analyst
01Agent Claude Code
Data analyst and market researcher — analyzes data, creates reports, market research. Use for analysis tasks.
Agent Claude Code
Data analyst and market researcher — analyzes data, creates reports, market research. Use for analysis tasks.
Agent Claude Code
Code implementation tasks — write features, fix bugs, write tests, refactor. Use for any coding task.
Agent Claude Code
Write or update inline docs, README sections, and API references after a code change. Use when code has been added/modified and the docs need to catch up, or when a module is undocumented.
Agent Claude Code
Diagnose production incidents from logs, metrics, and symptom reports. Trace root cause, propose a fix, and write a short post-mortem. Use when a service is broken, throwing errors, or behaving unexpectedly.
Agent Claude Code
Deep research tasks — web search, multi-source analysis, report writing. Use for any research request that requires thoroughness.
Agent Claude Code
Code and PR reviewer — analyzes code quality, finds bugs, suggests improvements. Use for code review requests.
Agent Claude Code
System administrator — manages services, deploys, troubleshoots infrastructure. Use for ops/infra tasks.
Agent Claude Code
Run test suites, parse failures, and propose fixes. Use when the user wants tests run, when CI is failing, or when a code change needs verification beyond static review.
Agent Claude Code
Technical writer and content creator — documentation, reports, business plans, pitch decks. Use for writing tasks.
Command Claude Code
Composite health audit — skills, services, watchdog, memory index, recent restarts.
Command Claude Code
Run the morning briefing — weather, market overview, system health, upcoming tasks.
Command Claude Code
Dump current context — recent memory, active tasks, in-flight projects — for handoff or review.
Command Claude Code
Scheduled-jobs dashboard — cron, systemd, what ran, what failed, upcoming runs.
Command Claude Code
Write today's daily memory file + send a day-summary message to the user.
Command Claude Code
Switch focus to a project and summarize its live state — branch, changes, recent commits, next steps.
Command Claude Code
Semantic memory/RAG search across memories, transcripts, and cross-agent context.
Command Claude Code
Recap recent activity — what got done, what's in-flight, what's next.
Command Claude Code
Capture a fact to today's daily note (and durable auto-memory if it's lasting).
Command Claude Code
Graceful restart of Claudex with a reason logged to watchdog.log.
Command Claude Code
Commit and push current work with guardrails — branch-safe, secret-safe, conventional message.
Command Claude Code
Force-invoke a specific skill by name, bypassing auto-selection.
Hook Claude Code
One of 3 in settings.json
Runs when a session starts, running an inline shell check. From JansenAnalytics/claudex.
Hook Claude Code
One of 3 in settings.json
Runs when the agent finishes a response, running an inline shell check. From JansenAnalytics/claudex.
Settings file Claude Code
One of 3 in settings.json
Agent settings declaring 2 hook events (SessionStart, Stop) and 6 allowed tools.
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: