Skill Claude CodeCodex
Teaches agents how to operate within Open Station — find tasks, execute work, update state, and store artifacts.
Skill Claude CodeCodex
Teaches agents how to operate within Open Station — find tasks, execute work, update state, and store artifacts.
Skill Claude CodeCodex
Supervise active openstation tasks — list in-progress and review tasks, check session health for each, and present actionable recommendations. Use when asked to check on tasks, supervise work, or get a status overview.
Skill Claude CodeCodex
Generate a changelog entry for a new Open Station release from conventional commits and domain-specific categories.
Settings file Claude Code
Agent settings declaring 1 allowed tools.
Agent
../../artifacts/agents/architect.md.
Agent
../../artifacts/agents/author.md.
Agent
../../artifacts/agents/developer.md.
Agent
../../artifacts/agents/devrel.md.
Agent
../../artifacts/agents/project-manager.md.
Agent
../../artifacts/agents/qa.md.
Agent
../../artifacts/agents/researcher.md.
Agent
../../artifacts/agents/technical-writer.md.
Command
Check on a running or completed agent session. $ARGUMENTS = task ID or run ID. Analyzes logs for health, progress, issues, and blockers.
Command
Create an agent spec. $ARGUMENTS is the agent name or role description. Use when user says "create an agent", "add agent X", or "new agent for Y".
Command
Create an alert artifact. $ARGUMENTS is the alert description. Use when user says "create an alert", "add a reminder", "set up a notification", or "schedule an alert".
Command
File a well-structured bug task from a description. $ARGUMENTS is the bug description. Use when user says "file a bug", "this is broken", "X is stale", or reports a defect.
Command
Create a planning note artifact. $ARGUMENTS is the note topic or title. Use when user says "create a note", "add a note about X", or "capture planning notes for Y".
Command
Create a research artifact. $ARGUMENTS is the research topic or question. Use when user says "research X", "investigate Y", or "look into Z".
Command
Create a spec artifact. $ARGUMENTS is the spec topic or design question. Use when user says "create a spec", "write a spec for X", or "design Y".
Command
Mark a task as done. $ARGUMENTS = task name. Use when user says "done task", "complete task", "mark done", or wants to finish a task.
Command
Mark a task as failed with a mandatory reason. $ARGUMENTS = task-name reason... Use when an agent cannot complete a task (max turns exhausted, blocked, missing permissions).
Command
Initialize or update an Open Station project. Runs CLI init for structural setup, then uses LLM understanding to merge upstream template changes into customized agent files without losing local customizations.
Command
List backlog tasks. Shortcut for /openstation.list status:backlog. Use when user asks "what's in the backlog", "pending tasks", or "untriaged tasks".
Command
List all tasks with status, agent, and dates. Supports filters via $ARGUMENTS (e.g., status:ready, agent:researcher). Use when user asks "what tasks exist", "show tasks", "task status", or wants a status overview.