From fulcrum
Fetch workspace status at session start — running agents, WIP budget, blocked runs. Before starting new run or responding to user request.
npx claudepluginhub moabualruz/fulcrum --plugin fulcrumThis skill uses the workspace's default tool permissions.
Session start, before `start_agent_run`, call `fulcrum action exec get_workspace_status`. Cheapest way to avoid duplicate work, WIP surprises, stale context.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Automates semantic versioning and release workflow for Claude Code plugins: bumps versions in package.json, marketplace.json, plugin.json; verifies builds; creates git tags, GitHub releases, changelogs.
Session start, before start_agent_run, call fulcrum action exec get_workspace_status. Cheapest way to avoid duplicate work, WIP surprises, stale context.
# Step 1: workspace_id (no params)
fulcrum action exec get_current_context
# Step 2: use returned workspace_id
fulcrum action exec get_workspace_status --json '{"workspace_id":"ws_123"}'
Response:
start_agent_run denied. Pick different role or block with reason "role at WIP limit".reason, consider resolving first.As chief_of_staff, also call fulcrum action exec build_cos_context. Returns curated markdown block (active runs, recent completions, pending blocks, WIP pressure) ready to prepend to next response. Call at session start + before major planning turns. Cheaper than re-deriving state.
start_agent_run without prior get_workspace_status → flying blind. Collect context first next time.See also: start-every-task, block-when-stuck.