Agent Claude Code
A coding helper for understanding a project's overall structure before making changes. It can trace API routes, data schemas, authentication flows, and dependencies between modules.
Agent Claude Code
A coding helper for understanding a project's overall structure before making changes. It can trace API routes, data schemas, authentication flows, and dependencies between modules.
Agent Claude Code
A coding helper for reviewing one function, class, or file at a time. It looks for code-quality issues and possible logic errors, but not security or whole-system architecture.
Agent Claude Code
A coding helper for updating project documentation after implementation work. It examines the changes in the Git version history and writes matching sections for documents such as README files, changelogs, and API references.
Agent Claude Code
A coding agent that carries out clearly specified implementation tasks.
Agent Claude Code
A coding agent that researches a codebase and returns a short summary.
Agent Claude Code
A senior consulting agent for difficult software decisions and reviews.
Agent Claude Code
A coding agent that reviews changes for security problems.
Agent Claude Code
A coding agent that writes tests for changes prepared before they are committed.
Hook Claude Code
Runs when a session starts, executing session-init.sh via bash. From zeuikli/claude-code-workspace.
Hook Claude Code
Runs after instructions files are loaded, executing instructions-loaded.sh. From zeuikli/claude-code-workspace.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing user-prompt-submit.sh via bash. From zeuikli/claude-code-workspace.
Hook Claude Code
Runs when a subagent starts, executing subagent-start.sh. From zeuikli/claude-code-workspace.
Hook Claude Code
Runs when a subagent finishes, executing subagent-stop.sh. From zeuikli/claude-code-workspace.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing pre-commit-review.sh via bash. From zeuikli/claude-code-workspace.
Hook Claude Code
Runs after a tool call finishes for Edit and Write tool calls, executing post-edit.sh via bash. From zeuikli/claude-code-workspace.
Hook Claude Code
Runs before the context is compacted, executing pre-compact.sh via bash. From zeuikli/claude-code-workspace.
Hook Claude Code
Runs after the context is compacted, executing post-compact.sh via bash. From zeuikli/claude-code-workspace.
Hook Claude Code
Runs when the agent finishes a response, executing session-stop.sh via bash. From zeuikli/claude-code-workspace.
Settings file Claude Code
Agent settings declaring 10 hook events (SessionStart, InstructionsLoaded, UserPromptSubmit, SubagentStart).
Skill Claude CodeCodex
A skill for creating Claude Code skills, including their required SKILL.md file and naming and description checks. Progressive disclosure means showing basic guidance first and loading more detail only when needed.
Skill Claude CodeCodex
A mode where multiple worker agents handle parts of a task in parallel and share what they discover.
Skill Claude CodeCodex
A manually run tool for analyzing new articles on the Claude blog, extracting practical insights, and updating workspace settings.
Skill Claude CodeCodex
A report generator for Claude Code session data, covering model usage, tool efficiency, delegated work, and use of TodoWrite, a task-list feature.
Skill Claude CodeCodex
A session-level tracker that calculates token usage and its cost in US dollars, with a before-and-after comparison report.