From agent-runway
Check the current Agent Runway status - loaded architectural map, active conventions, module boundaries, and enforcement levels. Use when debugging agent behavior or verifying plugin configuration.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-runway:runway-statusThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read and display the current Agent Runway architectural map to understand what context is being injected into subagents.
Read and display the current Agent Runway architectural map to understand what context is being injected into subagents.
Read the arch-map.json from the plugin data directory:
${CLAUDE_PLUGIN_DATA}/arch-map.json (or check /tmp/agent-runway/arch-map.json as fallback)Display a summary:
If .agent-runway.yml exists in the working directory, also display:
If the arch-map.json does not exist, inform the user that the plugin has not scanned the project yet (happens on SessionStart).
npx claudepluginhub rennf93/agent-runway --plugin agent-runwayAudits agent configuration drift and AI maintainability across instruction surfaces, hooks/MCP, and verifiers. Use for diagnosing Claude/Codex/Pi ignoring instructions or stale verifier output.
Scans ambient context artifacts (CLAUDE.md, memory, local skills, settings hooks) for compatibility with swarm governance, returning a classified report of interference risks.
Audits agent lifecycles in Claude Code plugins, validating execution capabilities against configs via 8 semantic audits on alignments, skill loading, contracts, prompts, tools, dead agents, and patterns. Writes reports to .claude/audits/.