdkMcpServer and the tool helper, wiring them into query via mcpServers, allowing them, error handling, and returning images or structured data.
A practical walkthrough of Claude Code channels: how an MCP-server channel pushes messages, alerts, and webhooks into a running session, how to install and enable Telegram, Discord, or iMessage, sender allowlists, and enterprise controls.
A practical walkthrough of Claude Code checkpointing: how automatic checkpoints capture code before each edit, how to rewind and summarize with /rewind, the difference between restore and summarize, and the limitations you must know before a risky refactor.
A reusable agent prompt that reviews a Claude Code auto mode setup: whether autoMode.environment trusts the right repos, buckets, and domains, how the allow, soft_deny, and hard_deny tiers resolve, and whether $defaults is kept across settings scopes.
An agent prompt for planning an enterprise Claude Code rollout via server-managed settings: permission deny lists, disableBypassPermissionsMode, allowManagedPermissionRulesOnly, managed MCP allow/deny, and forceRemoteSettingsRefresh fail-closed startup.
Source-backed agent that designs safe recurring Claude Code routines, turning a repeated task into a well-scoped, idempotent skill-driven workflow with clear triggers, permissions, and reporting, grounded in the official Claude Code skills docs.
Source-backed agent that coordinates parallel Claude Code sessions across git worktrees, planning isolation, base-branch choice, gitignored-file copying, subagent worktrees, and cleanup so parallel edits do not collide, grounded in the official Claude Code worktrees docs.
A reusable agent prompt that vets a Claude Code plugin or marketplace before a team installs it. It walks source trust, the plugin's Will-install list and bundled components (skills, agents, hooks, MCP servers, commands), the context-window cost, version pinning, and the user/project/local/managed install scope.
A practical walkthrough of structuring CLAUDE.md across a monorepo: how files load up the directory tree and on demand in subdirectories, path-scoped rules, imports, excluding other teams' files, and keeping per-package context lean.
A practical walkthrough of token and spend accounting in the Claude Agent SDK. Read total_cost_usd from the result message, deduplicate parallel tool calls that share an assistant id, break spend down per model with modelUsage, sum cost across query() calls yourself, and read cache_creation/cache_read tokens.
Terminal-based agentic AI coding assistant from Charm that works with many LLM providers, uses LSP and MCP for context, manages per-project sessions, and asks permission before running tools by default.
Open-source infrastructure for securely running AI-generated code in isolated sandboxes that start in milliseconds, with SDKs for Python, TypeScript, and other languages, persistent snapshots, and an optional managed cloud.
A practical walkthrough of Claude Code deep links: the claude-cli:// URL scheme, how to build links with repo, cwd, and prompt parameters, embedding them in runbooks and alerts, and the safety model where prompts are inert until you press Enter.
Open-source infrastructure for running AI-generated code in secure, isolated cloud sandboxes, with Python and JavaScript SDKs, a Code Interpreter package, and self-hosting options.
A practical walkthrough of mirroring Claude Agent SDK session transcripts to external storage: the SessionStore interface, the SessionKey shape, resuming across hosts, reference adapters for S3/Redis/Postgres, and behavior notes.
A practical walkthrough of file checkpointing in the Claude Agent SDK: enabling it, capturing checkpoint UUIDs from user messages, rewinding files by resuming the session, multiple restore points, and the limitations you must know.
Open-source, extensible AI agent that goes beyond code suggestions to install, execute, edit, and test with any LLM, available as a desktop app, CLI, and API with 70+ MCP extensions.
A practical walkthrough of running Claude Code non-interactively with claude -p: bare mode, output formats (text, json, stream-json), JSON schema output, piping stdin, auto-approving tools, and authentication for scripts and CI.
Open-source project behind CodeLayer, an IDE for orchestrating AI coding agents built on Claude Code, with keyboard-first workflows, team context engineering, and parallel Claude Code sessions across worktrees and cloud workers.
Source-backed agent that threat-models an MCP server before it is connected to Claude Code, covering trust verification, tool authority and side effects, prompt injection via tool output, network and credential exposure, and least-privilege mitigations, grounded in the official security docs.
Source-backed Claude Code subagent that reviews MCP tool result sizes against output token budgets, flagging tools that exceed the warning and default limits and recommending pagination, filtering, MAX_MCP_OUTPUT_TOKENS tuning, and per-tool size annotations.
Open-source platform that runs Claude agents in isolated per-session containers, connects them to messaging channels, keeps per-agent memory and scheduled tasks, and routes credentials through a vault so keys never enter containers.
Source-backed agent that reviews the container isolation posture of a NanoClaw deployment, checking filesystem mounts, per-agent scoping, credential vault routing, messaging channel permissions, and scheduled tasks before agents run with real access.
Open-source framework for building internal coding agents that accept tasks via Slack, Linear, or GitHub, execute code changes in isolated cloud sandboxes, and open draft pull requests automatically.
Lightweight, open-source coding agent from OpenAI that runs in your terminal, edits and runs code locally with configurable sandbox and approval modes, and authenticates with a ChatGPT plan or API key.
A practical walkthrough of exporting OpenTelemetry traces, metrics, and events from the Claude Agent SDK: enabling telemetry, configuring OTLP exporters, reading agent spans, linking traces to your app, and controlling sensitive data.
A practical walkthrough of least-privilege permission design in the Claude Agent SDK. Learn the evaluation order (hooks → deny → mode → allow → canUseTool), how allowedTools and disallowedTools differ, the six permission modes, and how to lock an agent to a fixed tool surface with dontAsk.
A practical walkthrough of Claude Code permission modes for teams: what each mode allows, how to switch and default them, protected paths, and how administrators enforce or lock modes with managed settings.
Source-backed agent that reviews Claude Code plugins for dependency and compatibility issues, checking the plugin.json manifest, bundled components, external binaries like LSP servers, versioning, and namespace conflicts, grounded in the official Claude Code plugin docs.
A practical walkthrough of loading local plugins in the Claude Agent SDK: the plugins option with type local and a path, what plugins bundle (skills, agents, hooks, MCP servers), verifying loads via the init message, and invoking namespaced plugin skills.
Source-backed agent that reduces token cost and latency in Claude Code by improving prompt-cache hit rates, advising on stable context ordering, lean CLAUDE.md, on-demand skills, and MCP tool-search, grounded in the official docs.
A practical walkthrough of managing Claude Code sessions: resuming with --continue, --resume, and --from-pr, naming sessions, using the session picker, branching to try a different approach, and where transcripts are stored.
Source-backed agent that reviews Claude Code's sandboxed Bash configuration for safe boundaries, checking filesystem allow/deny paths, network allowlists, unsandboxed escape hatches, excluded commands, and credential read scope, grounded in the official Claude Code sandboxing docs.
A practical walkthrough of securely deploying Claude Agent SDK applications: the prompt-injection threat model, isolation options (sandbox runtime, containers, gVisor, VMs), least privilege, the proxy credential pattern, and filesystem controls.
A practical walkthrough of slash commands in the Claude Agent SDK. Read the slash_commands array from the system init message, dispatch a command by placing it in the prompt string, handle built-ins like /compact and /clear, and author your own as SKILL.md files with allowed-tools frontmatter.
A practical walkthrough of real-time streaming in the Claude Agent SDK: enabling partial messages, reading StreamEvent text and tool-call deltas, the message flow, and building a streaming UI.
A practical walkthrough of structured outputs in the Claude Agent SDK: defining a JSON Schema via the outputFormat option, reading validated structured_output, type-safe schemas with Zod or Pydantic, and handling validation failures.
A practical walkthrough of subagents in the Claude Agent SDK: defining them programmatically with the agents option and AgentDefinition, context isolation, parallelization, tool restrictions, invocation, and resuming.
Open-source configuration framework that enhances Claude Code with slash commands, specialized agents, behavioral modes, and MCP server integrations for a more structured development workflow.
A practical walkthrough for configuring your terminal to work well with Claude Code: multiline newlines and Shift+Enter, the /terminal-setup command, tmux passthrough and extended keys, notifications, and Vim editor mode.
A practical walkthrough of the Claude Code context window: what consumes it (system prompt, memory, CLAUDE.md, MCP tools, skills, file reads, history), how each piece loads, and how the /context view helps you design leaner prompts and setups.
No reviewed entries yet.