Knowledge Curate

Phase 2 of the inverted pipeline. Reads <project>/.metadata/plan.json, fans out one source-curator dispatch per sub-question (WebSearch + scoring, then a WebFetch body-pull of each survivor into the shared fetch-cache), and merges the per-sub-question candidate batches into the canonical <project>/.metadata/candidates.json via candidate-store.py append-batch. Each merged candidate carries a fetch sub-object recording cache key / content hash on success or the unavailable reason on a WebFetch miss.

Read ${CLAUDE_PLUGIN_ROOT}/references/inverted-pipeline.md §"Phase 2 — knowledge-curate" once to anchor on the contract.

When to run

• plan.json exists for the project (Phase 1 has run) AND candidates.json does not yet exist (or the user explicitly wants a re-curate)
• User explicitly invokes /cogni-knowledge:knowledge-curate

Never run when

• No plan.json exists at <project_path>/.metadata/ — offer knowledge-plan first.
• No binding.json exists at the resolved knowledge root — offer knowledge-setup first.

Parameters