From fulcrum
Query Fulcrum memory before writing new code, docs, or architectural decisions. Applies before producing novel output on a topic project may have prior context on.
npx claudepluginhub moabualruz/fulcrum --plugin fulcrumThis skill uses the workspace's default tool permissions.
Fulcrum L2 memory stores prior decisions, outcomes, lessons. Skipping = reinventing wheel, or worse, contradicting a prior agent's decision. Always call `fulcrum action exec recall_memory` before novel output.
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.
Fulcrum L2 memory stores prior decisions, outcomes, lessons. Skipping = reinventing wheel, or worse, contradicting a prior agent's decision. Always call fulcrum action exec recall_memory before novel output.
Short list of search terms drawn from task goal:
fulcrum action exec recall_memory
workspace_id: (same as your run)
query: "plain english what you are about to do"
limit: 5 or 10
Run 2-3 queries, not one:
"{task goal plain english}" — e.g., "reranker tokenizer batching"."{file path or dir}" — e.g., "packages/core/src/memory"."{component or pattern name}" — e.g., "FTS5 fallback", "WIP limiter".Read every returned memory before typing. Single 200-word decision from prior run can save an hour.
Recalled memory changed your approach? Cite:
Refs memory M-0423.complete_agent_run summary: include memory IDs relied on.Creates visible reasoning chain CoS can audit.
recall_memory calls → probably contradicting something.See also: start-every-task, write-memory-on-completion.