From fulcrum
Finalize agent run with meaningful summary + changed-file list. When work finishes, handoff, or stopping a run you started.
npx claudepluginhub moabualruz/fulcrum --plugin fulcrumThis skill uses the workspace's default tool permissions.
Finished work → `fulcrum action exec complete_agent_run` with `run_id` from `start_agent_run`. Do not just say "done" + exit. Summary persists as `task_outcome` memory + is primary signal CoS uses for next decision.
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.
Finished work → fulcrum action exec complete_agent_run with run_id from start_agent_run. Do not just say "done" + exit. Summary persists as task_outcome memory + is primary signal CoS uses for next decision.
fulcrum action exec complete_agent_run --json '{
"run_id": "run_123",
"output_summary": "What changed and why.",
"files_changed": ["packages/core/src/memory/recall.ts"],
"tests_passed": 91,
"tests_failed": 0
}'
output_summarySQLITE_ERROR from a MATCH query, not just keyword-specific parse error."files_changedEvery path mutated, relative to workspace root. Feeds reviewer + integration worker. Incomplete list = incomplete reviews.
output_summary <40 chars → almost certainly useless. Expand.files_changed empty but called Edit/Write → tracking bug. Fix before completing.output_summary.See also: write-memory-on-completion, start-every-task.