Skill Claude CodeCodex
A durable session-history component that records committed events and rebuilds conversation views for different interfaces.
Skill Claude CodeCodex
A durable session-history component that records committed events and rebuilds conversation views for different interfaces.
Skill Claude CodeCodex
A session-lifecycle component for finding, resuming, archiving, branching, rewinding, searching, and exporting saved conversations.
Skill Claude CodeCodex
A tool platform that defines, registers, authorises, and runs the actions an agent can take, such as file edits, shell commands, browser work, and Git worktrees.
Skill Claude CodeCodex
A browser-automation component that gives each session an isolated Chromium browser for navigating pages, inspecting them, interacting with them, and taking diagnostic screenshots.
Skill Claude CodeCodex
A file-management component for reading, searching, editing, and patching files, including notebooks and files on remote systems.
Skill Claude CodeCodex
An integration layer that turns built-in services and external tool definitions into tools an agent can discover and use.
Skill Claude CodeCodex
Shell and Git worktree support for running commands, managing long-lived processes, and giving sessions isolated working directories. A Git worktree is a separate checkout linked to the same repository.
Skill Claude CodeCodex
A common contract and registry for built-in tools, MCP tools, and agent-facing tools. It validates tool parameters, decides which tools are visible to a model, and stores session artifacts privately.
Skill Claude Code
The controlled path that turns a tool request into an actual side effect, such as editing files or running a command. It coordinates validation, permissions, hooks, approvals, concurrency, file locks, safe retries, verification, and result delivery.
Skill Claude CodeCodex
A shared foundation for configuration, workspace trust, session resources, API contracts, tool access, capacity limits, output flow, and shutdown across the command line, web app, agents, and extensions.
Skill Claude Code
A resource-management layer that limits concurrent sessions, tasks, tools, providers, and browser work. It also controls streamed output and cleans up processes during cancellation or shutdown.
Skill Claude CodeCodex
A configuration system that combines user, project, local, and per-call settings, then saves each field to the correct scope and file. It can rebuild settings for a particular source project.
Skill Claude Code
A permission and workspace-trust system for deciding whether tools, hooks, browser actions, project settings, and sensitive paths may be used. It supports allow, ask, and deny decisions and identifies trusted project sources.
Skill Claude CodeCodex
Shared runtime state and diagnostics for the command line, server, web app, agents, tools, and extensions. It tracks working directories, project roots, session IDs, logs, environment details, and registered projects.
Skill Claude CodeCodex
Shared request and response definitions for the server and web app, with runtime checks for incoming data and cleaned JSON schemas for tools. TypeBox is the library used to describe these data shapes.
Skill Claude CodeCodex
A workspace resource layer that gives each agent session its own fixed view of models, communication styles, hooks, and project instructions. It keeps the project that owns a resource separate from the working directory where files are edited.
MCP server Claude CodeCodexCursor +2
MCP server "mermaid-chart-mcp" as configured in echoVic/mermaid-chart-mcp. Runs locally from the mermaid-chart-mcp npm package.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 30 tokens together
Agent-neutral macOS computer use over MCP.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: